{ "title": { "path": "Path of the page URL", "name": "Data name", "database_name": "Database name", "doi": "DOI", "description": "Description of data contents", "files": "Data file", "file_name": "File name", "file_url": "File URL", "file_size": "File size", "togodb_url": "Simple search URL", "data_acquisition": "Data acquisition method", "analysis": "Data analysis method", "data_number": "Number of data entries", "details": "Data detail" }, "data": [ { "path": "en\/metagenomerefdb\/data-1.html", "name": "16S RNA sequence set for metagenomic analysis", "database_name": "16S RNA sequence set for metagenomic analysis", "doi": "10.18908\/lsdba.nbdc02583-001", "description": "A 16S RNA sequence dataset that can be used for metagenomic data analysis by Kraken2. The header of each record in FASTA format file indicates Taxonomy ID, Accession No, and Definition from the left.", "files": [ { "file_name": "16S_kraken2_db_7.fasta.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/metagenomeRefDB\/LATEST\/16S_kraken2_db_7.fasta.gz", "file_size": "148 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "https:\/\/github.com\/bonohu\/SAQE\/blob\/main\/101Kraken2.md", "data_number": "1,153,543", "details": [] }, { "path": "en\/acest\/data-1.html", "name": "AcEST(EST sequences of Adiantum capillus-veneris and their annotation)", "database_name": "AcEST", "doi": "10.18908\/lsdba.nbdc00839-001", "description": "EST sequence of Adiantum capillus-veneris and its annotation (clone ID, library name, Blastx search results, etc.) CSV format text file.", "files": [ { "file_name": "acest_est.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/acest\/LATEST\/acest_est.zip", "file_size": "110MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/archive_acest#en", "data_acquisition": "Capillary sequencer", "analysis": "Functional annotation (Results of blastx search against UniProtKB\/Swiss-Prot and UniProtKB\/TrEMBL databases)", "data_number": "Adiantum capillus-veneris ESTs: 30,540.", "details": [ { "name": "Clone id", "description": "Clone ID of EST sequence of Adiantum capillus-veneris." }, { "name": "Library", "description": "Library name" }, { "name": "Length", "description": "Number of bases" }, { "name": "Definition", "description": "Definition" }, { "name": "Accession", "description": "DDBJ accession number" }, { "name": "Tissue type", "description": "Name of the tissue from which the sequence is derived" }, { "name": "Developmental stage", "description": "Developmental stage" }, { "name": "Sequence(60)", "description": "Nucleotide sequence (line break after 60 characters)" }, { "name": "sequence", "description": "Nucleotide sequence (without line break)" }, { "name": "||Homology search results||", "description": "" }, { "name": "Swiss-Prot (release 56.9)", "description": "Results of blastx search against Swiss-Prot (release 56.9)" }, { "name": "UniProt ID of top hit in Swiss-Prot", "description": "UniProt ID of the hit sequence with the highest score in the blastx search against Swiss-Prot (release 56.9)" }, { "name": "Definition", "description": "Accession and definition of the hit sequence with the highest score in the blastx search against Swiss-Prot (release 56.9). Link to Uniprot is provided in TogoDB." }, { "name": "Align length", "description": "The alignment length between the query and the hit sequence with the highest score in the blastx search against Swiss-Prot (release 56.9)." }, { "name": "Score (bit)", "description": "Score (bit) of the alignment between the query and the hit sequence with the highest score in the blastx search against Swiss-Prot (release 56.9)." }, { "name": "E-value", "description": "E-value of the alignment between the query and the hit sequence with the highest score in the blastx search against Swiss-Prot (release 56.9)." }, { "name": "Report", "description": "Results of blastx search against the UniProtKB\/Swiss-Prot (release 56.9) database." }, { "name": "TrEMBL (release 39.9)", "description": "Results of blastx search against TrEMBL (release 39.9)" }, { "name": "UniProt ID of top hit in TrEMBL", "description": "UniProt ID of the hit sequence with the highest score in the blastx search against TrEMBL (release 39.9)." }, { "name": "Definition", "description": "Accession and definition of the hit sequence with the highest score in the blastx search against TrEMBL (release 39.9). Link to Uniprot is provided in TogoDB." }, { "name": "Align length", "description": "The alignment length between the query and the hit sequence with the highest score in the blastx search against TrEMBL (release 39.9)." }, { "name": "Score (bit)", "description": "Score (bit) of the alignment between the query and the hit sequence with the highest score in the blastx search against TrEMBL (release 39.9)." }, { "name": "E-value", "description": "E-value of the alignment between the query and the hit sequence with the highest score in the blastx search against TrEMBL (release 39.9)." }, { "name": "Report", "description": "Results of blastx search against the UniProtKB\/TrEMBL (release 39.9) database." } ] }, { "path": "en\/acest\/data-2.html", "name": "BlastX Result : Swiss-Prot", "database_name": "AcEST", "doi": "10.18908\/lsdba.nbdc00839-002", "description": "Results of the blastx search of Adiantum capillus-veneris EST (AcEST) sequences against the UniProtKB\/Swiss-Prot (release 56.9) database. The alignment information of each blast-hit is provided on a single line. CSV format text file.", "files": [ { "file_name": "blasthits_sp.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/acest\/LATEST\/blasthits_sp.zip", "file_size": "7.77MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/archive_acest_blasthits_sp#en", "data_acquisition": "blastx search", "analysis": "The blastx search was performed between Adiantum capillus-veneris EST sequences and UniProtKB\/Swiss-Prot database.", "data_number": "282,196 hits", "details": [ { "name": "Query", "description": "Clone ID of Adiantum capillus-veneris EST sequence used for query" }, { "name": "BlastX Hits", "description": "Accession and definition of the hit sequence in the blastx search against the UniProtKB\/Swiss-Prot (release 56.9) database. Link to Uniprot is provided in TogoDB." }, { "name": "Align Length", "description": "The alignment length between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "Bit score", "description": "Score (bit) of the alignment between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "E-value", "description": "E-value of the alignment between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "Report", "description": "Results of blastx search against the UniProtKB\/Swiss-Prot (release 56.9) database." }, { "name": "UniProt ID", "description": "UniProt ID of the above hit sequence" } ] }, { "path": "en\/acest\/data-3.html", "name": "BlastX Result : TrEMBL", "database_name": "AcEST", "doi": "10.18908\/lsdba.nbdc00839-003", "description": "Results of the blastx search of Adiantum capillus-veneris EST (AcEST) sequences against the UniProtKB\/TrEMBL (release 39.9) database. The alignment information of each hit in the Blastx hit list is provided on a single line. CSV format text file.", "files": [ { "file_name": "blasthits_tr.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/acest\/LATEST\/blasthits_tr.zip", "file_size": "7.03MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/archive_acest_blasthits_tr#en", "data_acquisition": "blastx search", "analysis": "The blastx search was performed between Adiantum capillus-veneris EST sequences and the UniProtKB\/TrEMBL database.", "data_number": "303,873 hits", "details": [ { "name": "Query", "description": "Clone ID of Adiantum capillus-veneris EST sequence subjected to the blastX search" }, { "name": "BlastX Hits", "description": "Accession and definition of the hit sequence in the blastx search against the UniProtKB\/TrEMBL (release 39.9) database. Link to Uniprot is provided in TogoDB." }, { "name": "Align Length", "description": "The alignment length between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "Bit score", "description": "Score (bit) of the alignment between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "E-value", "description": "E-value of the alignment between the above hit sequence and an Adiantum capillus-veneris EST sequence" }, { "name": "Report", "description": "Results of blastx search against the UniProtKB\/TrEMBL (release 39.9) database" }, { "name": "UniProt ID", "description": "UniProt ID of the above hit sequence" } ] }, { "path": "en\/acest\/data-4.html", "name": "AcEST Contig", "database_name": "AcEST", "doi": "10.18908\/lsdba.nbdc00839-004", "description": "Information on the contig sequence comprising Adiantum capillus-veneris EST (AcEST). CSV format text file.", "files": [ { "file_name": "acestcontig.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/acest\/LATEST\/acestcontig.zip", "file_size": "1.34MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/archive_acestcontig#en", "data_acquisition": "", "analysis": "", "data_number": "4,298 entries", "details": [ { "name": "Contig ID", "description": "ID of contig sequence of Adiantum capillus-veneris" }, { "name": "Length", "description": "Length of the contig sequence of Adiantum capillus-veneris" }, { "name": "Number of clones", "description": "The number of EST clones constituting the contig sequence of Adiantum capillus-veneris" }, { "name": "Definition", "description": "Definition" }, { "name": "Link to clone list", "description": "In the TogoDB edition, link to a list of EST clones constituting the contig sequence of Adiantum capillus-veneris is provided. It is blank in the downloaded file." }, { "name": "Clone ID", "description": "ID of the EST clone constituting the contig sequence of Adiantum capillus-veneris with link to the AcEST clone information" }, { "name": "Sequence", "description": "Nucleotide sequence" } ] }, { "path": "en\/acest\/data-5.html", "name": "About Libraries", "database_name": "AcEST", "doi": "10.18908\/lsdba.nbdc00839-005", "description": "Information about cDNA library of Adiantum capillus-veneris EST (AcEST). CSV format text file.", "files": [ { "file_name": "acest_library.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/acest\/LATEST\/acest_library.zip", "file_size": "2KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/archive_acest_library#en", "data_acquisition": "", "analysis": "Adiantum capillus-veneris EST library creation information", "data_number": "4 entries", "details": [ { "name": "Name", "description": "Name of Adiantum capillus-veneris EST library" }, { "name": "About", "description": "Adiantum capillus-veneris EST library creation information" }, { "name": "References", "description": "References of creation of Adiantum capillus-veneris EST library" } ] }, { "path": "en\/aoe\/data-1.html", "name": "Gene expression data list", "database_name": "AOE", "doi": "10.18908\/lsdba.nbdc00467-001", "description": "An index of public gene expression database.", "files": [ { "file_name": "aoe_data_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/aoe\/LATEST\/aoe_data_list.zip", "file_size": "9.2 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/aoe_data_list#en", "data_acquisition": "ArrayExpress, Gene Expression Omnibus(GEO), Genomic Expression Archive", "analysis": "", "data_number": "123,756 entries", "details": [ { "name": "PRJID", "description": "BioProject ID of the project where data is obtained" }, { "name": "AEID", "description": "ArrayExpress ID of data\r\n(Link to ArrayExpress in simple search)" }, { "name": "GSE", "description": "GEO SeriesID of data\r\n(Link to GEO in simple search)" }, { "name": "Description", "description": "Data description" }, { "name": "Date", "description": "Data submission date" }, { "name": "ArrayType", "description": "ArrayType" }, { "name": "ArrayGroup", "description": "ArrayType group" }, { "name": "Technology", "description": "Experiment technology" }, { "name": "Instrument", "description": "Instrument name or ID of BioProject entry where instument information is described" }, { "name": "NGSGroup", "description": "Instrument group when NGS is used" }, { "name": "Organisms", "description": "Organisms" }, { "name": "Rep_organism", "description": "Representative of Organisms" } ] }, { "path": "en\/arabidopsis-phenome\/data-1.html", "name": "Observation of Arabidopsis phenotype", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-001", "description": "Observation data are distinguished by phenotype, method of mutation, mutant ID etc., and standardized with appropriate ontology terms. The listed observation data are correspond to original observation data one-to-one,which are presented in databases including Ds tagging line, activation tagging line, and Fox-hunting line.", "files": [ { "file_name": "riken_piam_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/riken_piam_main.zip", "file_size": "367 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/riken_piam_main#en", "data_acquisition": "Ds tagging line, Ac activation tagging line, Fox-hunting line", "analysis": "", "data_number": "14,629 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Image", "description": "Mutant image" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Original data name", "description": "Name in the original database" }, { "name": "Observed phenotype", "description": "Observed phenotype" }, { "name": "Phenotype URI", "description": "Phenotype URI" }, { "name": "Modified gene", "description": "Modified gene" } ] }, { "path": "en\/arabidopsis-phenome\/data-2.html", "name": "Image of Arabidopsis phenotype", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-002", "description": "Mutant images in \"Observation of Arabidopsis phenotype\"", "files": [ { "file_name": "piam_image.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/piam_image.tar.gz", "file_size": "8.4 GB" } ], "togodb_url": "", "data_acquisition": "Ds tagging line, Ac activation tagging line, Fox-hunting line", "analysis": "", "data_number": "7,341 entries", "details": [] }, { "path": "en\/arabidopsis-phenome\/data-3.html", "name": "Plant phenotype", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-003", "description": "Phenotypes mentioned in the presented database, such as \"long leaf\", can be expressed as combinations of \"entity\" and \"quality\". Terms of entities and qualities are expressed with ontology terms, to standardize phenotype information. Entities: Names of organs, tissues, development stages. The vocabulary is defined in Plant Ontology(PO). Qualities: Characteristics, attributes of entities. The vocabulary is defined in Phenotype Ontology(PATO).", "files": [ { "file_name": "riken_piam_phenome.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/riken_piam_phenome.zip", "file_size": "2.3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/riken_piam_phenome#en", "data_acquisition": "Plant Ontology, Phenotype Ontology", "analysis": "", "data_number": "114 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Entity in PO", "description": "Entity (defined in PO)" }, { "name": "Quality in PATO", "description": "Quality (defined in PATO)" }, { "name": "Num of observation data", "description": "The number of entries where the phenotype is used in \"Observation of Arabidopsis phenotype\"" } ] }, { "path": "en\/arabidopsis-phenome\/data-4.html", "name": "Phenotype-gene", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-004", "description": "Combination of phenotype observation and gene modification found by literature curation", "files": [ { "file_name": "cpp_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/cpp_main.zip", "file_size": "39 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/cpp_main#en", "data_acquisition": "Literature", "analysis": "", "data_number": "823 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Reference", "description": "Curated reference" }, { "name": "Reference URI", "description": "Reference URI" }, { "name": "Pheno abnormality", "description": "Pheno abnormality" }, { "name": "Abnormality URI", "description": "Abnormality URI" }, { "name": "Muteted gene", "description": "Muteted gene" } ] }, { "path": "en\/arabidopsis-phenome\/data-5.html", "name": "Phenotype abnormality", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-005", "description": "We have collected various kind of phenotypes, including those of morphology, responsibility to environmental factors. They are standardized by combination of ontology terms and properties. Phenotypes for morphology are standardized using Plant Ontology (PO) or Trait Ontology (TO), with Phenotype Ontology (PATO). PATO is the vocabulary covering terms of characcteristics such as \"large\" and \"long\". PO and TO are the vocabularies covering names of organs and developmental stages. Phenotypes of biochemical characteristics or stress tolerance can be expressed using Gene Ontology (GO), ChEBI etc. Some phenotypes are observed under some specific environements such as \"long-day condition\". Such phenotypes have links to environmental factors standardized and listed in another class.", "files": [ { "file_name": "cpp_abnormality.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/cpp_abnormality.zip", "file_size": "12 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/cpp_abnormality#en", "data_acquisition": "Plant Ontology, Phenotype Ontology", "analysis": "", "data_number": "488 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Experimental condition", "description": "Experimental condition" }, { "name": "Condition URI", "description": "Condition URI" }, { "name": "Quality in PATO", "description": "Quality (defined in PATO)" }, { "name": "In organ named", "description": "In organ named" }, { "name": "In period of", "description": "In period of" }, { "name": "In response to organism", "description": "In response to organism" }, { "name": "In situation of", "description": "In situation of" }, { "name": "After", "description": "After" }, { "name": "Under influence of", "description": "Under influence of" }, { "name": "During process named", "description": "During process named" }, { "name": "Exhibited by", "description": "Exhibited by" }, { "name": "For quantity of", "description": "For quantity of" }, { "name": "For state of", "description": "For state of" }, { "name": "For trait of", "description": "For trait of" }, { "name": "Num of phenotype gene", "description": "The number of entries where the abnormality is used in \"Phenotype-gene\"" } ] }, { "path": "en\/arabidopsis-phenome\/data-6.html", "name": "Experimental Condition", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-006", "description": "Environmental factor necessary to express phenotypes\r\n- Light condition etc.\r\nPlant Environment Ontology (EO) is used for standardization.\r\n- Existence or absence of specified substances\r\nThe focused factors are standardized with ChEBI for substance names, and some properties.", "files": [ { "file_name": "cpp_exp_condition.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/cpp_exp_condition.zip", "file_size": "0.8 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/cpp_exp_condition#en", "data_acquisition": "Plant Environment Ontology, ChEBI", "analysis": "", "data_number": "22 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Description", "description": "Description" }, { "name": "In environment of", "description": "In environment of" }, { "name": "In presence of", "description": "In presence of" }, { "name": "In absense of", "description": "In absense of" }, { "name": "Num of phenotype abnormality", "description": "The number of entries where the condition is used in \"Phenotype abnormality\"" } ] }, { "path": "en\/arabidopsis-phenome\/data-7.html", "name": "Reference", "database_name": "Arabidopsis Phenome Database", "doi": "10.18908\/lsdba.nbdc01509-007", "description": "Literature as evidence of phenotype information", "files": [ { "file_name": "cpp_reference.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/arabid_pheno\/LATEST\/cpp_reference.zip", "file_size": "475 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/cpp_reference#en", "data_acquisition": "Literature", "analysis": "", "data_number": "801 entries", "details": [ { "name": "Entry URI", "description": "Entry URI" }, { "name": "Entry name", "description": "Entry name" }, { "name": "Title", "description": "Title" }, { "name": "Authors", "description": "Authors" }, { "name": "Abstract", "description": "Abstract" }, { "name": "Pubmed ID", "description": "Pubmed ID" }, { "name": "Journal", "description": "Journal" }, { "name": "Volume", "description": "Volume" }, { "name": "Issue", "description": "Issue" }, { "name": "Pages", "description": "Pages" }, { "name": "Publication date", "description": "Publication date" }, { "name": "Num of phenotype gene", "description": "The number of entries where the reference is used in \"Phenotype-gene\"" } ] }, { "path": "en\/astra\/data-1.html", "name": "Locus", "database_name": "ASTRA", "doi": "10.18908\/lsdba.nbdc00371-001", "description": "List of locus and splicing patterns in respective locus", "files": [ { "file_name": "astra_locus.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/astra\/LATEST\/astra_locus.zip", "file_size": "887 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/astra_locus#en", "data_acquisition": "For the five organisms (H. sapiens, M. musculus, D. melanogaster, and A. thaliana, C. elegans) other than O. sativa, cDNA sequences were obtained from UniGene database. For the UniGene cDNAs, we chose those sequences that presumably code for mature protein coding sequences (CDSs) according to the annotation. For O. sativa, a full-length 32 k cDNA clone set and information of coding sequences were obtained from the Laboratory of Gene Expression, Department of Molecular Genetics, National Institute of Agrobiological Sciences (Kikuchi et al., 2003; ftp:\/\/cdna01.dna.affrc.go.jp\/pub\/data\/CURRENT).\r\nThe genomic sequences of H. sapiens, M. musculus, D. melanogaster, and A. thaliana were obtained from NCBI (ftp:\/\/ftp.ncbi.nih.gov\/genomes\/). The genomic sequences of C. elegans and the draft contigs of O. sativa were obtained from Sanger Center (ftp:\/\/ftp.sanger.ac.uk\/pub\/) and TIGR Institute (ftp:\/\/ftp.tigr.org\/pub\/data\/Eukaryotic_Projects\/o_sativa\/annotaion_dbs\/pseudomolecules\/version_3.0\/), respectively.", "analysis": "Genes were identificatified by mapping locus and cDNA annotations", "data_number": "17,034 entries", "details": [ { "name": "Locus ID", "description": "Specific locus ID for this database" }, { "name": "UniGene ID", "description": "UniGene ID" }, { "name": "Species", "description": "Species name" }, { "name": "Chr. No.", "description": "Chromosome No." }, { "name": "Strand", "description": "Strand" }, { "name": "Matched genome", "description": "Definition of the genome sequence matching this locus" }, { "name": "Matched genome (GI)", "description": "Genbank ID of the genome sequence matching this locus" }, { "name": "Matched genome (RefSeq)", "description": "RefSeq ID of the genome sequence matching this locus" }, { "name": "Gene name", "description": "Gene name" }, { "name": "Left", "description": "The left position of this locus onto genome" }, { "name": "Right", "description": "The right position of this locus onto genome" }, { "name": "GO", "description": "Gene Ontology" }, { "name": "Variants", "description": "Number of splicing variants" }, { "name": "Splicing type", "description": "Splicing type (ex. cassette)" } ] }, { "path": "en\/astra\/data-2.html", "name": "cDNA", "database_name": "ASTRA", "doi": "10.18908\/lsdba.nbdc00371-002", "description": "List of cDNA in locus", "files": [ { "file_name": "astra_cdna.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/astra\/LATEST\/astra_cdna.zip", "file_size": "3.3 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/astra_cdna#en", "data_acquisition": "For the five organisms (H. sapiens, M. musculus, D. melanogaster, and A. thaliana, C. elegans) other than O. sativa, cDNA sequences were obtained from UniGene database. For the UniGene cDNAs, we chose those sequences that presumably code for mature protein coding sequences (CDSs) according to the annotation. For O. sativa, a full-length 32 k cDNA clone set and information of coding sequences were obtained from the Laboratory of Gene Expression, Department of Molecular Genetics, National Institute of Agrobiological Sciences (Kikuchi et al., 2003; ftp:\/\/cdna01.dna.affrc.go.jp\/pub\/data\/CURRENT).\r\nThe genomic sequences of H. sapiens, M. musculus, D. melanogaster, and A. thaliana were obtained from NCBI (ftp:\/\/ftp.ncbi.nih.gov\/genomes\/). The genomic sequences of C. elegans and the draft contigs of O. sativa were obtained from Sanger Center (ftp:\/\/ftp.sanger.ac.uk\/pub\/) and TIGR Institute (ftp:\/\/ftp.tigr.org\/pub\/data\/Eukaryotic_Projects\/o_sativa\/annotaion_dbs\/pseudomolecules\/version_3.0\/), respectively.", "analysis": "As the first, mapping between full-length cDNAs and genome sequences by MEGABLAST. Following that, convertion to mapping data into bit arrays, detection of splicing patterns and distribution to the types. Genes were identificatified by cDNA annotations", "data_number": "84,438 entries", "details": [ { "name": "cDNA ID", "description": "Specific cDNA ID for this database" }, { "name": "Locus ID", "description": "Specific locus ID for this database" }, { "name": "Species", "description": "Species name" }, { "name": "Chr. No.", "description": "Chromosome No." }, { "name": "Strand", "description": "Strand" }, { "name": "Gene name", "description": "Gene name" }, { "name": "UniGene ID", "description": "UniGene ID" }, { "name": "cDNA UniGene ID", "description": "UniGene ID of this cDNA" }, { "name": "Genbank accession", "description": "Genbank accession number" }, { "name": "GI", "description": "Genbank ID" }, { "name": "CDS left", "description": "The left position of coding region onto this cDNA" }, { "name": "CDS right", "description": "The right position of coding region onto this cDNA" }, { "name": "Splicing pattern", "description": "Splicing pattern (gene model)" }, { "name": "cDNA sequence length", "description": "cDNA sequence length" }, { "name": "DOU start", "description": "Premature (pseudo) start codon (true) or not (false)" }, { "name": "DOU end", "description": "Premature (pseudo) stop codon (true) or not (false)" }, { "name": "NMD", "description": "Nonsense-mediated mRNA Decay (NMD) might happen (true) or not (false)" }, { "name": "Number of exons", "description": "Number of exons in this variant" }, { "name": "Number of splicing regions", "description": "Number of alternative splicing\/transcriptional initiation regionss" } ] }, { "path": "en\/astra\/data-3.html", "name": "Exon", "database_name": "ASTRA", "doi": "10.18908\/lsdba.nbdc00371-003", "description": "Exons in variants", "files": [ { "file_name": "astra_exon.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/astra\/LATEST\/astra_exon.zip", "file_size": "5.9 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/astra_exon#en", "data_acquisition": "For the five organisms (H. sapiens, M. musculus, D. melanogaster, and A. thaliana, C. elegans) other than O. sativa, cDNA sequences were obtained from UniGene database. For the UniGene cDNAs, we chose those sequences that presumably code for mature protein coding sequences (CDSs) according to the annotation. For O. sativa, a full-length 32 k cDNA clone set and information of coding sequences were obtained from the Laboratory of Gene Expression, Department of Molecular Genetics, National Institute of Agrobiological Sciences (Kikuchi et al., 2003; ftp:\/\/cdna01.dna.affrc.go.jp\/pub\/data\/CURRENT).\r\nThe genomic sequences of H. sapiens, M. musculus, D. melanogaster, and A. thaliana were obtained from NCBI (ftp:\/\/ftp.ncbi.nih.gov\/genomes\/). The genomic sequences of C. elegans and the draft contigs of O. sativa were obtained from Sanger Center (ftp:\/\/ftp.sanger.ac.uk\/pub\/) and TIGR Institute (ftp:\/\/ftp.tigr.org\/pub\/data\/Eukaryotic_Projects\/o_sativa\/annotaion_dbs\/pseudomolecules\/version_3.0\/), respectively.", "analysis": "As the first, mapping between full-length cDNAs and genome sequences by MEGABLAST. Following that, convertion to mapping data into bit arrays, detection of splicing patterns and distribution to the types.", "data_number": "676,111 entries", "details": [ { "name": "Exon ID", "description": "Specific exon ID for this database" }, { "name": "Species", "description": "Species name" }, { "name": "Locus ID", "description": "Specific locus ID for this database" }, { "name": "cDNA ID", "description": "Specific cDNA ID for this database" }, { "name": "Left in cDNA", "description": "The left position of exon onto cDNA" }, { "name": "Right in cDNA", "description": "The right position of exon onto cDNA" }, { "name": "Left in genome", "description": "The left position of exon onto genome" }, { "name": "Right in genome", "description": "The right position of exon onto genome" } ] }, { "path": "en\/astra\/data-4.html", "name": "Splicing pattern", "database_name": "ASTRA", "doi": "10.18908\/lsdba.nbdc00371-004", "description": "The patterns of alternative splicing\/transcriptional initiation", "files": [ { "file_name": "astra_splicing_pattern.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/astra\/LATEST\/astra_splicing_pattern.zip", "file_size": "1.2 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/astra_splicing_pattern#en", "data_acquisition": "For the five organisms (H. sapiens, M. musculus, D. melanogaster, and A. thaliana, C. elegans) other than O. sativa, cDNA sequences were obtained from UniGene database. For the UniGene cDNAs, we chose those sequences that presumably code for mature protein coding sequences (CDSs) according to the annotation. For O. sativa, a full-length 32 k cDNA clone set and information of coding sequences were obtained from the Laboratory of Gene Expression, Department of Molecular Genetics, National Institute of Agrobiological Sciences (Kikuchi et al., 2003; ftp:\/\/cdna01.dna.affrc.go.jp\/pub\/data\/CURRENT).\r\nThe genomic sequences of H. sapiens, M. musculus, D. melanogaster, and A. thaliana were obtained from NCBI (ftp:\/\/ftp.ncbi.nih.gov\/genomes\/). The genomic sequences of C. elegans and the draft contigs of O. sativa were obtained from Sanger Center (ftp:\/\/ftp.sanger.ac.uk\/pub\/) and TIGR Institute (ftp:\/\/ftp.tigr.org\/pub\/data\/Eukaryotic_Projects\/o_sativa\/annotaion_dbs\/pseudomolecules\/version_3.0\/), respectively.", "analysis": "As the first, mapping between full-length cDNAs and genome sequences by MEGABLAST. Following that, convertion to mapping data into bit arrays, detection of splicing patterns and distribution to the types.", "data_number": "156,654 entries", "details": [ { "name": "ID", "description": "ID for splicing pattern" }, { "name": "Species", "description": "Species name" }, { "name": "Locus ID", "description": "Specific locus ID for this database" }, { "name": "Region", "description": "Splicing Region number in this locus" }, { "name": "Splicing pattern", "description": "Splicing pattern number in this locus" }, { "name": "cDNA ID", "description": "Specific cDNA ID for this database" }, { "name": "Splicing left", "description": "The left position of splicing region onto genome" }, { "name": "Splicing right", "description": "The right position of splicing region onto genome" }, { "name": "Splicing pattern", "description": "Splicing pattern represented into bit array.\r\n\"1\" means splicing region." }, { "name": "Splicing type", "description": "Splicing type (ex. cassette)" }, { "name": "NAGNAG", "description": "NAGNAG (6bp acceptor site) or not" } ] }, { "path": "en\/atatlas\/data-1.html", "name": "Main", "database_name": "AT Atlas", "doi": "10.18908\/lsdba.nbdc01162-001", "description": "It is a summary table of achievements in the Technology Development projects of the Targeted Proteins Research Program (TPRP); details of the developed technology, reference information etc.", "files": [ { "file_name": "at_atlas_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/at_atlas\/LATEST\/at_atlas_en.zip", "file_size": "3.75 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/at_atlas_en", "data_acquisition": "", "analysis": "", "data_number": "15 entries", "details": [ { "name": "ID", "description": "ID of the subject (There are one to six technological subjects in a project.)" }, { "name": "Project ID", "description": "ID of the project" }, { "name": "Subject", "description": "Subject in the project" }, { "name": "Project Theme", "description": "Theme of the project" }, { "name": "Principal Investigator", "description": "Principal Investigator of the project" }, { "name": "Affiliation", "description": "Affiliation of the project" }, { "name": "Backgrounds", "description": "Backgrounds of the subject" }, { "name": "Highlights", "description": "Highlights of the subject" }, { "name": "Outline", "description": "Outline of the protocol" }, { "name": "Application", "description": "Project ID (in TPRP) that carried out using the protocol" }, { "name": "Article", "description": "Related paper (In the cases of multiple items, they are arranged in the same order as PubMed ID.)" }, { "name": "PubMed ID", "description": "PubMed ID (In the cases of multiple items, they are arranged in the same order as Article.)" }, { "name": "CSML File", "description": "Name of the diagram data (CMSL file) (Linked to the diagram data in the Simple Search site.)" } ] }, { "path": "en\/atatlas\/data-2.html", "name": "Protein", "database_name": "AT Atlas", "doi": "10.18908\/lsdba.nbdc01162-002", "description": "It is a table of proteins whose structures were solved using method(s) developed in the Technology Development projects of the Targeted Proteins Research Program (TPRP).", "files": [ { "file_name": "at_atlas_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/at_atlas\/LATEST\/at_atlas_protein.zip", "file_size": "1.13 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/at_atlas_protein#en", "data_acquisition": "", "analysis": "", "data_number": "101 entries", "details": [ { "name": "Project ID", "description": "Project ID" }, { "name": "PDB ID", "description": "PDB ID in PDBj" }, { "name": "Protein Name", "description": "Name of the protein" } ] }, { "path": "en\/atatlas\/data-3.html", "name": "PREIMS", "database_name": "AT Atlas", "doi": "10.18908\/lsdba.nbdc01162-003", "description": "It is a table of protocols that were developed in the Technology Development projects of the Targeted Proteins Research Program (TPRP).", "files": [ { "file_name": "at_atlas_preims.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/at_atlas\/LATEST\/at_atlas_preims.zip", "file_size": "5.09 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/at_atlas_preims#en", "data_acquisition": "", "analysis": "", "data_number": "206 entries", "details": [ { "name": "Project ID", "description": "Project ID" }, { "name": "Protocol ID", "description": "Protocol ID in PREIMS (PRotein Experimental Information Management Sysmtem)" }, { "name": "Protocol Name", "description": "Name of the protocol" }, { "name": "Category", "description": "Category of the protocol" }, { "name": "Author", "description": "Author of the protocol" } ] }, { "path": "en\/atatlas\/data-4.html", "name": "Graphical abstract", "database_name": "AT Atlas", "doi": "10.18908\/lsdba.nbdc01162-004", "description": "Graphical abstracts (flow chart) in the Technology Development projects of the Targeted Proteins Research Program (TPRP), which is drawn by use of Cell Illustrator. The graphics are in CSML format. One project includes one to six subject(s), and there is a CSML file for every subject.", "files": [ { "file_name": "at_atlas_csml.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/at_atlas\/LATEST\/at_atlas_csml.zip", "file_size": "1.22 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "15 entries", "details": [] }, { "path": "en\/atatlas\/data-5.html", "name": "Image File", "database_name": "AT Atlas", "doi": "10.18908\/lsdba.nbdc01162-005", "description": "Graphical abstracts (in PNG format) for the Technology Development projects of the Targeted Proteins Research Program (TPRP). One project includes one to six subject(s), and there is a PNG file originally drawn by Cell Illustrator for every subject.", "files": [ { "file_name": "at_atlas_png.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/at_atlas\/LATEST\/at_atlas_png.zip", "file_size": "5.37 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "15 entries", "details": [] }, { "path": "en\/bodyparts3d\/data-1.html", "name": "Table of 3D organ model IDs and organ names (IS-A Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-001", "description": "List of downloadable 3D organ models in a tab-delimited text file format, describing the correspondence between 3D organ model IDs and organ names available in IS-A Tree.", "files": [ { "file_name": "isa_parts_list_e.txt (IS-A Tree)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/isa_parts_list_e.txt", "file_size": "126 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_isa_parts_list_e", "data_acquisition": "", "analysis": "", "data_number": "2,905 entries", "details": [ { "name": "concept id", "description": "ID of the corresponding FMA (Foundational Model of Anatomy)." }, { "name": "representation id", "description": "ID of the corresponding 3D representation." }, { "name": "en", "description": "English name. Basically, a preferred name of FMA is assigned." } ] }, { "path": "en\/bodyparts3d\/data-2.html", "name": "Table of 3D organ model IDs and organ names (PART-OF Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-002", "description": "List of downloadable 3D organ models in a tab-delimited text file format, describing the correspondence between 3D organ model IDs and organ names available in PART-OF Tree.", "files": [ { "file_name": "partof_parts_list_e.txt (PART-OF Tree)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/partof_parts_list_e.txt", "file_size": "58 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_partof_parts_list_e", "data_acquisition": "", "analysis": "", "data_number": "1,368 entries", "details": [ { "name": "concept id", "description": "ID of the corresponding FMA (Foundational Model of Anatomy)." }, { "name": "representation id", "description": "ID of the corresponding 3D representation." }, { "name": "en", "description": "English name. Basically, a preferred name of FMA is assigned." } ] }, { "path": "en\/bodyparts3d\/data-3.html", "name": "Data describing the inclusion relationships between two organs (IS-A Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-003", "description": "File of data describing the inclusion relationships between two organs of the downloadable 3D organ models.", "files": [ { "file_name": "isa_inclusion_relation_list.txt", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/isa_inclusion_relation_list.txt", "file_size": "203 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_isa_inclusion_relation_list#en", "data_acquisition": "", "analysis": "", "data_number": "2,904 entries", "details": [ { "name": "parent id", "description": "Concept ID of parent organ" }, { "name": "parent name", "description": "English name of parent organ" }, { "name": "child id", "description": "Concept ID of an organ that is included in the parent organ" }, { "name": "child name", "description": "English name of an organ that included in the parent organ" } ] }, { "path": "en\/bodyparts3d\/data-4.html", "name": "Data describing the inclusion relationships between two organs (PART-OF Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-004", "description": "File of data describing the inclusion relationships between two organs of the downloadable 3D organ models.", "files": [ { "file_name": "partof_inclusion_relation_list.txt", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/partof_inclusion_relation_list.txt", "file_size": "90 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_partof_inclusion_relation_list#en", "data_acquisition": "", "analysis": "", "data_number": "1,367 entries", "details": [ { "name": "parent id", "description": "Concept ID of parent organ" }, { "name": "parent name", "description": "English name of parent organ" }, { "name": "child id", "description": "Concept ID of an organ that is included in the parent organ" }, { "name": "child name", "description": "English name of an organ that included in the parent organ" } ] }, { "path": "en\/bodyparts3d\/data-5.html", "name": "Data describing the definition of compound organs (IS-A Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-005", "description": "In BodyParts3D, only atomic organs (ELEMENT) are constructed as polygon meshes. Compound organs (COMPOUND) defined as a sum of atomic ones are not provided in the form of the meshes. This file describes which ELEMENT parts consistute each COMPOUND organ.", "files": [ { "file_name": "isa_element_parts.txt", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/isa_element_parts.txt", "file_size": "1.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_isa_element_parts#en", "data_acquisition": "", "analysis": "", "data_number": "29,549 entries", "details": [ { "name": "concept id", "description": "Concept ID of COMPOUND organ" }, { "name": "name", "description": "Name of COMPOUND organ" }, { "name": "element file id", "description": "Polygon mesh file ID of ELEMENT constituting the COMPOUND organ" } ] }, { "path": "en\/bodyparts3d\/data-6.html", "name": "Data describing the definition of compound organs (PART-OF Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-006", "description": "In BodyParts3D, only atomic organs (ELEMENT) are constructed as polygon meshes. Compound organs (COMPOUND) defined as a sum of atomic ones are not provided in the form of the meshes. This file describes which ELEMENT parts consistute each COMPOUND organ.", "files": [ { "file_name": "partof_element_parts.txt", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/partof_element_parts.txt", "file_size": "654 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/bodyparts3d_partof_element_parts#en", "data_acquisition": "", "analysis": "", "data_number": "17,943 entries", "details": [ { "name": "concept id", "description": "Concept ID of COMPOUND organ" }, { "name": "name", "description": "Name of COMPOUND organ" }, { "name": "element file id", "description": "Polygon mesh file ID of ELEMENT constituting the COMPOUND organ" } ] }, { "path": "en\/bodyparts3d\/data-7.html", "name": "Polygon mesh data (Polygon reduction rate = 99% IS-A Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-007", "description": "BodyParts3D organ model data with the polygon reduction rate of 99%. The zip-compressed download files contain multiple files of ELEMENT file ID-specific polygon data in Wavefront OBJ format.", "files": [ { "file_name": "isa_BP3D_4.0_obj_99.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/isa_BP3D_4.0_obj_99.zip", "file_size": "136 MB" } ], "togodb_url": "", "data_acquisition": "Creation by three-dimensional CAD", "analysis": "", "data_number": "2,234 entries", "details": [] }, { "path": "en\/bodyparts3d\/data-8.html", "name": "Polygon mesh data (Polygon reduction rate = 99% PART-OF Tree)", "database_name": "BodyParts3D", "doi": "10.18908\/lsdba.nbdc00837-008", "description": "BodyParts3D organ model data with the polygon reduction rate of 99%. The zip-compressed download files contain multiple files of ELEMENT file ID-specific polygon data in Wavefront OBJ format.", "files": [ { "file_name": "partof_BP3D_4.0_obj_99.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/bodyparts3d\/LATEST\/partof_BP3D_4.0_obj_99.zip", "file_size": "62 MB" } ], "togodb_url": "", "data_acquisition": "Creation by three-dimensional CAD", "analysis": "", "data_number": "1,258 entries", "details": [] }, { "path": "en\/yeast-cdna\/data-1.html", "name": "5'-end sequences of budding yeast full-length cDNA clones and quality scores", "database_name": "Budding yeast cDNA sequencing project", "doi": "10.18908\/lsdba.nbdc00838-001", "description": "5'-end sequences of full-length cDNA clones generated from the budding yeast full-length cDNA library by the vector-capping method, the sequence quality score generated by the Phred software, and links to SGD, dbEST and UCSC Genome Browser are provided. Links to the SGD are found only in the cDNAs mapped to the genome. Links to dbEST and UCSC Genome Browser are found only in the cDNAs possessing genuine 5'-end. The number of links to SGD is 51,027, the number of links to dbEST and UCSC Genome Browser is 31,847, and the total number of cDNAs is 83,707. The data are given in a CSV format text file.", "files": [ { "file_name": "yeast_seq_qual.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_cdna\/LATEST\/yeast_seq_qual.zip", "file_size": "59.9MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/budding_yeast_cdna_sequencing_project#en", "data_acquisition": "", "analysis": "Sequencing, Base call by Phred", "data_number": "83,706 entries", "details": [ { "name": "Clone ID", "description": "Clone ID, and name in the SGD." }, { "name": "Link to SGD", "description": "Link to SGD (Saccharomyces Genome Database, http:\/\/www.yeastgenome.org\/) based on the clone ID of the cDNAs mapped to the genome. The link is found in the TogoDB edition, and only Clone ID is found in the archive file." }, { "name": "Link to dbEST", "description": "Link to NCBI's dbEST based on accession of the GenBank for the cDNAs possessing genuine 5'-end. The link is found in the TogoDB edition, and the archive file has accession only." }, { "name": "Link to UCSC Genome Browser", "description": "Link to the UCSC Genome Browser based on accession of the GenBank for the cDNAs possessing genuine 5'-end. The link is found in the TogoDB edition, and the archive file has accession only." }, { "name": "Sequence", "description": "5'-end sequence data of budding yeast full-length cDNA clones. FASTA format." }, { "name": "Quality", "description": "Phred's quality score" } ] }, { "path": "en\/yeast-cdna\/data-2.html", "name": "5'-end sequences of budding yeast full-length cDNA clones", "database_name": "Budding yeast cDNA sequencing project", "doi": "10.18908\/lsdba.nbdc00838-002", "description": "cDNA sequence data of budding yeast. Sequence data in the FASTA format, one file for each cDNA, and compressed to a single file in the tar.gz format. 83,706 entries.", "files": [ { "file_name": "Sequence.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_cdna\/LATEST\/Sequence.tar.gz", "file_size": "21MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "Sequencing", "data_number": "83,706 entries", "details": [] }, { "path": "en\/yeast-cdna\/data-3.html", "name": "cDNA sequence quality data", "database_name": "Budding yeast cDNA sequencing project", "doi": "10.18908\/lsdba.nbdc00838-003", "description": "Phred's quality score. PHD format, one file to a single cDNA data, and compressed to a single file in the tar.gz format. 83,706 entries.", "files": [ { "file_name": "Quality.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_cdna\/LATEST\/Quality.tar.gz", "file_size": "45MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "Base call by Phred", "data_number": "83,706 entries", "details": [] }, { "path": "en\/yeast-cdna\/data-4.html", "name": "Vector sequences", "database_name": "Budding yeast cDNA sequencing project", "doi": "10.18908\/lsdba.nbdc00838-004", "description": "Vector sequences used for sequencing. Multi FASTA format. 7 entries.", "files": [ { "file_name": "vector_seqeunce.fasta.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_cdna\/LATEST\/vector_seqeunce.fasta.gz", "file_size": "1KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "7 entries", "details": [] }, { "path": "en\/chemtheatre\/data-1.html", "name": "Project information", "database_name": "ChemTHEATRE", "doi": "10.18908\/lsdba.nbdc01632-001.V002", "description": "Information of researches and researchers to conduct the monitoring", "files": [ { "file_name": "ct_project.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chemtheatre\/LATEST\/ct_project.zip", "file_size": "47 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ct_project#en", "data_acquisition": "From articles", "analysis": "", "data_number": "102 entries", "details": [ { "name": "Project ID", "description": "Project ID" }, { "name": "Link", "description": "Links to \"Sample\" and \"Measured Data\" obtained in this project (Only simple search)" }, { "name": "Submitter Name", "description": "Submitter name" }, { "name": "Submitter Affiliation", "description": "Submitter affiliation" }, { "name": "Submitter Department", "description": "Submitter department" }, { "name": "Submetter City", "description": "Submetter city" }, { "name": "Submetter Country", "description": "Submetter country" }, { "name": "Corresponding Author Name", "description": "Corresponding author name" }, { "name": "Corresponding Author Affiliation", "description": "Corresponding author affiliation" }, { "name": "Corresponding Author Department", "description": "Corresponding author department" }, { "name": "Corresponding Author City", "description": "Corresponding author city" }, { "name": "Corresponding Author Country", "description": "Corresponding author country" }, { "name": "Release Date", "description": "Data release date" }, { "name": "Title", "description": "Article title" }, { "name": "Publication", "description": "Article ID (DOI)" }, { "name": "Grant", "description": "Grant to this project" } ] }, { "path": "en\/chemtheatre\/data-2.html", "name": "Sample information", "database_name": "ChemTHEATRE", "doi": "10.18908\/lsdba.nbdc01632-002.V002", "description": "Information of samples obtained in environment", "files": [ { "file_name": "ct_sample.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chemtheatre\/LATEST\/ct_sample.zip", "file_size": "206 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ct_sample#en", "data_acquisition": "Monitoring", "analysis": "", "data_number": "8,543 entries", "details": [ { "name": "Sample ID", "description": "Sample ID" }, { "name": "Link", "description": "Links to \"Measured Data\" obtained in this sample (Only simple search)" }, { "name": "Project ID", "description": "ID of sampling project" }, { "name": "Sample Type 1", "description": "Sample type" }, { "name": "Sample Type 2", "description": "Sample type" }, { "name": "Sample Type 3", "description": "Sample type" }, { "name": "Sample Type 4", "description": "Sample type" }, { "name": "Sample Type 5", "description": "Sample type" }, { "name": "Taxonomy ID", "description": "Taxonomy ID for biotic sample" }, { "name": "es-BANK ID", "description": "ID of Environmental Specimen Bank (es-BANK)" }, { "name": "Sample Name", "description": "Sample name" }, { "name": "Scientific Name", "description": "Scientific name" }, { "name": "Common Name", "description": "Common name" }, { "name": "Sampling Time", "description": "Sampling time" }, { "name": "Weather", "description": "Weather at sampling" }, { "name": "Region", "description": "Region" }, { "name": "Country", "description": "Country" }, { "name": "Area", "description": "Area" }, { "name": "Latitude From", "description": "Latitude from" }, { "name": "Latitude To", "description": "Latitude to" }, { "name": "Longitude From", "description": "Longitude from" }, { "name": "Longitude To", "description": "Longitude to" }, { "name": "Sex", "description": "Sex for biotic sample" }, { "name": "Tissue Organ", "description": "Organ for biotic sample" }, { "name": "Tissue Lipid", "description": "Lipid weight for biotic sample" }, { "name": "Tissue Moist", "description": "Moist weight for biotic sample" }, { "name": "Weight", "description": "Weight" }, { "name": "Weight Unit", "description": "Weight unit" }, { "name": "Length", "description": "Length" }, { "name": "Length Unit", "description": "Length unit" }, { "name": "Length Type", "description": "Length type" }, { "name": "Growth Stage", "description": "Growth stage for biotic sample" }, { "name": "Age", "description": "Age for biotic sample" }, { "name": "Disease", "description": "Disease for biotic sample" }, { "name": "Temperature", "description": "Temperature" }, { "name": "Water Temperature", "description": "Water temperature" }, { "name": "pH", "description": "pH for water sample" }, { "name": "DO", "description": "Dissolved oxygen for water sample" }, { "name": "EC", "description": "Electrical conductivity for water sample" }, { "name": "Salinity", "description": "Salinity for water sample" }, { "name": "SS", "description": "Suspended solids for water sample" }, { "name": "Water Depth", "description": "Water depth" }, { "name": "Transparency", "description": "Transparency for water sample" }, { "name": "Water Color", "description": "Color for water sample" }, { "name": "Sediment Temperature", "description": "Temperature for sediment sample" }, { "name": "Sediment Depth", "description": "Water depth for sediment sample" }, { "name": "Sediment Appearance", "description": "Appearance for sediment sample" }, { "name": "Sediment Color", "description": "Color for sediment sample" }, { "name": "Sediment Surface Color", "description": "Surface color for sediment sample" }, { "name": "Sediment Odor", "description": "Odor for sediment sample" }, { "name": "Sediment Impurities", "description": "Impurities for sediment sample" }, { "name": "Sediment Moisture Onsite Analysis", "description": "Moisture weight for sediment sample" }, { "name": "Ignition Loss Onsite Analysis", "description": "Ignition loss for sediment sample" }, { "name": "Soil Depth", "description": "Depth for soil sample" }, { "name": "Flow Rate", "description": "Flow rate for air sample" }, { "name": "Mean PM10", "description": "Mean amount of PM10 for air sample" }, { "name": "Mean Total Suspended Particles", "description": "Mean total suspended particles for air sample" }, { "name": "Humidity", "description": "Humidity for air sample" }, { "name": "Wind Direction", "description": "Wind direction for air sample" }, { "name": "Wind Speed MS", "description": "Wind speed (m\/sec) for air sample" }, { "name": "Amount of Collected Air", "description": "Amount of collected Air" } ] }, { "path": "en\/chemtheatre\/data-3.html", "name": "Chemical Information", "database_name": "ChemTHEATRE", "doi": "10.18908\/lsdba.nbdc01632-003.V002", "description": "Information of chemical contained in samples", "files": [ { "file_name": "ct_chemical.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chemtheatre\/LATEST\/ct_chemical.zip", "file_size": "28 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ct_chemical#en", "data_acquisition": "PubChem", "analysis": "", "data_number": "1,205 entries", "details": [ { "name": "Chemical ID", "description": "Chemical ID" }, { "name": "Chemical Name", "description": "Chemical Name" }, { "name": "IUPAC", "description": "IUPAC" }, { "name": "Synonyms", "description": "Synonyms" }, { "name": "PubChem", "description": "PubChem ID" }, { "name": "CAS", "description": "CAS Number" }, { "name": "Link", "description": "Links to \"Measured Data\" that contains this chemical (Only simple search)" } ] }, { "path": "en\/chemtheatre\/data-4.html", "name": "Measured data", "database_name": "ChemTHEATRE", "doi": "10.18908\/lsdba.nbdc01632-004.V002", "description": "Measured data of chemical on samples", "files": [ { "file_name": "ct_measured_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chemtheatre\/LATEST\/ct_measured_data.zip", "file_size": "746 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ct_measured_data#en", "data_acquisition": "Experiment", "analysis": "", "data_number": "106,552 entries", "details": [ { "name": "Measured ID", "description": "Measured ID" }, { "name": "Project ID", "description": "ID of measuring project" }, { "name": "Sample ID", "description": "ID of measured sample" }, { "name": "Instrument Group", "description": "Instrument group" }, { "name": "Instrument", "description": "Instrument name" }, { "name": "Method Extraction", "description": "Extraction method" }, { "name": "Method Cleanup", "description": "Cleanup method" }, { "name": "Derivatization", "description": "Derivatization method" }, { "name": "Recovery Correction", "description": "Recovery correction method" }, { "name": "LOD", "description": "Limit Of Detection of instrument" }, { "name": "Repeatability", "description": "Repeatability" }, { "name": "Standard", "description": "Standard instrument for analysis" }, { "name": "Chemical ID", "description": "ID of detected chemical" }, { "name": "Measured Value", "description": "Measured value" }, { "name": "Alternative Value", "description": "Alternative Value" }, { "name": "Unit", "description": "Measure unit" } ] }, { "path": "en\/chip-atlas\/data-1.html", "name": "Experiment list", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-001.V020", "description": "A list of metadata of the reanalysed ChIP-Seq data archived in Sequence Read Archive (SRA), grouped by SRA Experiment ID, providing the information of reference genome data, antigen, or cell type. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#downloads_doc", "files": [ { "file_name": "chip_atlas_experiment_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/LATEST\/chip_atlas_experiment_list.zip", "file_size": "20 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/chip_atlas_experiment_list#en", "data_acquisition": "We have processed data downloaded from SRA by using a standard ChIP-Seq data analysis pipeline, then we curated metadata of archived data manually.", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "279,509 entries", "details": [ { "name": "Experimental ID", "description": "Experimental ID (SRX, ERX, DRX)" }, { "name": "Genome assembly", "description": "Genome assembly" }, { "name": "Antigen class", "description": "Antigen class" }, { "name": "Antigen", "description": "Antigen" }, { "name": "Cell type class", "description": "Cell type class" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Cell type description", "description": "Cell type description" }, { "name": "Processing logs", "description": "Processing logs (# of reads, % mapped, % duplicates, # of peaks [q < 1E-05])" }, { "name": "Title", "description": "Title submitted by authors" }, { "name": "Meta data", "description": "Meta data submitted by authors" }, { "name": "BigWig", "description": "Link to a BigWig-formatted coverage score binary file." }, { "name": "Peak-call (BED) (q < 1E-05)", "description": "Link to a BED4-formatted peak-call data file with the q-value threshold 1E-05." }, { "name": "Peak-call (BED) (q < 1E-10)", "description": "Link to a BED4-formatted peak-call data file with the q-value threshold 1E-10." }, { "name": "Peak-call (BED) (q < 1E-20)", "description": "Link to a BED4-formatted peak-call data file with the q-value threshold 1E-20." }, { "name": "Peak-call (BigBed) (q < 1E-05)", "description": "Link to a BigBed-formatted peak-call data file binarized from the corresponding BED4 file (q < 1E-05)." }, { "name": "Peak-call (BigBed) (q < 1E-10)", "description": "Link to a BigBed-formatted peak-call data file binarized from the corresponding BED4 file (q < 1E-10)." }, { "name": "Peak-call (BigBed) (q < 1E-20)", "description": "Link to a BigBed-formatted peak-call data file binarized from the corresponding BED4 file (q < 1E-20)." } ] }, { "path": "en\/chip-atlas\/data-2.html", "name": "File list", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-002.V020", "description": "A list of merged bed file and its metadata, including reference genome data, antigen, cell type, and identifier of merged experiments. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#downloads_doc", "files": [ { "file_name": "chip_atlas_file_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/LATEST\/chip_atlas_file_list.zip", "file_size": "28 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/chip_atlas_file_list#en", "data_acquisition": "We have generated a list of this bed file automatically by processing data downloaded from Sequence Read Archive.", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "573,691 entries", "details": [ { "name": "File name", "description": "File name" }, { "name": "Genome assembly", "description": "Genome assembly" }, { "name": "Antigen class", "description": "Antigen class" }, { "name": "Antigen", "description": "Antigen" }, { "name": "Cell type class", "description": "Cell type class" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Threshold", "description": "Threshold" }, { "name": "Experimental IDs included", "description": "Experimental IDs included" }, { "name": "Peak-call (BED)", "description": "Link to a BED9 + GFF3 format file concatenated and converted from the BED4-formatted peak-call data files of the experiments in the \"Experimental IDs included\"." } ] }, { "path": "en\/chip-atlas\/data-3.html", "name": "Analysis list", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-003.V020", "description": "A list of metadata to generate file paths of analysis provided on ChIP-Atlas, target gene analysis and colocalization analysis. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#downloads_doc", "files": [ { "file_name": "chip_atlas_analysis_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/LATEST\/chip_atlas_analysis_list.zip", "file_size": "131 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/chip_atlas_analysis_list#en", "data_acquisition": "A list is generated from our result of analysis based on bed files processed by our pipeline.", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "4,249 entries", "details": [ { "name": "Antigen", "description": "Antigen" }, { "name": "Cell type class in Colocalization", "description": "Cell type class in Colocalization (comma separated)" }, { "name": "Recorded (+) or not (-) in Target Genes", "description": "Target gene analysis performed or not (+\/-)" }, { "name": "Genome assembly", "description": "Genome assembly" }, { "name": "Target Genes (TSS ±1k)", "description": "Link to a TSV (Tab-Separeted Values) file that describes the genes bound by the given antigen in the range of ± 1 kb of each TSS (transcription start site)." }, { "name": "Target Genes (TSS ±5k)", "description": "Link to a TSV (Tab-Separeted Values) file that describes the genes bound by the given antigen in the range of ± 5 kb of each TSS (transcription start site)." }, { "name": "Target Genes (TSS ±10k)", "description": "Link to a TSV (Tab-Separeted Values) file that describes the genes bound by the given antigen in the range of ± 10 kb of each TSS (transcription start site)." }, { "name": "Colocalization (TSV)", "description": "Link to a TSV (Tab-Separeted Values) file that describes the protein colocalization with the given antigen in the given cell type class." }, { "name": "Colocalization (GML)", "description": "Link to a GML (Graph Modelling Language) file that describes the protein colocalization in the given cell type class." } ] }, { "path": "en\/chip-atlas\/data-4.html", "name": "Antigen list", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-004.V020", "description": "A list of all antigen names of data provided on ChIP-Atlas. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#downloads_doc", "files": [ { "file_name": "chip_atlas_antigen_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/LATEST\/chip_atlas_antigen_list.zip", "file_size": "715 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/chip_atlas_antigen_list#en", "data_acquisition": "We have generated the list by curating metadata manually.", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "5,311 entries", "details": [ { "name": "Genome assembly", "description": "Genome assembly" }, { "name": "Antigen class", "description": "Antigen class" }, { "name": "Antigen", "description": "Antigen" }, { "name": "Number of experiments", "description": "Number of experiments" }, { "name": "Experimental IDs included", "description": "Experimental IDs included" } ] }, { "path": "en\/chip-atlas\/data-5.html", "name": "Cell type list", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-005.V020", "description": "A list of all cell type names of data provided on ChIP-Atlas. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#downloads_doc", "files": [ { "file_name": "chip_atlas_celltype_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/LATEST\/chip_atlas_celltype_list.zip", "file_size": "680 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/chip_atlas_celltype_list#en", "data_acquisition": "We have generated the list by curating metadata manually.", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "4,956 entries", "details": [ { "name": "Genome assembly", "description": "Genome assembly" }, { "name": "Cell type class", "description": "Cell type class" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Number of experiments", "description": "Number of experiments" }, { "name": "Experimental IDs included", "description": "Experimental IDs included" } ] }, { "path": "en\/chip-atlas\/data-6.html", "name": "Data directory", "database_name": "ChIP-Atlas", "doi": "10.18908\/lsdba.nbdc01558-006.V020", "description": "All ChIP-Seq data analyzed on ChIP-Atlas. BigWig, Bed, BigBed format files are provided for each individual Experiment. Bed files are provided for data assembled by antigens and cell types. Analysis data from target genes analysis and colocalization analysis are provided in tab separated values (tsv). See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki#peak_browser_doc\r\n* The dataset of past version can not be downloaded.", "files": [ { "file_name": "hg19", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/hg19\/", "file_size": "25 TB" }, { "file_name": "hg38", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/hg38\/", "file_size": "25 TB" }, { "file_name": "mm9", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/mm9\/", "file_size": "19 TB" }, { "file_name": "mm10", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/mm10\/", "file_size": "19 TB" }, { "file_name": "ce10", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/ce10\/", "file_size": "285 GB" }, { "file_name": "ce11", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/ce11\/", "file_size": "285 GB" }, { "file_name": "dm3", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/dm3\/", "file_size": "872 GB" }, { "file_name": "dm6", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/dm6\/", "file_size": "827 GB" }, { "file_name": "saccer3", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/sacCer3\/", "file_size": "194 GB" }, { "file_name": "rn6", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/chip-atlas\/data\/rn6\/", "file_size": "722 GB" } ], "togodb_url": "", "data_acquisition": "We have processed data downloaded from SRA by using a standard ChIP-Seq data analysis pipeline. See details here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "analysis": "See details of data processing here: https:\/\/github.com\/inutano\/chip-atlas\/wiki", "data_number": "5,428,910 files", "details": [] }, { "path": "en\/clest\/data-1.html", "name": "Clone", "database_name": "ClEST", "doi": "10.18908\/lsdba.nbdc01137-001", "description": "Infomarion of clones of each Cimex lectularius EST library", "files": [ { "file_name": "clest_clone.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/clest\/LATEST\/clest_clone.zip", "file_size": "660 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/clest_clone#en", "data_acquisition": "One pass sequencing from 5' termini using the Sanger sequencing method with ABI3130xl", "analysis": "Basecalling by the phred program", "data_number": "7,389 entries", "details": [ { "name": "Clone ID", "description": "ID of the clone" }, { "name": "Library", "description": "Tissue used for library construction" }, { "name": "Category", "description": "Category of affiliation of sequence" }, { "name": "Cluster", "description": "ID of cluster to which the clone belongs" }, { "name": "ACC No. of clone", "description": "Accession number of the clone in GenBank" }, { "name": "Length", "description": "Sequence length of the clone" }, { "name": "Sequence", "description": "Sequence" } ] }, { "path": "en\/clest\/data-2.html", "name": "Cluster", "database_name": "ClEST", "doi": "10.18908\/lsdba.nbdc01137-002", "description": "Information of clustered sequences including Blastx search results and GO annotations", "files": [ { "file_name": "clest_cluster.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/clest\/LATEST\/clest_cluster.zip", "file_size": "525 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/clest_cluster#en", "data_acquisition": "\"Clone\" dataset", "analysis": "Clustering using the phred\/phrap program, Blastx homology search against a non-redundant protein database from the NCBI web site, and describing presumed function and GO annotation using the Blast2GO software.", "data_number": "3,161 entries", "details": [ { "name": "Cluster ID", "description": "ID of the cluster" }, { "name": "Description", "description": "Description of presumed function of the cluster" }, { "name": "Category", "description": "Category of affiliation of the cluster" }, { "name": "Length", "description": "Consensus sequence length of the cluster" }, { "name": "Sequence", "description": "Consensus sequence" }, { "name": "Source", "description": "Source clones" }, { "name": "No. of clones", "description": "Number of source clones" }, { "name": "Top Blastx hit (E value < 1e-6)", "description": "Gene name of top Blastx hit" }, { "name": "ACC No.", "description": "Accession number of top Blastx hit" }, { "name": "E-value", "description": "E-value of top Blastx hit" }, { "name": "GO", "description": "GO annotation" } ] }, { "path": "en\/confc\/data-1.html", "name": "Data of conformation changes by some binding", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-001", "description": "A protein structure pair which ID% (sequence identity) is more than 99%, and Dmax (maximum distance between Cα atoms of superimposed protein structures) is more than 20 Å, is stored.", "files": [ { "file_name": "confc_all.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_all.zip", "file_size": "14.2 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/confc_all#en", "data_acquisition": "PDB (Protein Data Bank)", "analysis": "The distance values of φ and ψ between the superimposed protein structures of each residues are calculated, and the Z score of distance is computed.", "data_number": "352 entries", "details": [ { "name": "confID", "description": "ID of this table" }, { "name": "classID", "description": "ID including structural change class information" }, { "name": "index", "description": "Record Index" }, { "name": "pdbIDA", "description": "PDB ID compared protein structure A" }, { "name": "pdbIDB", "description": "PDB ID compared protein structure B" }, { "name": "pdbChainA", "description": "PDB chain ID compared protein structure A" }, { "name": "pdbChainB", "description": "PDB chain ID compared protein structure B" }, { "name": "confDatafile", "description": "Link to conformation analysis file (zip)" }, { "name": "confClass", "description": "Binding molecular type" }, { "name": "confName", "description": "Name of binding molecules" }, { "name": "dmax", "description": "Maximum distance between Cα atoms of superimposed protein structures" }, { "name": "rmsd", "description": "RMSD of distance between Cα of superimposed protein structures" }, { "name": "identity", "description": "Protein sequence identity" } ] }, { "path": "en\/confc\/data-2.html", "name": "Supplement data for conformation changes by some binding", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-002", "description": "The distance values of φ and ψ between the superimposed protein structures of each residues are calculated, and the Z score of distance is computed.The information about a regions of structural change sekected with the Z score is stored.", "files": [ { "file_name": "confc_part.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_part.zip", "file_size": "231 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/confc_part#en", "data_acquisition": "PDB (Protein Data Bank)", "analysis": "The distance values of φ and ψ between the superimposed protein structures of each residues are calculated, and the Z score of distance is computed. Finally, the regions of structural change are selected with the Z score", "data_number": "12,692 entries", "details": [ { "name": "confID", "description": "ID of ConfAll table" }, { "name": "siteNo", "description": "Site number in residue number order" }, { "name": "siteStart1", "description": "Dihedral angle number at the start of the site in the structure 1 (numbering starts at the second visible residue)" }, { "name": "siteStartR1", "description": "Residue number at the start of the site in the structure 1" }, { "name": "siteEnd1", "description": "Dihedral angle number at the end of the site in the structure 1" }, { "name": "siteEndR1", "description": "Residue number at the end of the site in the structure 1" }, { "name": "siteLength1", "description": "The longest site length in the structure 1" }, { "name": "siteStart2", "description": "Dihedral angle number at the start of the site in the structure 2 (numbering starts at the second visible residue)" }, { "name": "siteStartR2", "description": "Residue number at the start of the site in the structure 2" }, { "name": "siteEnd2", "description": "Dihedral angle number at the end of the site in the structure 2" }, { "name": "siteEndR2", "description": "Residue number at the end of the site in the structure 2" }, { "name": "siteLength2", "description": "The longest site length in the structure 2" }, { "name": "phiMax", "description": "Maximum value of φchange" }, { "name": "psiMax", "description": "Maximum value of ψchange" } ] }, { "path": "en\/confc\/data-3.html", "name": "Data of evolutionary structure change", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-003", "description": "The information about a regions of structural change by mutation, insersion and\/or deletion is stored.", "files": [ { "file_name": "confc_ev.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_ev.zip", "file_size": "373 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/confc_ev#en", "data_acquisition": "PDB (Protein Data Bank)", "analysis": "", "data_number": "169,962 entries", "details": [ { "name": "confEVID", "description": "ID of this table" }, { "name": "pdbIDA", "description": "PDB ID of compared protein structure A" }, { "name": "pdbIDB", "description": "PDB ID of compared protein structure B" }, { "name": "pdbChainA", "description": "PDB chain ID of compared protein structure A" }, { "name": "pdbChainA", "description": "PDB chain ID of compared protein structure B" }, { "name": "identity", "description": "Sequence identity" }, { "name": "indelSize", "description": "Number of indels analyzed" }, { "name": "alignment", "description": "Sequence alignment" }, { "name": "indel", "description": "Analysis of indels" } ] }, { "path": "en\/confc\/data-4.html", "name": "Data of structural flexibility", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-004", "description": "The regions of structural flexibility are selected with the Z score of temperature factor (B-factor) values by Cα atom of each residue in PDB.", "files": [ { "file_name": "confc_disorder.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_disorder.zip", "file_size": "3.7 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/confc_disorder#en", "data_acquisition": "PDB (Protein Data Bank)", "analysis": "The regions of structural flexibility are selected with the Z score of temperature factor (B-factor) values by Cα atom of each residue in PDB.", "data_number": "130,563 entries", "details": [ { "name": "confID", "description": "ID of this table" }, { "name": "classID", "description": "ID of structural change class" }, { "name": "pdbID", "description": "PDB ID" }, { "name": "pdbChain", "description": "PDB chain ID" }, { "name": "method", "description": "Experimental technique used for the structure determination" }, { "name": "program", "description": "Refinement program" }, { "name": "temperature", "description": "Temperature at experiment" }, { "name": "resolution", "description": "Resolution" }, { "name": "Rfactor", "description": "R-factor" }, { "name": "depositDate", "description": "Deposition date" }, { "name": "depositDateClass", "description": "Date format" }, { "name": "ECnumber", "description": "EC number" }, { "name": "SCOPID", "description": "SCOP ID" }, { "name": "domainNumber", "description": "Number of domains" }, { "name": "complex", "description": "Type of complex" }, { "name": "SEQRESLength", "description": "SEQRES Length" }, { "name": "ATOMLength", "description": "ATOM Length" }, { "name": "REMARK465", "description": "Whether REMARK 465 (describing missing residues) is used" }, { "name": "disorderNumber", "description": "Number of disorder regions" }, { "name": "disSumLength", "description": "Total number of disordered residues" }, { "name": "maxDisLength", "description": "Maximum length of disorder region" }, { "name": "minDisLength", "description": "Minimum length of disorder region" }, { "name": "disSeqresPosition", "description": "Position of disorder regions by SEQRES" }, { "name": "disAtomPosition", "description": "Position of disorder regions by ATOM" }, { "name": "temperatureFactorAve", "description": "Average of temperature factor" }, { "name": "temperatureFactorStddev", "description": "Standard deviation of temperature factor" }, { "name": "checkOccupy", "description": "Whether OCCUPANCY less than 1.00 is used" }, { "name": "modelNumber", "description": "Whether MODEL NUMBER is used" } ] }, { "path": "en\/confc\/data-5.html", "name": "Conformation analysis", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-005", "description": "Results of conformation analysis for PDB files (raw data)\r\nEach result is linked from \"Data of conformation changes by some binding\" table.", "files": [ { "file_name": "confc_datafile.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_datafile.zip", "file_size": "63.9 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "352 entries", "details": [] }, { "path": "en\/confc\/data-6.html", "name": "Protein structure image", "database_name": "ConfC", "doi": "10.18908\/lsdba.nbdc00400-006", "description": "Structure images of the protein which has structural flexibility.\r\nEach image is linked from \"Data of structural flexibility\" table.", "files": [ { "file_name": "confc_structure_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/confc\/LATEST\/confc_structure_image.zip", "file_size": "1.3 GB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "130,547 entries", "details": [] }, { "path": "en\/create-portal\/data-1.html", "name": "InGaP", "database_name": "CREATE portal", "doi": "10.18908\/lsdba.nbdc00403-001", "description": "Expression of mKIAA genes in mouse organs and cell lines.", "files": [ { "file_name": "create_portal_ingap.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/create-portal\/LATEST\/create_portal_ingap.zip", "file_size": "57.6 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/create_portal_ingap#en", "data_acquisition": "Western blot: Extracts of adult mouse organs and cell lines were separated by SDS-PAGE and chemiluminescent results obtained using anti-mKIAA antibodies and HRP-conjugated anti-rabbit IgG were analyzed by CCD imaging apparatus.\r\nImmunohistochemical analysis: Fixed mouse brain sections were fluorescent-labeled and observed by confocal laser scanning microscope using anti-mKIAA antibodies and FITC-conjugated anti-rabbit IgG.\r\nSubcellular localization: Transiently transfected GFP-fusion KIAA\/mKIAA in HEK293 cells were observed by fluorescent microscope.\r\ncDNA microarray: [a-33P]dCTP-labeled mRNA derived from mouse organs and brain were hybridized against array which was prepared by spotting mKIAA cDNA on the nylon membrane attached to a slide glass using microarrayer, and the results were obtained by a microarray scanner.", "analysis": "", "data_number": "274 entries", "details": [ { "name": "mKIAA No.", "description": "Gene number of mouse KIAA" }, { "name": "Clone name", "description": "Name of the clone" }, { "name": "Accession No.", "description": "Accession number for DDBJ\/GenBank\/EMBL database" }, { "name": "Alias Name", "description": "Gene name" }, { "name": "Antigen size", "description": "Size of the antigen" }, { "name": "Antigen solubility", "description": "Solubility of the antigen" }, { "name": "Homolog human clone", "description": "Clone name for the human homolog" }, { "name": "Reference protein", "description": "Reference protein" }, { "name": "Predicted molecular weight", "description": "Predicted molecular weight" }, { "name": "Predicted gene function", "description": "Predicted gene function (Gene Ontology number)" }, { "name": "Antigen sequence name", "description": "Name of the antigen" }, { "name": "Antigen sequence", "description": "Amino acids sequence of the antigen" }, { "name": "Purification tag", "description": "Status of the purification tag" }, { "name": "Western blot (adult organs)", "description": "Results of the Western blot (adult mouse organs)" }, { "name": "Western blot (cell lines)", "description": "Results of the Western blot (Cultured cell lines)" }, { "name": "Infrared Fluorescence scanner (cerebellum)", "description": "Observation by Infrared Fluorescence scanner (cerebellum)" }, { "name": "Infrared Fluorescence scanner (forebrain 1)", "description": "Observation by Infrared Fluorescence scanner (forebrain 1)" }, { "name": "Infrared Fluorescence scanner (forebrain 2)", "description": "Observation by Infrared Fluorescence scanner (forebrain 2)" }, { "name": "Confocal laser scanning microscope (neocortex 1)", "description": "Observation by Confocal laser scanning microscope (neocortex 1)" }, { "name": "Confocal laser scanning microscope (neocortex 2)", "description": "Observation by Confocal laser scanning microscope (neocortex 2)" }, { "name": "Confocal laser scanning microscope (hippocampus)", "description": "Observation by Confocal laser scanning microscope (hippocampus)" }, { "name": "Confocal laser scanning microscope (cerebellum)", "description": "Observation by Confocal laser scanning microscope (cerebellum)" }, { "name": "Immunoprecipitation", "description": "Results of the immunoprecipitation" }, { "name": "Mascot search results", "description": "Results of the Mascot search in MS" }, { "name": "Ectopic expression (phase)", "description": "Expression of KIAA gene in HEK293 cells (phase)" }, { "name": "Ectopic expression (fluoro)", "description": "Expression of KIAA gene in HEK293 cells (fluoro)" }, { "name": "mKIAA cDNA array analysis", "description": "Results of mKIAA cDNA array analysis" } ] }, { "path": "en\/create-portal\/data-2.html", "name": "InCeP", "database_name": "CREATE portal", "doi": "10.18908\/lsdba.nbdc00403-002", "description": "mKIAA intracellular signaling pathway.", "files": [ { "file_name": "create_portal_incep.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/create-portal\/LATEST\/create_portal_incep.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/create_portal_incep#en", "data_acquisition": "Immunoprecipitation: Extracts derived from adult mouse tissues and cell lines were immunoprecipitated using anti-mKIAA antibodies.\r\nMass spectrometory: Precipitated proteins were separated by SDS-PAGE and protein bands cut out from the gel were analyzed by mass spectrometry.", "analysis": "Mass spectrometry: Results obtained by LC-MS were analyzed by Mascot and precipitated proteins were predicted.\r\nKeyMolnet analysys: Images of mKIAA intracellular signaling pathway were constructed by merging protein information obtained by mass spectrometry and known information using KeyMolnet software.", "data_number": "50 entries", "details": [ { "name": "mKIAA No.", "description": "Gene number of mouse KIAA" }, { "name": "Pathway image", "description": "Image for the signal transduction pathway" }, { "name": "KeyMolnet file", "description": "File derived from KeyMolnet software" }, { "name": "Reference", "description": "Related research paper" } ] }, { "path": "en\/create-portal\/data-3.html", "name": "InCeP images", "database_name": "CREATE portal", "doi": "10.18908\/lsdba.nbdc00403-003", "description": "Image files of mKIAA intracellular signaling pathway.", "files": [ { "file_name": "create_portal_images.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/create-portal\/LATEST\/create_portal_images.zip", "file_size": "13.4 MB" } ], "togodb_url": "", "data_acquisition": "From \"Keymol net data\"", "analysis": "", "data_number": "76 files", "details": [] }, { "path": "en\/create-portal\/data-4.html", "name": "KeyMolnet data", "database_name": "CREATE portal", "doi": "10.18908\/lsdba.nbdc00403-004", "description": "KeyMolnet files of mKIAA intracellular signaling pathway.", "files": [ { "file_name": "create_portal_keymolnet.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/create-portal\/LATEST\/create_portal_keymolnet.zip", "file_size": "7.1 MB" } ], "togodb_url": "", "data_acquisition": "From \"Mascot search results\"", "analysis": "Images of mKIAA intracellular signaling pathway were constructed by merging protein information obtained by mass spectrometry and known information using KeyMolnet software.", "data_number": "76 files", "details": [] }, { "path": "en\/create-portal\/data-5.html", "name": "Mascot search results", "database_name": "CREATE portal", "doi": "10.18908\/lsdba.nbdc00403-005", "description": "Mascot search result files.", "files": [ { "file_name": "create_portal_mascot.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/create-portal\/LATEST\/create_portal_mascot.zip", "file_size": "321 KB" } ], "togodb_url": "", "data_acquisition": "Immunoprecipitation: Extracts derived from adult mouse tissues and cell lines were immunoprecipitated using anti-mKIAA antibodies.\r\nMass spectrometory: Precipitated proteins were separated by SDS-PAGE and protein bands cut out from the gel were analyzed by mass spectrometry.", "analysis": "Mass spectrometry: Results obtained by LC-MS were analyzed by Mascot and precipitated proteins were predicted.", "data_number": "38 files", "details": [] }, { "path": "en\/dhaplodb\/data-1.html", "name": "SNP List (Phase II)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-001", "description": "A list of SNPs in D2 (Phase II). SNP genotypes in D1 (Phase I, Perlegen 281K SNPs) and those determined using Affymetrix 500K Array for overlapping 74 CHM samples were merged and QC'ed. LD bins were then determined.", "files": [ { "file_name": "dhaplo_d2_snp_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/dhaplo_d2_snp_list.zip", "file_size": "16.6MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dhaplo_d2_snp_list#en", "data_acquisition": "Perlegen 281K arrays, Affymetrix 500K arrays", "analysis": "The analyses by Perlegen 281K arrays are described in Kukita et al. (2005). The analyses by Affymetrix 500K are described in Higasa et al. (2009). Affymetrix markers were mapped to NCBI Build 35 (Higasa mapping was on Build 36), and merged with Perlegen data. The original Affymetrix data contained a small fraction (< 1%) of SNPs that were genotyped heterozygote. These typings were judged to be errors because the materials were presumed to be homozygotes. Thus, all heterozygous calls (in Affymetrix data) were forced to be no calls. Many of the heterozygous calls were also low S\/N calls and frequently irreproducible when tested. See \"LD bin List\" for the calculation of LD bins.", "data_number": "581,235 entries", "details": [ { "name": "RefSNP ID", "description": "RefSNP ID (rs number) given by dbSNP. (Linked to dbSNP in Quick Search)" }, { "name": "Affy\/Perlegen ID", "description": "SNP ID given by Affymetrix or Perlegen" }, { "name": "Chromosome", "description": "Chromosome number that each SNP resides" }, { "name": "Position", "description": "Chromosomal nucleotide position (NCBI Build 35) of each SNP" }, { "name": "Alleles", "description": "Alleles" }, { "name": "MAF", "description": "Minor allele frequency" }, { "name": "Genotypes", "description": "Genotypes for the 74 CHM samples" }, { "name": "LD bin", "description": "Name of LD bin (Linked to LD bin list in Quick Search)" }, { "name": "tagSNP", "description": "The flag that indicates whether the SNP is a tagSNP or not.\r\n1: tagSNP\r\n0: non-tagSNP\r\n-: SNP not included in LD bin calculation (MAF<0.05)" }, { "name": "Best tagSNP", "description": "The flag that indicates whether the SNP is the best tagSNP or not.\r\n1: Best tagSNP\r\n0: non-best tagSNP\r\n-: SNP not included in LD bin calculation (MAF<0.05)" } ] }, { "path": "en\/dhaplodb\/data-2.html", "name": "SNP List (Phase III)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-002", "description": "A list of SNPs in D3 (Phase III). The data is essentially the same as those described in Kukita et al. (2010) paper, but contains additional samples (CHM010 and CHM035) because their data were judged to be acceptable with regard to genotypes, though they were excluded at QC steps in the previous report. LD bins were then determined.", "files": [ { "file_name": "dhaplo_d3_snp_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/dhaplo_d3_snp_list.zip", "file_size": "23.9MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dhaplo_d3_snp_list#en", "data_acquisition": "Affymetrix SNP 6.0", "analysis": "A hundred complete hydatidiform moles (CHMs) were genotyped using Affymetrix SNP Array 6.0, and mapped on the human reference genome sequence, NCBI Build 36. Low log2R calls, calls judged to be in deleted regions (determined by CNV analysis), and heterozygous calls were forced to no calls, as described in the Kukita paper. After QCs by sample call rate and SNP call rate, the final data for 87 CHMs (876K SNPs) was obtained. See “LD bin List” for the calculation of LD bins.", "data_number": "876,399 entries", "details": [ { "name": "RefSNP ID", "description": "RefSNP ID (rs number) given by dbSNP. (Linked to dbSNP in Quick Search)" }, { "name": "Affy\/Perlegen ID", "description": "SNP ID given by Affymetrix" }, { "name": "Chromosome", "description": "Chromosome number that each SNP resides" }, { "name": "Position", "description": "Chromosomal nucleotide position (NCBI Build 36) of each SNP" }, { "name": "Alleles", "description": "Alleles" }, { "name": "MAF", "description": "Minor allele frequency" }, { "name": "Genotypes", "description": "Genotypes for the 87 CHM samples" }, { "name": "LD bin", "description": "Name of LD bin (Linked to LD bin list in Quick Search)" }, { "name": "tagSNP", "description": "The flag that indicates whether the SNP is a tagSNP or not.\r\n1: tagSNP\r\n0: non-tagSNP\r\n-: SNP not included in LD bin calculation (MAF<0.05)" }, { "name": "Best tagSNP", "description": "The flag that indicates whether the SNP is the best tagSNP or not.\r\n1: Best tagSNP\r\n0: non-best tagSNP\r\n-: SNP not included in LD bin calculation (MAF<0.05)" } ] }, { "path": "en\/dhaplodb\/data-3.html", "name": "LD bin list (Phase II)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-003", "description": "LD bin list of D2 (Phase II). LD bin is a group of SNPs that mutually shows high LD (r2 > 0.8). See below for detail.", "files": [ { "file_name": "dhaplo_d2_ld_bin_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/dhaplo_d2_ld_bin_list.zip", "file_size": "3.0MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dhaplo_d2_ld_bin_list#en", "data_acquisition": "Perlegen 281K arrays, Affymetrix 500K arrays", "analysis": "Common SNPs (MAF > 5%) were selected, and LDs (r2 values) between every SNP pairs within 300 kb were calculated. LD bins were collected so that every pairs within the bin shows r2 >0.8, by the greedy method of ldSELECT (Carson et al., AJHG 74, 106-120, 2004) after the program was modified so that it can handle haploid data.", "data_number": "254,762 entries", "details": [ { "name": "LD bin", "description": "Name of LD bin" }, { "name": "Chromosome", "description": "Chromosome number each LD bin resides (Chr1 - Chr22, ChrX)" }, { "name": "Position Start", "description": "Start position of LD bin (nucleotide position in each chromosome, according to NCBI Build 35)" }, { "name": "Position End", "description": "End position of LD bin (nucleotide position in each chromosome, according to NCBI Build 35)" }, { "name": "SNPs Count", "description": "Number of SNPs in LD bin" }, { "name": "tagSNPs Count", "description": "Number of tagSNPs in LD bin" }, { "name": "Best tagSNP", "description": "tagSNP that showed the highest mean r2, given by RefSNP ID (rs number)" } ] }, { "path": "en\/dhaplodb\/data-4.html", "name": "LD bin list (Phase III)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-004", "description": "LD bin list of D3 (Phase III). LD bin is a group of SNPs that mutually shows high LD (r2 > 0.8). See below for detail.", "files": [ { "file_name": "dhaplo_d3_ld_bin_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/dhaplo_d3_ld_bin_list.zip", "file_size": "3.1MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dhaplo_d3_ld_bin_list#en", "data_acquisition": "Affymetrix SNP 6.0", "analysis": "Common SNPs (MAF > 5%) were selected, and LDs (r2 values) between every SNP pairs within 300 kb were calculated. LD bins were collected so that every pairs within the bin shows r2 >0.8, by the greedy method of tagzilla (which is a rapid method of bin selection based on the principle of ldSELECT (Carson et al., AJHG 74, 106-120, 2004)).", "data_number": "250,751 entries", "details": [ { "name": "LD bin", "description": "Name of LD bin" }, { "name": "Chromosome", "description": "Chromosome number each LD bin resides (Chr1 - Chr22, ChrX)" }, { "name": "Position Start", "description": "Start position of LD bin (nucleotide position in each chromosome, according to NCBI Build 36)" }, { "name": "Position End", "description": "End position of LD bin (nucleotide position in each chromosome, according to NCBI Build 36)" }, { "name": "SNPs Count", "description": "Number of SNPs in LD bin" }, { "name": "tagSNPs Count", "description": "Number of tagSNPs in LD bin" }, { "name": "Best tagSNP", "description": "tagSNP that showed the highest mean r2, given by RefSNP ID (rs number)\r\n(Link to dbSNP available in quick search)" } ] }, { "path": "en\/dhaplodb\/data-5.html", "name": "Genotype Data (Phase II)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-005", "description": "A list of SNP genotypes in D2(Phase II). SNP genotypes in D1 (Phase I, Perlegen 281K SNPs) and those determined using Affymetrix 500K Array for overlapping 74 CHM samples were merged and QC'ed.", "files": [ { "file_name": "mole_info_DhaploD2.txt.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/mole_info_DhaploD2.txt.gz", "file_size": "13.7MB" } ], "togodb_url": "", "data_acquisition": "Genotypes were determined using Perlegen 281K arrays and Affymetrix 500K arrays", "analysis": "The analyses by Perlegen 281K arrays are described in Kukita et al. (2005). The analyses by Affymetrix 500K are described in Higasa et al. (2009). Affymetrix markers were mapped to NCBI Build 35 (Higasa mapping was on Build 36), and merged with Perlegen data. The original Affymetrix data contained a small fraction (< 1%) of SNPs that were genotyped heterozygote. These typings were judged to be errors because the materials were presumed to be homozygotes. Thus, all heterozygous calls (in Affymetrix data) were forced to be no calls. Many of the heterozygous calls were also low S\/N calls and frequently irreproducible when tested.", "data_number": "581,235 entries", "details": [ { "name": "rs", "description": "RefSNP accession ID (rs number)" }, { "name": "chr", "description": "Chromosome number that the SNP resides (1 - 22, X)" }, { "name": "pos", "description": "Nucleotide position on chromosome that the SNP resides" }, { "name": "allele1", "description": "allele 1" }, { "name": "allele2", "description": "allele 2" }, { "name": "gtype", "description": "genotypes of 74 samples of CHMs" } ] }, { "path": "en\/dhaplodb\/data-6.html", "name": "Genotype Data (Phase III)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-006", "description": "Genotype data (876K SNPs, 87 samples). Essentially the same as described in Kukita et al. paper (2010), except that two additional samples (CHM010 and CHM035) were included. No CNV information is included in the download data.", "files": [ { "file_name": "mole_info_DhaploD3.txt.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/mole_info_DhaploD3.txt.gz", "file_size": "23.8MB" } ], "togodb_url": "", "data_acquisition": "Genotypes were determined using Affymetrix SNP 6.0 arrays", "analysis": "A hundred complete hydatidiform moles (CHMs) were genotyped using Affymetrix SNP Array 6.0, and mapped on the human reference genome sequence, NCBI Build 36. Low log2R calls, calls judged to be in deleted regions (determined by CNV analysis), and heterozygous calls were forced to no calls, as described in Kukita et al. 2010. After QCs by sample call rate and SNP call rate, the final data for 87 CHMs (876K SNPs) was obtained.", "data_number": "876,399 entries", "details": [ { "name": "chr", "description": "Chromosome number (1-22,X)" }, { "name": "sample", "description": "Sample (CHM) name" }, { "name": "rs", "description": "RefSNP accession ID (rs number)" }, { "name": "pos", "description": "Nucleotide position on chromosome" }, { "name": "allele1", "description": "allele 1" }, { "name": "allele2", "description": "allele 2" }, { "name": "gtype", "description": "genotypes of 87 CHM samples" }, { "name": "ss", "description": "Unique ID, given by Affymetrix" } ] }, { "path": "en\/dhaplodb\/data-7.html", "name": "LD_bin Data (Phase II)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-007", "description": "Results of LD bin calculations for D2 (Phase II) data sets. Files are in GFF format, and contains two kinds of lines, that are distinguishable by column# 3.\r\n- LD_BIN line: SNPs in LD bin. tagSNPs and best tagSNPs (*) are marked.\r\n- LD_BIN_BOUNDARIES: Limit of LD bin\r\n*SNP that shows the highest mean r2 among the SNPs in the bin", "files": [ { "file_name": "bin_2R80M5.gff.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/bin_2R80M5.gff.gz", "file_size": "12.1MB" } ], "togodb_url": "", "data_acquisition": "Genotype Data (Phase II)", "analysis": "Common SNPs (MAF > 5%) were selected, and LDs (r2 values) between every SNP pairs within 300 kb were calculated. LD bins were collected so that SNP pairs within the bin shows r2 >0.8, by the greedy method of ldSELECT (Carson et al., AJHG 74, 106-120, 2004) after the program was modified so that it can handle haploid data. tagSNP is the SNP that shows r2 >0.8 for all other members of the bin. Best tagSNP is the SNP that shows the highest mean r2 for all other members of the bin.", "data_number": "SNP: 541,686 entries\r\nLD Bin: 254,762 entries", "details": [ { "name": "seqname", "description": "Chromosome that the SNP resides (e.g. Chr1)" }, { "name": "source", "description": "name of dataset (e.g. CHM_2R80M5Z)" }, { "name": "feature", "description": "description of data. SNP information or LD bin boundary(e.g. LD_BIN, LD_BIN_BOUNDARIES)" }, { "name": "start", "description": "Chromosomal position of SNP or start position of bin (NCBI Build 35)" }, { "name": "end", "description": "Chromosomal position of SNP or end position of bin" }, { "name": "score", "description": "LD_BIN line: 2 for Best tagSNP, and 1 for tagSNP, and 0 for other SNP.\r\nLD_BIN_BOUNDARIES line: always \".\"" }, { "name": "strand", "description": "always \"+\"" }, { "name": "frame", "description": "always \",\"" }, { "name": "attributes", "description": "This column contains the following items.\r\n- ld_bin: LD bin name\r\n- RSID: RefSNP ID (rs number)\r\n- tagging: flag that indicates tagSNP\r\n- besttag: flag that indicates Best tagSNP\r\n- SNPID: unique ID given by Affymetrix\r\n(e.g. ld_bin 2R80M5Z_10_1 ; RSID rs16930466 ; tagging 1 ; besttag 0 ; SNPID SNP_A-2110939)" } ] }, { "path": "en\/dhaplodb\/data-8.html", "name": "LD_bin Data (Phase III)", "database_name": "D-HaploDB", "doi": "10.18908\/lsdba.nbdc00036-008", "description": "Results of LD bin calculations for D3 (Phase III) data sets. Files are in GFF format, and contains two kinds of lines, that are distinguishable by column# 3.\r\n- LD_BIN line: SNPs in LD bin. tagSNPs and best tagSNPs (*) are marked.\r\n- LD_BIN_BOUNDARIES: Limit of LD bin\r\n*SNP that shows the highest mean r2 among the SNPs in the bin", "files": [ { "file_name": "bin_3R80M5Zb36.gff.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dhaplodb\/LATEST\/bin_3R80M5Zb36.gff.gz", "file_size": "12.8MB" } ], "togodb_url": "", "data_acquisition": "Genotype Data (Phase III)", "analysis": "Common SNPs (MAF > 5%) were selected, and LDs (r2 values) between every SNP pairs within 300 kb were calculated. LD bins were collected so that SNP pairs within the bin shows r2 >0.8, by the greedy method of Tagzilla, which is based on the principle similar to ldSELECT (Carson et al., AJHG 74, 106-120, 2004). tagSNP is the SNP that shows r2 >0.8 for all other members of the bin. Best tagSNP is the SNP that shows the highest mean r2 for all other members of the bin.", "data_number": "SNP: 565,646 entries\r\nLD Bin: 250,751 entries", "details": [ { "name": "seqname", "description": "Chromosome that the SNP resides (e.g. Chr1)" }, { "name": "source", "description": "name of dataset (e.g. CHM_3R80M5Z)" }, { "name": "feature", "description": "description of data. SNP information or LD bin boundary (e.g. LD_BIN, LD_BIN_BOUNDARIES)" }, { "name": "start", "description": "Chromosomal position of SNP or start position of bin (NCBI Build 36)" }, { "name": "end", "description": "Chromosomal position of SNP or end position of bin" }, { "name": "score", "description": "LD_BIN line: 2 for Best tagSNP, and 1 for tagSNP, and 0 for other SNP.\r\nLD_BIN_BOUNDARIES line: always \".\"" }, { "name": "strand", "description": "always \"+\"" }, { "name": "frame", "description": "always \".\"" }, { "name": "attributes", "description": "This column contains the following items\r\n- ld_bin: LD bin name\r\n- RSID: RefSNP ID (rs number)\r\n- tagging: flag that indicates tagSNP\r\n- besttag: flag that indicates Best tagSNP\r\n- SNPID: unique ID given by Affymetrix\r\n(e.g. ld_bin 3R80M5Z_10_2 ; RSID rs16930466 ; tagging 1 ; besttag 0 ; SNPID SNP_A-2110939)" } ] }, { "path": "en\/dbspire\/data-1.html", "name": "PROSITE List", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-001", "description": "The list shows PROSITE entries and PDB entry\/chain matching status.", "files": [ { "file_name": "dbspire_prosite_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_prosite_list.zip", "file_size": "29.1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_prosite_list#en", "data_acquisition": "PROSITE", "analysis": "word search, motif search", "data_number": "1,565 entries", "details": [ { "name": "prositeLisAC", "description": "PROSITE DO" }, { "name": "PROSITE Info", "description": "Link to PROSITE Information from prositeLisAC (simple search only)" }, { "name": "prositeLisFamilySize", "description": "Number of ACs for this PROSITE DO" }, { "name": "prositeLisDE", "description": "Description of this PROSITE DO" }, { "name": "prositeLisPatternSize", "description": "Number of \"Pattern\" ACs for this PROSITE DO" }, { "name": "prositeLisRuleSize", "description": "Number of \"Rule\" ACs for this PROSITE DO" }, { "name": "prositeLisRuleWithPASize", "description": "Number of \"Pattern\" and \"Rule\" ACs for this PROSITE DO" }, { "name": "prositeLisRuleWithMASize", "description": "Number of \"Matrix\" and \"Rule\" ACs for this PROSITE DO" }, { "name": "prositeLisMatrixSize", "description": "Number of \"Matrix\" ACs for this PROSITE DO" }, { "name": "prosite3dLisIdSize", "description": "Number of PDB entries for this PROSITE DO (in PROSITE)" }, { "name": "prosite3dSeqIdLisSize", "description": "Number of PDB entries whose SEQRES matches this PROSITE DO" }, { "name": "prosite3dSeqChainLisSize", "description": "Number of PDB chains whose SEQRES matches this PROSITE DO" }, { "name": "prosite3dAtomIdLisSize", "description": "Number of PDB entries whose ATOM matches this PROSITE DO" }, { "name": "prosite3dAtomChainLisSize", "description": "Number of PDB chains whose ATOM matches this PROSITE DO" } ] }, { "path": "en\/dbspire\/data-2.html", "name": "PROSITE Information", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-002", "description": "It shows PROSITE entries and PDB entry\/chain matching status.", "files": [ { "file_name": "dbspire_prosite_info.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_prosite_info.zip", "file_size": "54.8 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_prosite_info#en", "data_acquisition": "PROSITE", "analysis": "word search, motif search", "data_number": "2,178 entries", "details": [ { "name": "prositeAC", "description": "PROSITE Accession" }, { "name": "PDB SEQRES", "description": "Link to PROSITE - PDB SEQRES matching from prositeAC (simple search only)" }, { "name": "prositeID", "description": "PROSITE ID" }, { "name": "prositeIDType", "description": "Accession type" }, { "name": "prositeDE", "description": "Description of this entry" }, { "name": "prositeDO", "description": "PROSITE DO of this entry" }, { "name": "prosite3dSize", "description": "Number of PDB entries for this entry (in PROSITE)" }, { "name": "prosite3dSeqIdSize", "description": "Number of PDB entries whose SEQRES matches this entry" }, { "name": "prosite3dSeqChainSize", "description": "Number of PDB chains whose SEQRES matches this entry" }, { "name": "prosite3dAtomIdSize", "description": "Number of PDB entries whose ATOM matches this entry" }, { "name": "prosite3dAtomChainSize", "description": "Number of PDB chains whose ATOM matches this entry" } ] }, { "path": "en\/dbspire\/data-3.html", "name": "PROSITE - PDB SEQRES matching", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-003", "description": "Sequence numbers of PDB entries\/chains whose SEQRES matches a PROSITE entry", "files": [ { "file_name": "dbspire_prosite_pdb_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_prosite_pdb_seq.zip", "file_size": "4.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_prosite_pdb_seq#en", "data_acquisition": "PROSITE, PDB(Protein Data Bank)", "analysis": "word search, motif search", "data_number": "654,777 entries", "details": [ { "name": "prositeAC", "description": "PROSITE Accession" }, { "name": "pdbID", "description": "PDB ID" }, { "name": "pdbChain", "description": "PDB chain" }, { "name": "pdbMatchLine", "description": "Sequence numbers of PDB entries\/chains whose SEQRES matches this PROSITE entry" } ] }, { "path": "en\/dbspire\/data-4.html", "name": "BLOCKS List", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-004", "description": "The list shows BLOCKS entries and PDB entry\/chain matching status.", "files": [ { "file_name": "dbspire_blocks_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_blocks_list.zip", "file_size": "113 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_blocks_list#en", "data_acquisition": "BLOCKS", "analysis": "word search, motif search", "data_number": "5,900 entries", "details": [ { "name": "blocksFamilyAC", "description": "BLOCKS Family Accession" }, { "name": "BLOCKS Info", "description": "Link to BLOCKS Information from blocksFamilyAC (simple search only)" }, { "name": "blocksType", "description": "Origing of this entry (PRINTS or PROTMAT)" }, { "name": "blocksFamilySize", "description": "Number of ACs for this family accession" }, { "name": "blocksPrints", "description": "PRINTS Accession (only from PRINTS)" }, { "name": "blocksName", "description": "Description of this entry" }, { "name": "blocks3dIdFamilySize", "description": "Number of PDB entries annotated with this entry by MAST" }, { "name": "blocks3dChainFamilySize", "description": "Number of PDB chains annotated with this entry by MAST" }, { "name": "blocks3dSeqIdFamilySize", "description": "Number of PDB entries whose SEQRES matches this entry" }, { "name": "blocks3dSeqChainFamilySize", "description": "Number of PDB chains whose SEQRES matches this entry" }, { "name": "blocks3dAtomIdFamilySize", "description": "Number of PDB entries whose ATOM matches this entry" }, { "name": "blocks3dAtomChainFamilySize", "description": "Number of PDB chains whose ATOM matches this entry" } ] }, { "path": "en\/dbspire\/data-5.html", "name": "BLOCKS Information", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-005", "description": "It shows BLOCKS entries and PDB entry\/chain matching status.", "files": [ { "file_name": "dbspire_blocks_info.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_blocks_info.zip", "file_size": "305 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_blocks_list#en", "data_acquisition": "BLOCKS", "analysis": "word search, motif search", "data_number": "29,068 entries", "details": [ { "name": "blocksAC", "description": "BLOCKS Accession" }, { "name": "PDB SEQRES", "description": "Link to BLOCKS - PDB SEQRES matching from BLOCKS AC (simple search only)" }, { "name": "PDB ATOM", "description": "Link to BLOCKS - PDB ATOM matching from BLOCKS AC (simple search only)" }, { "name": "blocksACFamily", "description": "BLOCKS Family Accession" }, { "name": "Family VS PDB", "description": "Link to BLOCKS - matching from BLOCKS AC Family (simple search only)" }, { "name": "blocksID", "description": "BLOCKS ID" }, { "name": "blocksDE", "description": "Description of this entry" }, { "name": "blocks3dIdSize", "description": "Number of PDB entries annotated with this entry by MAST" }, { "name": "blocks3dChainSize", "description": "Number of PDB chains annotated with this entry by MAST" }, { "name": "blocks3dSeqIdSize", "description": "Number of PDB entries whose SEQRES matches this entry" }, { "name": "blocks3dSeqChainSize", "description": "Number of PDB chains whose SEQRES matches this entry" }, { "name": "blocks3dAtomIdSize", "description": "Number of PDB entries whose ATOM matches this entry" }, { "name": "blocks3dAtomChainSize", "description": "Number of PDB chains whose ATOM matches this entry" } ] }, { "path": "en\/dbspire\/data-6.html", "name": "BLOCKS - PDB matching", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-006", "description": "PDB entries\/chains which matches a BLOCKS entry", "files": [ { "file_name": "dbspire_blocks_pdb.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_blocks_pdb.zip", "file_size": "512 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_blocks_pdb#en", "data_acquisition": "BLOCKS, PDB", "analysis": "word search, motif search", "data_number": "166,232 entries", "details": [ { "name": "blocksFamilyAC", "description": "BLOCKS Family Accession" }, { "name": "pdbID", "description": "PDB ID" }, { "name": "pdbChain", "description": "PDB Chain" } ] }, { "path": "en\/dbspire\/data-7.html", "name": "BLOCKS - PDB SEQRES matching", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-007", "description": "Sequence numbers of PDB entries\/chains whose SEQRES matches a BLOCKS entry", "files": [ { "file_name": "dbspire_blocks_pdb_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_blocks_pdb_seq.zip", "file_size": "6.4 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_blocks_pdb_seq#en", "data_acquisition": "BLOCKS, PDB", "analysis": "word search, motif search", "data_number": "858,156 entries", "details": [ { "name": "blocksFamilyAC", "description": "BLOCKS Accession" }, { "name": "pdbID", "description": "PDB ID" }, { "name": "pdbChain", "description": "PDB Chain" }, { "name": "pdbMatchLine", "description": "Sequence numbers of PDB entries\/chains whose SEQRES matches this BLOCKS entry" } ] }, { "path": "en\/dbspire\/data-8.html", "name": "BLOCKS - PDB ATOM matching", "database_name": "DB-SPIRE", "doi": "10.18908\/lsdba.nbdc00411-008", "description": "Sequence numbers of PDB entries\/chains whose ATOM matches a BLOCKS entry", "files": [ { "file_name": "dbspire_blocks_pdb_atom.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbspire\/LATEST\/dbspire_blocks_pdb_atom.zip", "file_size": "6.2 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbspire_blocks_pdb_atom#en", "data_acquisition": "BLOCKS, PDB", "analysis": "word search, motif search", "data_number": "824,198 entries", "details": [ { "name": "blocksFamilyAC", "description": "BLOCKS Accession" }, { "name": "pdbID", "description": "PDB ID" }, { "name": "pdbChain", "description": "PDB Chain" }, { "name": "pdbIndex", "description": "ATOM Start position" }, { "name": "pdbMatchLine", "description": "Sequence numbers of PDB entries\/chains whose SEQRES matches this BLOCKS entry" } ] }, { "path": "en\/dbqsnp\/data-1.html", "name": "Allele Frequency Data", "database_name": "dbQSNP", "doi": "10.18908\/lsdba.nbdc00042-001", "description": "SNP allele frequencies in Japanese and European populations, determined by quantitative fluorescent PCR-SSCP analysis of pooled DNA.", "files": [ { "file_name": "dbqsnp_frequency.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbqsnp\/LATEST\/dbqsnp_frequency.zip", "file_size": "159 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbqsnp_frequency#en", "data_acquisition": "Most of SNPs described here were initially collected by Sanger sequencing of transcription start sites (TSSs) of 8 randomly picked Japanese. Short fragments harboring the SNPs were further analyzed for their allele frequencies in several populations using quantitative fluorescent PCR-SSCP analysis of pooled DNA samples (Kukita et al. 2002; Baba et al. 2003: Tahira et al. 2005). A part of the results of association study of breast cancer patients (Miyagi et al. unpublished) and lupus erythematosus patients were also included (Miyagawa et al. 2008; Sakaguchi et al. unpublished).", "analysis": "Data analysis of fluorescent SSCP analysis was performed using QUISCA software that was integrated in dbQSNP system (Higasa et al. 2002; Sasaki et al. 2001; Tahira et al. 2005). SNPs in dbQSNP were submitted to dbSNP of NCBI under the handle name of KYUGEN, and refSNP ID #s were identified or given.", "data_number": "16,503 entries", "details": [ { "name": "dbQSNP_id", "description": "dbQSNP ID." }, { "name": "strand", "description": "Orientation of the STS compared with contig sequence of GenBank (NT sequence, NCBI Build 36) . Note that SNPs are always described as sequences in forward strand of the STS." }, { "name": "contig_id", "description": "ID of genomic contigs that showed highest homology to the STS (NT sequence, NCBI Build 36)" }, { "name": "rs#", "description": "dbSNP accession for the refSNP (dbSNP Build 128)" }, { "name": "allele_1", "description": "sequence of allele 1" }, { "name": "allele_2", "description": "sequence of allele 2" }, { "name": "AF_allele_1", "description": "allele frequency of allele 1" }, { "name": "AF_allele_2", "description": "allele frequency of allele 2" }, { "name": "pool_id", "description": "ID of pooled DNA (see below, DNA samples were extracted from peripheral blood lymphocytes)\r\n\"CAU200\", prepared from Caucasian Panel of 200, obtained from CORIELL (HD200, https:\/\/www.coriell.org) was used as the Caucasian pool in a large part of this study. \"CP\" (combined CEPH parents, prepared by us from 45 CEPH core family collection) and \"COP\" (HD100 from CORIELL) were also used.\r\n\r\n\"JSA426\", prepared from DNA derived from apparently healthy individuals enrolled at Kyushu area was used as the Japanese pool in a large part of study. Other pools derived from healthy individuals enrolled at various area of Japan were also used. Those were; JPK, JPK2, JPK3, JCM253, NCEP, NCL_P, NCP269, NCE_SP and JNCL_SP.\r\n\r\nThe allele frequency data of pools derived from breast cancer patients (BREP, BRLP, JBRE_SP, JBRL_SP) and pools derived from systemic lupus erythematosus patients (SLEP264, SLEP183), obtained in association studies of each diseases, are also included" }, { "name": "#individual", "description": "The number of individuals in the pool" } ] }, { "path": "en\/dbqsnp\/data-2.html", "name": "Sequence Data", "database_name": "dbQSNP", "doi": "10.18908\/lsdba.nbdc00042-002", "description": "SNPs and their flanking sequences were determined by Sanger sequencing of PCR products amplified from randomly picked Japanese individuals (in most cases, eight individuals).", "files": [ { "file_name": "dbqsnp_fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbqsnp\/LATEST\/dbqsnp_fasta.zip", "file_size": "1.0 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dbqsnp_fasta#en", "data_acquisition": "SNPs were identified by Phred\/Phrap\/Polyphred (http:\/\/www.phrap.org\/; http:\/\/droog.gs.washington.edu\/polyphred\/) and visual inspection. Insertions\/deletions were detected by software developed by us (Miura et al. JP-4009481-B2).", "analysis": "SNPs newly detected in this study was submitted to dbSNP under the handle name \"KYUGEN\".", "data_number": "10,848 entries", "details": [ { "name": "dbQSNP_id", "description": "dbQSNP ID." }, { "name": "allele_Pos", "description": "Variation allele position (1st base of variation) on the fasta sequence. It is always the 5' length plus 1." }, { "name": "total_Len", "description": "Total number of bases of the fasta sequence, a sum of length of 5', 3' and variation (A length of variation can be more than 1 in the case of ins\/del polymorphisms)." }, { "name": "Internal_STS_ID", "description": "Internal STS ID" }, { "name": "alleles", "description": "Lists alleles of the SNP separated by '\/'." }, { "name": "sequence", "description": "Sequence" } ] }, { "path": "en\/dbqsnp\/data-3.html", "name": "Original Dataset", "database_name": "dbQSNP", "doi": "10.18908\/lsdba.nbdc00042-003", "description": "Files which were formerly available from the original site ( http:\/\/qsnp.gen.kyushu-u.ac.jp\/download\/ , closed) - Readme.txt, dbQSNP.15.fasta.txt (\"Sequence Data\" original data), Frequency.15.txt (\"Allele Frequency Data\" original data) and the subdirectory pml\/ is included - the subdirectory old\/ is not included - pml\/ includes data in PML (Polymorphism Markup Language) which is based on XML to facilitate portability.", "files": [ { "file_name": "dbQSNPdownload.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dbqsnp\/LATEST\/dbQSNPdownload.tar.gz", "file_size": "1.2 MB" } ], "togodb_url": "", "data_acquisition": "Refer to pages of \"Allele Frequency Data\" and \"Sequence Data\".", "analysis": "Refer to pages of \"Allele Frequency Data\" and \"Sequence Data\".", "data_number": "", "details": [] }, { "path": "en\/dgby\/data-1.html", "name": "Experiments list", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-001", "description": "Published experimental data", "files": [ { "file_name": "dgby_main_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/dgby_main_en.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dgby_main_en", "data_acquisition": "Gene expression analyses using DNA microarray\r\nGenome-wide screening of deletion strain set of budding yeast", "analysis": "Transcriptomics\r\nPhenomics", "data_number": "7", "details": [ { "name": "ID", "description": "experiment ID" }, { "name": "Post-genomic approache", "description": "experimental method" }, { "name": "Stress", "description": "experimental condition" }, { "name": "Data file (GEO)", "description": "Registered ID in GEO" }, { "name": "Data file (CSV)", "description": "Name of data file in CSV format" }, { "name": "Data file (Excel)", "description": "Name of data file in Excel format" }, { "name": "Simple search", "description": "Table in the simple search site" }, { "name": "Reference (PubMed)", "description": "PubMed ID of reference" } ] }, { "path": "en\/dgby\/data-2.html", "name": "Transcriptome data - Initial stage of dough fermentation", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-002", "description": "Gene expression profiles of baker's yeast during initial dough-fermentation were investigated using liquid fermentation (LF) media to obtain insights at the molecular level into rapid adaptation mechanisms of baker's yeast. Results showed the onset of fermentation caused drastic changes in gene expression profiles within 15 min. Genes involved in the tricarboxylic acid (TCA) cycle were downregulated and genes involved in glycolysis were upregulated, indicating a metabolic shift from respiration to fermentation. Genes involved in ethanol production (PDC genes and ADH1), in glycerol synthesis (GPD1 and HOR2), and in low-affinity hexose transporters (HXT1 and HXT3) were upregulated at the beginning of model dough-fermentation. Among genes upregulated at 15 min, several genes classified as transcription were downregulated within 30 min. These down-regulated genes are involved in messenger RNA splicing and ribosomal protein biogenesis and in transcriptional regulator (SRB8, MIG1). In contrast, genes involved in amino acid metabolism and in vitamin metabolism, such as arginine biosynthesis, riboflavin biosynthesis, and thiamin biosynthesis, were subsequently upregulated after 30 min. Interestingly, the genes involved in the unfolded protein response (UPR) pathway were also subsequently upregulated. Our study presents the first overall description of the transcriptional response of baker's yeast during dough-fermentation, and will thus help clarify genomic responses to various stresses during commercial fermentation processes.", "files": [ { "file_name": "GEO Accession No: GSE3043", "file_url": "http:\/\/www.ncbi.nlm.nih.gov\/projects\/geo\/query\/acc.cgi?acc=GSE3043", "file_size": "" } ], "togodb_url": "", "data_acquisition": "Affymetrix Yeast Genome S98 Array", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/dgby\/data-3.html", "name": "Transcriptome data - High-sugar stress", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-003", "description": "In the modern baking industry, high-sucrose-tolerant (HS) and maltose-utilizing (LS) yeast were developed using breeding techniques and are now used commercially. Sugar utilization and high-sucrose tolerance differ significantly between HS and LS yeasts. We analyzed the gene expression profiles of HS and LS yeasts under different sucrose conditions in order to determine their basic physiology. Two-way hierarchical clustering was performed to obtain the overall patterns of gene expression. The clustering clearly showed that the gene expression patterns of LS yeast differed from those of HS yeast. Quality threshold clustering was used to identify the gene clusters containing upregulated genes (cluster 1) and downregulated genes (cluster 2) under high-sucrose conditions. Clusters 1 and 2 contained numerous genes involved in carbon and nitrogen metabolism, respectively. The expression level of the genes involved in the metabolism of glycerol and trehalose, which are known to be osmoprotectants, in LS yeast was higher than that in HS yeast under sucrose concentrations of 5-40%. No clear correlation was found between the expression level of the genes involved in the biosynthesis of the osmoprotectants and the intracellular contents of the osmoprotectants. The current gene expression data were compared with data previously reported in a comprehensive analysis of a gene deletion strain collection. Welch's t-test for this comparison showed that the relative growth rates of the deletion strains whose deletion occurred in genes belonging to cluster 1 were significantly higher than the average growth rates of all deletion strains.", "files": [ { "file_name": "GEO Accession No: GSE4295", "file_url": "http:\/\/www.ncbi.nlm.nih.gov\/projects\/geo\/query\/acc.cgi?acc=GSE4295", "file_size": "" } ], "togodb_url": "", "data_acquisition": "Affymetrix Yeast Genome 2.0 Array", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/dgby\/data-4.html", "name": "Transcriptome data - Air-drying stress", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-004", "description": "Changes in the gene expression of commercial baker’s yeast during an air-drying process, which simulated dried yeast production, were analyzed. K-means clustering suggested that the genes involved in protein folding were transiently upregulated at early stages, and that the genes involved in fatty acid metabolism were continuously upregulated.", "files": [ { "file_name": "GEO Accession No: GSE6454", "file_url": "http:\/\/www.ncbi.nlm.nih.gov\/geo\/query\/acc.cgi?acc=GSE6454", "file_size": "" } ], "togodb_url": "", "data_acquisition": "Affymetrix Yeast Genome S98 Array", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/dgby\/data-5.html", "name": "Phenome data - High-sugar stress", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-005", "description": "Yeasts used in bread making are exposed to high concentrations of sucrose during sweet dough fermentation. Despite its importance, tolerance to high-sucrose stress is poorly understood at the gene level. To clarify the genes required for tolerance to high-sucrose stress, genome-wide screening was undertaken using the complete deletion strain collection of diploid Saccharomyces cerevisiae. The screening identified 273 deletions that yielded high sucrose sensitivity, approximately 20 of which were previously uncharacterized. These 273 deleted genes were classified based on their cellular function and localization of their gene products. Cross-sensitivity of the high-sucrose-sensitive mutants to high concentrations of NaCl and sorbitol was studied. Among the 273 sucrose-sensitive deletion mutants, 269 showed cross-sensitivities to sorbitol or NaCl, and four (i.e. ade5,7, ade6, ade8, and pde2) were specifically sensitive to high sucrose. The general stress response pathways via high-osmolarity glycerol and stress response element pathways and the function of the invertase in the ade mutants were similar to those in the wild-type strain. In the presence of high-sucrose stress, intracellular contents of ATP in ade mutants were at least twofold lower than that of the wild-type cells, suggesting that depletion of ATP is a factor in sensitivity to high-sucrose stress. The genes identified in this study might be important for tolerance to high-sucrose stress, and therefore should be target genes in future research into molecular modification for breeding of yeast tolerant to high-sucrose stress.", "files": [ { "file_name": "CSV: dbgy_high_sugar_stress.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/dgby_high_sugar_stress.zip", "file_size": "90KB" }, { "file_name": "Original file: High-sugar_stress.xls", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/High-sugar_stress.xls", "file_size": "674KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dgby_high_sugar_stress#en", "data_acquisition": "OD630 of yeast culture grown in YPD medium containing 30 % sucrose for 20 h was measured using microtitre platereader Elx800.", "analysis": "Rate of OD630 of the mutant to that of the wild-type strain BY4743 was calcurated.", "data_number": "4,713", "details": [ { "name": "ORF", "description": "Systematic Name in SGD（Saccharomyces Genome Database；http:\/\/www.yeastgenome.org\/)" }, { "name": "GENE", "description": "Standard Gene Name in SGD" }, { "name": "Growth rate YM\/YW", "description": "Rate of growth in YPD medium (Mutant\/Wild-type）" }, { "name": "Growth rate SM\/SW", "description": "Rate of growth in YPD medium containing 30% sucrose (Mutant\/Wild-type）" }, { "name": "DESCRIPTION (MIPS)", "description": "Description in MIPS（Munich Information Center for Protein Sequences）" } ] }, { "path": "en\/dgby\/data-6.html", "name": "Phenome data - Freeze-thaw stress", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-006", "description": "Yeasts used in bread making are exposed to freeze-thaw stress during frozen-dough baking. To clarify the genes required for freeze-thaw tolerance, genome-wide screening was performed using the complete deletion strain collection of diploid Saccharomyces cerevisiae. The screening identified 58 gene deletions that conferred freeze-thaw sensitivity. These genes were then classified based on their cellular function and on the localization of their products. The results showed that the genes required for freeze-thaw tolerance were frequently involved in vacuole functions and cell wall biogenesis. The highest numbers of gene products were components of vacuolar H+-ATPase. Next, the cross-sensitivity of the freeze-thaw-sensitive mutants to oxidative stress and to cell wall stress was studied; both of these are environmental stresses closely related to freeze-thaw stress. The results showed that defects in the functions of vacuolar H+-ATPase conferred sensitivity to oxidative stress and to cell wall stress. In contrast, defects in gene products involved in cell wall assembly conferred sensitivity to cell wall stress but not to oxidative stress. Our results suggest the presence of at least two different mechanisms of freeze-thaw injury: oxidative stress generated during the freeze-thaw process, and defects in cell wall assembly.", "files": [ { "file_name": "CSV: dgby_freeze_thaw_stress.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/dgby_freeze_thaw_stress.zip", "file_size": "88KB" }, { "file_name": "Original File(Excel): Freeze-thaw_stress.xls", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/Freeze-thaw_stress.xls", "file_size": "676KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dgby_freeze_thaw_stress#en", "data_acquisition": "Yeast cells exposed to the freeze-thaw stress were inoculated to YPD medium. After grown for 23 h, OD630 was measured using microtitre platereader Elx800. OD630 of non-stressed control cells was measured after grown for 16 h.", "analysis": "Rate of OD630 of the mutant to that of the wild-type strain BY4743 was calcurated. The rate in stress condition was normalized by the rate in non-stressed control condition.", "data_number": "4,713", "details": [ { "name": "ORF", "description": "Systematic Name in SGD（Saccharomyces Genome Database；http:\/\/www.yeastgenome.org\/）" }, { "name": "GENE", "description": "Standard Gene Name in SGD" }, { "name": "Growth rate BM\/BW", "description": "Rate of growth in non-strees condition （Mutant\/Wild-type）" }, { "name": "Growth rate (AM\/AW)\/(BM\/BW)", "description": "AM\/AW represents rate of growth after exposure to freeze-thaw strees (Mutant\/Wild-type), (AM\/AW)\/(BM\/BW) represents rate of AM\/AW to BM\/BW" }, { "name": "DESCRIPTION (MIPS)", "description": "Description in MIPS（Munich Information Center for Protein Sequences）" } ] }, { "path": "en\/dgby\/data-7.html", "name": "Phenome data - Air-drying stress", "database_name": "DGBY", "doi": "10.18908\/lsdba.nbdc00953-007", "description": "Yeasts used in bread making are exposed to air-drying stress during dried yeast production processes. To clarify the genes required for air-drying tolerance, we performed genome-wide screening using the complete deletion strain collection of diploid Saccharomyces cerevisiae. The screening identified 278 gene deletions responsible for air-drying sensitivity. These genes were classified based on their cellular function and on the localization of their gene products. The results showed that the genes required for air-drying tolerance were frequently involved in mitochondrial functions and in connection with vacuolar H+-ATPase, which plays a role in vacuolar acidification. To determine the role of vacuolar acidification in air-drying stress tolerance, we monitored intracellular pH. The results showed that intracellular acidification was induced during air-drying and that this acidification was amplified in a deletion mutant of the VMA2 gene encoding a component of vacuolar H+-ATPase, suggesting that vacuolar H+-ATPase helps maintain intracellular pH homeostasis, which is affected by air-drying stress. To determine the effects of air-drying stress on mitochondria, we analyzed the mitochondrial membrane potential under air-drying stress conditions using MitoTracker. The results showed that mitochondria were extremely sensitive to air-drying stress, suggesting that a mitochondrial function is required for tolerance to air-drying stress. We also analyzed the correlation between oxidative-stress sensitivity and air-drying-stress sensitivity. The results suggested that oxidative stress is a critical determinant of sensitivity to air-drying stress, although ROS-scavenging systems are not necessary for air-drying stress tolerance.", "files": [ { "file_name": "CSV: dgby_air_drying_stress.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/dgby_air_drying_stress.zip", "file_size": "89KB" }, { "file_name": "Original File(Excel): Air-drying_stress.xls", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dgby\/LATEST\/Air-drying_stress.xls", "file_size": "676KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dgby_air_drying_stress#en", "data_acquisition": "Yeast cells exposed to the air-drying stress were inoculated to YPD medium. After grown for 25 h, OD630 was measured using microtitre platereader Elx800. OD630 of non-stressed control cells was measured after grown for 16 h.", "analysis": "Rate of OD630 of the mutant to that of the wild-type strain BY4743 was calcurated. The rate in stress condition was normalized by the rate in non-stressed control condition.", "data_number": "4,713", "details": [ { "name": "ORF", "description": "Systematic Name in SGD (Saccharomyces Genome Database；http:\/\/www.yeastgenome.org\/)" }, { "name": "GENE", "description": "Standard Gene Name in SGD" }, { "name": "Growth rate BM\/BW", "description": "Rate of growth in non-stress condition (Mutant\/Wild-type)" }, { "name": "Growth rate (DM\/DW)\/(BM\/BW)", "description": "DM\/DW represents rate of growth after exposure to air-drying stress (Mutant\/Wild-type). (DM\/DW)\/(BM\/BW) represents rate of DM\/DW to BM\/BW." }, { "name": "DESCRIPTION (MIPS)", "description": "Description in MIPS（Munich Information Center for Protein Sequences)" } ] }, { "path": "en\/dicty-cdb\/data-1.html", "name": "EST sequences and their annotation (amino acid sequence and results of homology search)", "database_name": "Dicty_cDB", "doi": "10.18908\/lsdba.nbdc00419-001", "description": "Sequences of cDNA clones of Dictyostelium discoideum and their annotations (amino acid sequence, homology search results (with target DBs: dicty EST-DB, DNA-DB and protein-DB)). Links to the Atlas database (http:\/\/dictycdb.biol.tsukuba.ac.jp\/~tools\/bin\/ISH\/index.html), which is the database of images depicting localization of clones in Dictyostelium discoideum, the National BioResource Project (http:\/\/www.nbrp.jp\/) and the dictyBase (http:\/\/dictybase.org\/) are provided. Link to the table of contigs containing EST sequences is also provided. For each clone, the following four categories are established: 5' EST sequence, 3' EST sequence, 5' EST-3'EST-ligated sequence and full-length cDNA sequence. If both 5' EST sequence and 3' EST sequence are available, the treatment to ligate the 5' EST sequence to the 3' EST sequence is peformed to generate a sequence connecting the two sequences with ten pieces of hyphen. If an overlapped region exists between the two sequences, the sequence obtained by overlapping is considered as a full-length sequence. For some clones that do not allow overlapping, the full-length is obtained by sequencing the gap region. F, Z, P and E are added to the end of the Clone ID to identify 5' EST sequence, 3' EST sequence, 5' EST-3'EST-ligated sequence and full-length cDNA sequence. For each clone, these sequences are stored on a single line. Among these sequences, one sequence is selected as the representative sequence by prioritizing full-length cDNA sequence, 5' EST-3'EST-ligated sequence, 5' EST sequence and 3' EST sequence in this order, and the BLAST-based homology search is performed. Search is performed by the blastn search against clone sequences of dicty_cDB, the DNA sequence in public database, and blastx search against the protein sequence in public database, and then the top 10 hit information is stored. CSV format text file.", "files": [ { "file_name": "dicty_cdb_clone.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dicty_cdb\/LATEST\/dicty_cdb_clone.zip", "file_size": "181MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dicty_cdb_clone#en", "data_acquisition": "Capillary sequencer", "analysis": "Clones obtained from 11 different cDNA libraries originating from five developmental stages were sequenced.", "data_number": "97,337 entries", "details": [ { "name": "IDs and Links", "description": "" }, { "name": "Library", "description": "14 different sequenced cDNA libraries (AF, AH, CF, CH, FC, FC-IC, FCL, SF, SH, SL, SS, VF, VH and VS) derived from five developmental stages." }, { "name": "Clone ID", "description": "ID of cDNA clone" }, { "name": "Atlas ID", "description": "ID of Atlas database (http:\/\/dictycdb.biol.tsukuba.ac.jp\/~tools\/bin\/ISH\/index.html) and link to Atlas database" }, { "name": "NBRP ID", "description": "ID of cDNA clone covering full-length ORF provided by the National BioResource Project (http:\/\/www.nbrp.jp\/). The link to the \"National BioResource Project (NBRP) Dictyostelium discoideum\" gene database (http:\/\/nenkin.lab.nig.ac.jp\/genes?locale=en) is provided in the TogoDB edition." }, { "name": "dictyBase ID", "description": "ID of Protein Coding Gene in dictyBase (http:\/\/dictybase.org\/). The link to dictyBase is provided in the TogoDB edition." }, { "name": "Link to Contig", "description": "Link to contig containing EST (TogoDB edition only)" }, { "name": "Representative Seq. and Annotation", "description": "" }, { "name": "Representative seq. ID", "description": "ID of DNA sequence used in homology search. Among these sequences, one sequence is selected as the representative DNA sequence by prioritizing 1) full-length cDNA sequence, 2) 5' EST-3'EST-ligated sequence, 3) 5' EST sequence and 4) 3' EST sequence in this order." }, { "name": "Representative DNA sequence", "description": "Representative DNA sequence" }, { "name": "sequence update", "description": "Last update of representative DNA sequence" }, { "name": "Translated Amino Acid sequence", "description": "Amino acid sequence translated from representative DNA sequence" }, { "name": "Translated Amino Acid sequence (All Frames)", "description": "Amino acid sequences resulting from translation in all six reading frames of DNA sequence" }, { "name": "Homology vs CSM-cDNA", "description": "List of top 10 hits in blastn search against the clone sequence in dicty_cDB" }, { "name": "own update", "description": "Last update of homology search against CSM (a set of clone sequences)" }, { "name": "Homology vs DNA", "description": "List of top 10 hits in blastn search against DNA sequences in public database" }, { "name": "dna update", "description": "Last update of homology search against DNA sequences in public database" }, { "name": "Homology vs Protein", "description": "List of top 10 hits in blastx search against protein sequences in public database" }, { "name": "protein update", "description": "Last update of homology search against protein sequences in public database" }, { "name": "PSORT", "description": "The results of PSORT (http:\/\/psort.ims.u-tokyo.ac.jp\/), which is a program to predict the subcellular localization of proteins." }, { "name": "Seqeunces", "description": "" }, { "name": "5' end seq. ID", "description": "ID of 5' EST sequence. \"F\" is added to the end of ID." }, { "name": "5' end seq.", "description": "5' EST sequence. FASTA format." }, { "name": "Length of 5' end seq.", "description": "Length of 5' EST sequence." }, { "name": "3' end seq. ID", "description": "ID of 3' EST sequence. \"Z\" is added to the end of ID." }, { "name": "3' end seq.", "description": "3' EST sequence. FASTA format." }, { "name": "Length of 3' end seq.", "description": "Length of 3' EST sequence." }, { "name": "Connected seq. ID", "description": "ID of 5' EST-3' EST-ligated sequence. \"P\" is added to the end of ID." }, { "name": "Connected seq.", "description": "Sequence of 5' EST ligated to 3' EST by 10 gaps (-)." }, { "name": "Length of connected seq.", "description": "ID of 5' EST-3' EST-ligated sequence. (Gap (-) are not counted.)" }, { "name": "Full length Seq ID", "description": "ID of full-length cDNA. \"E\" is added to the end of ID." }, { "name": "Full length Seq.", "description": "Full-length cDNA sequence. FASTA format." }, { "name": "Length of full length seq.", "description": "Length of full-length cDNA." } ] }, { "path": "en\/dicty-cdb\/data-2.html", "name": "Contig sequences and their annotation (amino acid sequence and results of homology search), and expression profile", "database_name": "Dicty_cDB", "doi": "10.18908\/lsdba.nbdc00419-002", "description": "Contig sequences of cDNA sequences of Dictyostelium discoideum and their annotation (amino acid sequence and results of homology search (with target DBs: contig sequence-DB, DNA-DB and protein-DB)). Contig sequences are obtained by assemblying 5' EST sequence, 3' EST sequence, 5' EST-3'EST-ligated sequence and full-length cDNA sequence by the assembly program Phrap (http:\/\/www.phrap.org\/index.html). Link to the list of clones constituting the contig, the information on its mapping to the genome mapped to genome sequence and the list of top 10 hits in the results of homology search are provided. Also, the number of clones constituting the contig in each library is given for five developmental stages and 14 different libraries. Library-specific clones can be searched. The data are given in a CSV format text file.", "files": [ { "file_name": "dicty_cdb_contig.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dicty_cdb\/LATEST\/dicty_cdb_contig.zip", "file_size": "91.6MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dicty_cdb_contig#en", "data_acquisition": "", "analysis": "EST sequences were assembled by Phrap.", "data_number": "8,402 entries", "details": [ { "name": "Contig information", "description": "" }, { "name": "Contig ID", "description": "ID of contig sequence" }, { "name": "Contig update", "description": "Last update of sequence" }, { "name": "Contig sequence", "description": "Contig sequence" }, { "name": "Gap", "description": "Presence of gap (-) in contig.\r\n-If gap is included: gap included.\r\n-If gap is not included: no gap." }, { "name": "Contig length", "description": "Length of contig" }, { "name": "Chromosome number (1..6, M)", "description": "Chromosome number of the chromosome to which the contig is mapped. If mapped, numbers 1 to 6 or M (mitochondria) will be used." }, { "name": "Chromosome length", "description": "Length of the chromosome to which the contig is mapped." }, { "name": "Start point", "description": "Start position of the contig mapped to the genome." }, { "name": "End point", "description": "End position of the contig mapped to the genome." }, { "name": "Strand (PLUS\/MINUS)", "description": "Direction of the contig mapped to the genome (PLUS\/MINUS)" }, { "name": "Number of clones", "description": "Number of clones constituting the contig" }, { "name": "Number of EST", "description": "Number of ESTs constituting the contig" }, { "name": "Link to clone list", "description": "Link of all clones constituting contig to TogoDB edition. Link to the clone list is provided in the TogoDB edition only." }, { "name": "List of clone(s)", "description": "List of clones constituting contig. Link to each clone is provided in the TogoDB edition only." }, { "name": "Annotation", "description": "" }, { "name": "Translated Amino Acid sequence", "description": "Representative amino acid sequence translated from DNA sequence." }, { "name": "Translated Amino Acid sequence (All Frames)", "description": "Amino acid sequences resulting from translation in all six reading frames of DNA sequence." }, { "name": "own update", "description": "Last update of blastn search against contig sequences in dicty_cDB." }, { "name": "Homology vs CSM-cDNA", "description": "List of top 10 hits in blastn search against contig sequences in dicty_cDB." }, { "name": "dna update", "description": "Last update of blastn search against DNA sequences in public database." }, { "name": "Homology vs DNA", "description": "List of top 10 hits in the results of blastn search against DNA sequences in public database." }, { "name": "protein update", "description": "Last update of blastx search against protein sequences in public database." }, { "name": "Homology vs Protein", "description": "List of top 10 hits in the results of blastx search against protein sequences in public database." }, { "name": "PSORT", "description": "The results of running PSORT(http:\/\/psort.ims.u-tokyo.ac.jp\/), which is the program to predict the localization of proteins in the cell." }, { "name": "Expression profile", "description": "" }, { "name": "VS (DIR, S)", "description": "Number of VS-derived clones constituting the contig" }, { "name": "VH (FL, L)", "description": "Number of VH-derived clones constituting the contig" }, { "name": "VF (FL, S)", "description": "Number of VF-derived clones constituting the contig" }, { "name": "AH (FL, L)", "description": "Number of AH-derived clones constituting the contig" }, { "name": "AF (FL, S)", "description": "Number of AF-derived clones constituting the contig" }, { "name": "SL (DIR, L)", "description": "Number of SL-derived clones constituting the contig" }, { "name": "SS (DIR, S)", "description": "Number of SS-derived clones constituting the contig" }, { "name": "SH (FL, L)", "description": "Number of SH-derived clones constituting the contig" }, { "name": "SF (FL, S)", "description": "Number of SF-derived clones constituting the contig" }, { "name": "CH (FL, L)", "description": "Number of CH-derived clones constituting the contig" }, { "name": "CF (FL, S)", "description": "Number of CF-derived clones constituting the contig" }, { "name": "FCL (DIR, L)", "description": "Number of FCL-derived clones constituting the contig" }, { "name": "FC (DIR, S)", "description": "Number of FC-derived clones constituting the contig" }, { "name": "FC-IC (SUB)", "description": "Number of FC-IC-derived clones constituting the contig" } ] }, { "path": "en\/dicty-cdb\/data-3.html", "name": "cDNA library information", "database_name": "Dicty_cDB", "doi": "10.18908\/lsdba.nbdc00419-003", "description": "Description of cDNA libraries of Dictyostelium discoideum (Functional Genomics of the Social Amoebae, Dictyostelium discoideum, Hideko Urushihara, Mol. Cells, Vol. 13, No. 1, pp. 1-4, http:\/\/molcells.inforang.com\/article_pdf\/Ksmcb\/13\/Ksmcb13-1-1.pdf,http:\/\/dictycdb.biol.tsukuba.ac.jp\/cDNAproject.html,http:\/\/lifesciencedb.jp\/houkoku\/pdf\/001\/c009.pdf)", "files": [ { "file_name": "dicty_cdb_lib.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dicty_cdb\/LATEST\/dicty_cdb_lib.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dicty_cdb_lib#en", "data_acquisition": "", "analysis": "", "data_number": "14 entries", "details": [ { "name": "cDNA library name", "description": "Names of cDNA libraries (AF, AH, CF, CH, FC, FC-IC, FCL, SF, SH, SL, SS, VF, VH and VS)" }, { "name": "stages of the life cycle", "description": "Stages in the life cycle of Dictyostelium discoideum\r\n1) vegetatively growing cells (Vegetative phase)(V)\r\n2) asexually developing cells at the aggregating (Aggregation phase)(A)\r\n3) slug cells (Slug phase)(S)\r\n4) culminating stages (Morphogenetic phase)(C)\r\n5) sexually fusion-competent KAX3 cells (Gamete phase) (F)" }, { "name": "cDNA library construction method", "description": "How to construct cDNA library\r\n1) Conventional oligo-d(T) primed, directional cDNA libraries (dir)\r\n2) Full-length cDNA libraries (oligocapped method)(fl)\r\n3) Gamete-specific subtraction library (sub)" }, { "name": "cDNA library construction protocol", "description": "Link to the webpage describing the protocol for generating cDNA library" }, { "name": "Size fractionation", "description": "Size fractionation of clone\r\n1) Fractionation of long clone (long)\r\n2) Fractionation of short clone (short)\r\n3) No fractionation (no)" }, { "name": "clone size", "description": "Clone size(kb)" } ] }, { "path": "en\/dmpd\/data-1.html", "name": "Literature list concerning differentiation and activation of macrophage and pathways found in the literature", "database_name": "DMPD", "doi": "10.18908\/lsdba.nbdc00558-001", "description": "Literature list concerning curated differentiation and activation of macrophage. The list is a CSV format text file.", "files": [ { "file_name": "dmpd.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dmpd\/LATEST\/dmpd.zip", "file_size": "16KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/dynamic_macrophage_pathway_csml_db#en", "data_acquisition": "Search on PubMed", "analysis": "The curator reads the literature, and converts the contents into a pathway in the CSML format by using the Cell Illustrator Online (CIO).", "data_number": "231 entries", "details": [ { "name": "PubmedID", "description": "PubMed ID (PMID) of article" }, { "name": "Title", "description": "Article title" }, { "name": "Authors", "description": "Article author(s)" }, { "name": "Publication", "description": "Journal published the article" }, { "name": "Pathway", "description": "Diagram of the pathway (Blank in the downloaded data)" }, { "name": "PNG File", "description": "Link to the pathway diagram (PNG file) (In the downloaded data, a flag indicating the existence of the diagram is shown.)" }, { "name": "SVG File", "description": "Link to the pathway diagram (SVG file) (In the downloaded data, a flag indicating the existence of the diagram is shown.)" }, { "name": "HTML File", "description": "Link to the pathway information (HTML file) (In the downloaded data, a flag indicating the existence of the information is shown.)" }, { "name": "CSML File", "description": "Link to the pathway information (CSML file) (In the downloaded data, a flag indicating the existence of the information is shown.)" }, { "name": "Open .csml file with CIOPlayer", "description": "Link to open a CSML file on Cell Illustrator Online Player (Blank in the downloaded data.)" }, { "name": "Open .csml file with CIO", "description": "Link to open a CSML file at Cell Illustrator Online (Blank in the downloaded data.)" } ] }, { "path": "en\/dmpd\/data-2.html", "name": "Pathway data concerning differentiation and activation of macrophage", "database_name": "DMPD", "doi": "10.18908\/lsdba.nbdc00558-002", "description": "Pathways concerning differentiation and activation of macrophage extracted from the literature list in the CSML format, which is an XML format. One CSML file to an article.", "files": [ { "file_name": "macrophageCSML.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/dmpd\/LATEST\/macrophageCSML.zip", "file_size": "11.6MB" } ], "togodb_url": "", "data_acquisition": "Pathways are extracted from each paper in the above literature list in the CSML format, which is an XML format.", "analysis": "The curator reads the literature, and converts the contents into a pathway in the CSML format by using Cell Illustrator Online (CIO).", "data_number": "231 entries", "details": [] }, { "path": "en\/esol\/data-1.html", "name": "Solubility", "database_name": "eSOL", "doi": "10.18908\/lsdba.nbdc00440-001", "description": "The solubilities of individual proteins were evaluated by using a cell-free translation system (PURE system) which is chaperone-free.\r\nThe data of chaperone effects on the prevention of aggregate formation are available for 788 aggregation-prone proteins.\r\nThe concentrations of chaperones were as follows:\r\n- TF (Trigger factor): 5.0 (monomer) μM\r\n- GroE (GroEL and GroES): 0.5 (tetradecamer) and 1.0 (heptamer) μM\r\n- KJE (DnaK, DnaJ and GrpE): 5.0 (monomer), 2.0 (monomer), and 2.0 (monomer) μM", "files": [ { "file_name": "esol.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/esol\/LATEST\/esol.zip", "file_size": "192 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/esol#en", "data_acquisition": "After the protein synthesis with [35S]methionine, an aliquot was withdrawn as the total fraction, and the remainder was centrifuged at 21,600 × g for 30 min. Both the total and supernatant fractions were separated by SDS-PAGE, and the band intensities were quantified by autoradiography.", "analysis": "", "data_number": "4,132 entries. (Out of all the entries, 3,173 entries have the data of solubilities and 788 entries have the data of chaperone effects on the prevention of aggregate formation.)", "details": [ { "name": "JW_ID", "description": "Gene ID assigned by GenoBase to the E. coli strain K-12 substrain W3110." }, { "name": "ECK number", "description": "Accession number which can refer to genes in both substrains MG1655 and W3110 of the E. coli strain K-12." }, { "name": "B number", "description": "Gene accession number assigned by the Blattner laboratory to the E. coli strain K-12 substrain MG1655." }, { "name": "Gene name K-12", "description": "Gene name of the E. coli strain K-12." }, { "name": "Locus name K-12", "description": "Locus name of the E. coli strain K-12." }, { "name": "Synonyms of locus names K-12", "description": "Synonyms of the locus name of the E. coli strain K-12." }, { "name": "Solubility (%)", "description": "Solubility determined in Niwa et. al., PNAS 2009. (unit: %)" }, { "name": "Yield (uM)", "description": "Yield of the protein measured in Niwa et. al., PNAS 2009. (unit: μM)" }, { "name": "Yield (ug\/ml)", "description": "Yield of the protein measured in Niwa et. al., PNAS 2009. (unit: μg\/ml)" }, { "name": "Minus Sol (%)", "description": "Solubility in the absence of any chaperons. (unit: %) It is redetermined to evaluate chaperon effects." }, { "name": "TF Sol (%)", "description": "Solubility in the presence of Trigger Factor. (unit: %)" }, { "name": "GroE Sol (%)", "description": "Solubility in the presence of GroEL\/ES. (unit: %)" }, { "name": "KJE Sol (%)", "description": "Solubility in the presence of DnaK\/DnaJ\/GrpE. (unit: %)" }, { "name": "Minus Yield (uM)", "description": "Yield in the absence of any chaperons. (unit: μM)" }, { "name": "TF Yield (uM)", "description": "Yield in the presence of Trigger Factor. (unit: μM)" }, { "name": "GroE Yield (uM)", "description": "Yield in the presence of GroEL\/ES. (unit: μM)" }, { "name": "KJE Yield (uM)", "description": "Yield in the presence of DnaK\/DnaJ\/GrpE. (unit: μM)" }, { "name": "Minus Yield (ug\/ml)", "description": "Yield in the absence of any chaperons. (unit: μg\/ml)" }, { "name": "TF Yield (ug\/ml)", "description": "Yield in the presence of Trigger Factor. (unit: μg\/ml)" }, { "name": "GroE Yield (ug\/ml)", "description": "Yield in the presence of GroEL\/ES. (unit: μg\/ml)" }, { "name": "KJE Yield (ug\/ml)", "description": "Yield in the presence of DnaK\/DnaJ\/GrpE. (unit: μg\/ml)" }, { "name": "Calculated MW (kDa)", "description": "Molecular weight calculated from amino acid sequences. (unit: kDa)" }, { "name": "Calculated pI", "description": "Isoelectric point calculated from amino acid sequences." }, { "name": "Type of gene product", "description": "Type of gene product obtained from Genobase.\r\n(About the description of \"Type of gene product\", see this page.)" }, { "name": "Gene product description", "description": "Description obtained from Genobase." }, { "name": "Cell location", "description": "Localization in the cell." }, { "name": "Structure (PDB) ID", "description": "PDB ID obtained from Genobase." }, { "name": "SCOP assignment", "description": "SCOP assignment obtained from Genobase." } ] }, { "path": "en\/fantom5\/data-1.html", "name": "HeliscopeCAGE sequencing, Delve mapping and CAGE TSS aggregation", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-001.V003", "description": "Time course and snapshot data by HeliScopeCAGE\r\n\"basic\" directory contains the following:\r\n \r\nSubdirectories with \"CAGEScan\" in end (only human)\r\n00_.assay_sdrf.txt:Experimental information for each sample (tab-delimited text)*.bam:Binary read mapping results (BAM format)*.bam.bai:Indexes of BAM files*.3prime.fq.gz:3' sequences in CAGEscan tags (FASTQ format)*.5prime.fq.gz:5' sequences in CAGEscan tags (FASTQ format)*.clusters.bed.gzClustering results with CAGEscan (standard BED12 format). 4th column shows the CAGE tag name that represents the cluster and 5th column shows the number of pairs that constitute the cluster.*.pairs.bed.gzRead pairs mapped with CAGEscan (standard BED12 format). 4th column shows the pair's name and 5th column shows the total mapping quality value of reads.\r\n \r\nSubdirectories expect above\r\n00_.assay_sdrf.txt:Experimental information for each sample (tab-delimited text)*.bam:Binary read mapping results (BAM format)*.bam.bai:Indexes of BAM files*.ctss.bed.gz:TSS (CTSS) identified by CAGE tag analysis (BED format)*.rdna.fa.gz:rDNA sequences (FASTA format)", "files": [ { "file_name": "fantom5_experimental_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/LATEST\/fantom5_experimental_details.zip", "file_size": "273 KB" }, { "file_name": "basic", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/basic\/", "file_size": "2.5 TB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/fantom5_experimental_details#en", "data_acquisition": "", "analysis": "HeliScopeCAGE (http:\/\/fantom.gsc.riken.jp\/protocols\/heliscope.html)\r\nCAGEscan(http:\/\/fantom.gsc.riken.jp\/protocols\/nanocage.html)\r\nDelve (Alignment software for short read) (http:\/\/fantom.gsc.riken.jp\/jp\/software\/)", "data_number": "", "details": [ { "name": "Extract name", "description": "Internal ID" }, { "name": "FF ontology", "description": "Ontology ID in FANTOM" }, { "name": "Description", "description": "Description" }, { "name": "Catalog ID", "description": "RNA catalog ID" }, { "name": "Category", "description": "Category" }, { "name": "Species", "description": "Species" }, { "name": "Sex", "description": "Sex" }, { "name": "Age", "description": "Age" }, { "name": "Developmental stage", "description": "Developmental stage" }, { "name": "Tissue", "description": "Tissue" }, { "name": "Cell lot", "description": "Cell lot" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Catalogue ID", "description": "Cell catalogue ID" }, { "name": "Collaboration", "description": "Collaboration" }, { "name": "Provider", "description": "Cell provider" }, { "name": "Extraction protocol", "description": "RNA extraction protocol" }, { "name": "Material type", "description": "RNA Material type" }, { "name": "RNA tube", "description": "RNA tube ID (the same as Extact name)" }, { "name": "Sample name", "description": "Sample name" }, { "name": "RNA extraction", "description": "RNA extraction" }, { "name": "RNA ID", "description": "Internal RNA ID" }, { "name": "Comment on RNA", "description": "Comment on RNA" }, { "name": "ratio_260\/230", "description": "Ratio (260nm\/230nm) of the sample" }, { "name": "ratio_260\/280", "description": "Ratio (260nm\/280nm) of the sample" }, { "name": "Concentration", "description": "RNA concentration" }, { "name": "RNA Integrity number", "description": "RNA Integrity number" }, { "name": "lsid", "description": "Sample group ID" }, { "name": "Library protocol", "description": "Library protocol" }, { "name": "Library ID", "description": "Library ID" }, { "name": "Sequence protocol", "description": "Sequence protocol" }, { "name": "Machine name", "description": "Machine name" }, { "name": "Run name", "description": "Run name" }, { "name": "Flowcell channel", "description": "Flowcell channel" }, { "name": "Alignment protocol", "description": "Alignment protocol" }, { "name": "BAM file", "description": "Read mapping results (BAM format)" }, { "name": "BAI file", "description": "Index of BAM file" }, { "name": "CAGE TSS file", "description": "TSS identified by CAGE analysis (BED format)" }, { "name": "Ribosomal DNA sequence file", "description": "rDNA sequence file (FASTA format)" }, { "name": "Barcode", "description": "Barcode sequence for RNA sample identification" } ] }, { "path": "en\/fantom5\/data-2.html", "name": "CAGE peaks", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-002.V003", "description": "Data about CAGE peak regions and RNA transcriptional initiation activities measured by CAGE", "files": [ { "file_name": "CAGE_peaks", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/CAGE_peaks\/", "file_size": "4.1 GB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE\r\nDPI (Decomposition-based peak identification)", "data_number": "35 files", "details": [] }, { "path": "en\/fantom5\/data-3.html", "name": "Pathway enrichment and co-expression cluster analysis", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-003.V003", "description": "Pathway enrichment and co-expression cluster analysis", "files": [ { "file_name": "Co-expression_clusters", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/phase1.3\/extra\/Co-expression_clusters\/", "file_size": "86 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "Co-expression cluster analysis\r\nGostat enrichment analysis\r\nPathway enrichment analysis", "data_number": "14 files", "details": [] }, { "path": "en\/fantom5\/data-4.html", "name": "Enhancers", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-004.V003", "description": "Human and mouse enhancers identified by measuring RNA transcripts amount with CAGE in phase1.0 and phase2.0", "files": [ { "file_name": "Enhancers", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/Enhancers\/", "file_size": "160 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE", "data_number": "9 files", "details": [] }, { "path": "en\/fantom5\/data-5.html", "name": "Results of de-novo and Motif activity analyses", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-005.V003", "description": "Analysis results of TFBS motif near TSS\r\n\r\nde-novo motif analysis with HOMER etc.\r\nSignificance of the correlation between transcriptional activations mesured by CAGE and de-novo motif\/known TFBS motif (registered in JASPAR)", "files": [ { "file_name": "Motifs", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/phase1.3\/extra\/Motifs\/", "file_size": "6.2 GB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "JASPER motif search\r\nHOMER motif analysis", "data_number": "400 files", "details": [] }, { "path": "en\/fantom5\/data-6.html", "name": "Sample ontology, GOstat and ontology term enrichment", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-006.V003", "description": "The ontology to express samples in phase2.0\r\nIt is based on Cell Ontology, Disease Ontology and Pan-vertebrate Uberon Ontology. The file format is OBO.", "files": [ { "file_name": "Ontology", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/Ontology\/", "file_size": "1.8 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "2 files", "details": [] }, { "path": "en\/fantom5\/data-7.html", "name": "CAGE peaks identified as true TSS by TSS classifier", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-007.V003", "description": "Evaluation of CAGE peaks\r\nIt shows that the sequence close to CAGE peak has \"TSS-like\" or not. \"TSS_human.bed.gz\" and \"TSS_mouse.bed.gz\" contain identified TSS.", "files": [ { "file_name": "TSS_classifier", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/phase1.3\/extra\/TSS_classifier\/", "file_size": "32 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "TSS Classifier（http:\/\/sourceforge.net\/p\/tometools\/wiki\/TssClassifier\/）", "data_number": "4 files", "details": [] }, { "path": "en\/fantom5\/data-8.html", "name": "(reprocessed)HeliscopeCAGE sequencing, Delve mapping and CAGE TSS aggregation", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-008.V003", "description": "Time course and snapshot data by HeliScopeCAGE\r\nHuman and mouse reads are re-mapped to new reference genome sequences (hg38\/mm10).\r\n\"basic\" directory contains the following:\r\n \r\n00_.assay_sdrf.txt:Experimental information for each sample (tabbed text)*.bam:Binary read mapping results (BAM format)*.bam.bai:Indexes of BAM files*.ctss.bed.gz:TSS (CTSS) identified by CAGE tag analysis (BED format)*.rdna.fa.gz:rDNA sequences (FASTA format)", "files": [ { "file_name": "fantom5_rp_exp_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/LATEST\/fantom5_rp_exp_details.zip", "file_size": "237 KB" }, { "file_name": "(reprocessed)basic (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/basic\/", "file_size": "1.4 TB" }, { "file_name": "(reprocessed)basic (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/basic\/", "file_size": "889 GB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/fantom5_rp_exp_details#en", "data_acquisition": "HeliScopeCAGE (http:\/\/fantom.gsc.riken.jp\/protocols\/heliscope.html)\r\nDelve (Alignment software for short read) (http:\/\/fantom.gsc.riken.jp\/jp\/software\/)", "analysis": "", "data_number": "", "details": [ { "name": "Extract name", "description": "Internal ID" }, { "name": "FF ontology", "description": "Ontology ID in FANTOM" }, { "name": "Description", "description": "Description" }, { "name": "Catalog ID", "description": "RNA catalog ID" }, { "name": "Category", "description": "Category" }, { "name": "Species", "description": "Species" }, { "name": "Sex", "description": "Sex" }, { "name": "Age", "description": "Age" }, { "name": "Developmental stage", "description": "Developmental stage" }, { "name": "Tissue", "description": "Tissue" }, { "name": "Cell lot", "description": "Cell lot" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Catalogue ID", "description": "Cell catalogue ID" }, { "name": "Collaboration", "description": "Collaboration" }, { "name": "Provider", "description": "Cell provider" }, { "name": "Extraction protocol", "description": "RNA extraction protocol" }, { "name": "Material type", "description": "RNA Material type" }, { "name": "RNA tube", "description": "RNA tube ID (the same as Extact name)" }, { "name": "Sample name", "description": "Sample name" }, { "name": "RNA extraction", "description": "RNA extraction" }, { "name": "RNA ID", "description": "Internal RNA ID" }, { "name": "Comment on RNA", "description": "Comment on RNA" }, { "name": "ratio_260\/230", "description": "Ratio (260nm\/230nm) of the sample" }, { "name": "ratio_260\/280", "description": "Ratio (260nm\/280nm) of the sample" }, { "name": "Concentration", "description": "RNA concentration" }, { "name": "lsid", "description": "RNA Integrity number" }, { "name": "Library protocol", "description": "Library protocol" }, { "name": "Library ID", "description": "Library ID" }, { "name": "Sequence protocol", "description": "Sequence protocol" }, { "name": "Machine name", "description": "Machine name" }, { "name": "Run name", "description": "Run name" }, { "name": "Flowcell channel", "description": "Flowcell channel" }, { "name": "Alignment protocol", "description": "Alignment protocol" }, { "name": "BAM file", "description": "Read mapping results (BAM format)" }, { "name": "BAI file", "description": "Index of BAM file" }, { "name": "CAGE TSS file", "description": "TSS identified by CAGE analysis (BED format)" }, { "name": "Ribosomal DNA sequence file", "description": "rDNA sequence file (FASTA format)" } ] }, { "path": "en\/fantom5\/data-9.html", "name": "(reprocessed)CAGE peaks", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-009.V003", "description": "Data about CAGE peak regions and RNA transcriptional initiation activities measured by CAGE. Human and mouse reads in phase2.0 are re-mapped to new reference genome sequences (hg38\/mm10).", "files": [ { "file_name": "(reprocessed)CAGE_peaks (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/CAGE_peaks\/", "file_size": "11 MB" }, { "file_name": "(reprocessed)CAGE_peaks (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/extra\/CAGE_peaks\/", "file_size": "8.1 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE\r\nDPI (Decomposition-based peak identification)", "data_number": "Human: 8 files \/ Mouse: 8 files", "details": [] }, { "path": "en\/fantom5\/data-10.html", "name": "CAGE_peaks_annotation", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-010.V003", "description": "Annotation of human and mouse CAGE peaks and RNA transcriptional initiation activities by CAGE", "files": [ { "file_name": "CAGE_peaks_annotation", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/CAGE_peaks_annotation", "file_size": "195 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE", "data_number": "9 files", "details": [] }, { "path": "en\/fantom5\/data-11.html", "name": "(reprocessed)CAGE_peaks_annotation", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-011.V003", "description": "Annotation of human and mouse CAGE peaks and RNA transcriptional initiation activities by CAGE\r\nHuman and mouse reads in phase2.0 are re-mapped for new reference sequences (hg38\/mm10).", "files": [ { "file_name": "(reprocessed)CAGE_peaks_annotation (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/CAGE_peaks_annotation\/", "file_size": "19 MB" }, { "file_name": "(reprocessed)CAGE_peaks_annotation (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/extra\/CAGE_peaks_annotation\/", "file_size": "14 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE", "data_number": "Human: 4 files \/ Mouse: 4 files", "details": [] }, { "path": "en\/fantom5\/data-12.html", "name": "(reprocessed)CAGE_peaks_expression", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-011.V003", "description": "Expression of human and mouse RNA transcriptional initiation activities by CAGE\r\nHuman and mouse reads in phase2.0 are re-mapped for new reference sequences (hg38\/mm10).", "files": [ { "file_name": "(reprocessed)CAGE_peaks_annotation (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/CAGE_peaks_annotation\/", "file_size": "16 MB" }, { "file_name": "(reprocessed)CAGE_peaks_annotation (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/extra\/CAGE_peaks_annotation\/", "file_size": "13 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE", "data_number": "Human: 7 files \/ Mouse: 7 files", "details": [] }, { "path": "en\/fantom5\/data-13.html", "name": "(reprocessed)pooled_ctss", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-013.V003", "description": "Mapping results of the all CAGE tags used from phase1.0 to phase2.0\r\nHuman and mouse reads in phase2.0 are re-mapped for new reference sequences (hg38\/mm10).", "files": [ { "file_name": "(reprocessed)pooled_ctss (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/pooled_ctss\/", "file_size": "6.5 GB" }, { "file_name": "(reprocessed)pooled_ctss (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/extra\/pooled_ctss\/", "file_size": "4.5 GB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "Human: 2 files \/ Mouse: 2 files", "details": [] }, { "path": "en\/fantom5\/data-14.html", "name": "DRA_accession_tables", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-014.V003", "description": "Accession number list of FANTOM5 sample data registered in DRA (http:\/\/trace.ddbj.nig.ac.jp\/dra\/index.html).", "files": [ { "file_name": "fantom5_dra_accession_tables.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/LATEST\/fantom5_dra_accession_tables.zip", "file_size": "64 KB" }, { "file_name": "DRA_accession_tables", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/DRA_accession_tables", "file_size": "251KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/db\/fantom5_dra_accession_tables#en", "data_acquisition": "DRA", "analysis": "", "data_number": "3,075 entries", "details": [ { "name": "Library ID", "description": "DNA sequence library ID" }, { "name": "FF ontology", "description": "Ontology ID defined in FANTOM" }, { "name": "DRA sample accession number", "description": "DRA sample accession number" }, { "name": "DRA experiment accession number", "description": "DRA experiment accession number" }, { "name": "DRA run accession number", "description": "DRA run accession number" }, { "name": "DRA analysis accession number (BAM)", "description": "DRA analysis accession number (BAM)" }, { "name": "DRA analysis accession number (BED)", "description": "DRA analysis accession number (BED)" }, { "name": "Experiment method", "description": "Experiment method" } ] }, { "path": "en\/fantom5\/data-15.html", "name": "Gene_level_expression", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-015.V003", "description": "Those tables shows the number of CAGE tags mapped on the same gene in each sample (human\/mouse). The \"counts\" tables mean simple tabulation of tags and the \"tpm\" tables mean \"TPM\" (Transcripts Per Million) with RLE (Relative Log Expression).", "files": [ { "file_name": "gene_level_expression", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/gene_level_expression", "file_size": "415MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "Simple tabulation, RLE (Relative Log Expression)", "data_number": "4 files", "details": [] }, { "path": "en\/fantom5\/data-16.html", "name": "Summary_CAGEScan", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-016.V003", "description": "The summary of CAGEscan experiments assembled in every DNA sequence library", "files": [ { "file_name": "fantom5_summary_cagescan.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/LATEST\/fantom5_summary_cagescan.zip", "file_size": "4.64 KB" }, { "file_name": "Summary_CAGEScan", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/LATEST\/extra\/Summary_CAGEScan", "file_size": "62KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/fantom5_summary_cagescan#en", "data_acquisition": "CAGEscan (http:\/\/fantom.gsc.riken.jp\/protocols\/nanocage.html)", "analysis": "", "data_number": "61 entries", "details": [ { "name": "Library ID", "description": "DNA sequence library ID" }, { "name": "Raw", "description": "Measured reads" }, { "name": "Removed by extraction", "description": "Removed reads by extraction" }, { "name": "Extracted", "description": "Extracted reads by analysis" }, { "name": "Removed by artifacts", "description": "Removed artifatcts" }, { "name": "Filtered for artifact", "description": "Reads filterd for artifacts" }, { "name": "Removed by rRNA", "description": "Removed reads as rRNA" }, { "name": "Filtered for rRNA", "description": "Reads filterd for rRNAs" }, { "name": "Non alignment", "description": "Reads not mapped on genome" }, { "name": "Genome mapped", "description": "Reads mapped on genome" }, { "name": "Duplicated", "description": "Duplicated reads" }, { "name": "Uniquely mapped", "description": "Unique reads" }, { "name": "Inproperly mapped pairs", "description": "Read pairs inproperly mapped on genome" }, { "name": "Properly mapped pairs", "description": "Read pairs properly mapped on genome" }, { "name": "Total pairs", "description": "Total pairs" }, { "name": "Exon", "description": "Pairs on exon" }, { "name": "Intergenic", "description": "Pairs on intergenic" }, { "name": "Promoter", "description": "Pairs on promoter" } ] }, { "path": "en\/fantom5\/data-17.html", "name": "(reprocessed) Enhancers", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-017.V003", "description": "Identified enhancers of human and mouse by RNA transcription mesurement with CAGE. They are reprocessed with new reference genome sequences (hg38\/mm10).", "files": [ { "file_name": "(reprocessed) enhancer (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/enhancer", "file_size": "101MB" }, { "file_name": "(reprocessed) enhancer (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/mm10_latest\/extra\/enhancer", "file_size": "7.3MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "CAGE", "data_number": "Human: 5files \/ Mouse: 4files", "details": [] }, { "path": "en\/fantom5\/data-18.html", "name": "(reprocessed)DPI_clustering", "database_name": "FANTOM5", "doi": "10.18908\/lsdba.nbdc01389-018.V003", "description": "This is the peak identification of human and mouse reprocessed mapping data with DPI (Decomposition-based peak identification) method. (BED format)\r\n*.tc.bed.gz:CAGE tag clusters with original definition*.tc.decompose_smoothing_merged.bed.gz:All peaks with DPI*.tc.decompose_smoothing_merged.ctssMaxCounts3.bed.gz:All extracted peaks*.tc.decompose_smoothing_merged.ctssMaxCounts11_ctssMaxTpm1.bed.gz:Probable extracted peaks", "files": [ { "file_name": "(reprocessed)DPI_clustering (Homo sapiens)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/DPI_clustering", "file_size": "150MB" }, { "file_name": "(reprocessed)DPI_clustering (Mus musculus)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/fantom5\/datafiles\/reprocessed\/hg38_latest\/extra\/DPI_clustering", "file_size": "124MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "Human: 4 files \/ Mouse: 4 files", "details": [] }, { "path": "en\/first-authors\/data-1.html", "name": "Body text collection", "database_name": "First Author's", "doi": "", "description": "It is the collection of this reviews' body text. It is provided in doc format and txt format.\r\nIn simple search, you can view the body text and link doc\/txt files and figures.", "files": [ { "file_name": "fa_collection.zip (file list)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/first_authors\/LATEST\/fa_collection.zip", "file_size": "23 MB" }, { "file_name": "format_doc.zip (doc format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/first_authors\/LATEST\/format_doc.zip", "file_size": "22 MB" }, { "file_name": "format_txt.zip (txt format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/first_authors\/LATEST\/format_txt.zip", "file_size": "7.7 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/fa_collection#en", "data_acquisition": "", "analysis": "", "data_number": "1265", "details": [ { "name": "FA ID", "description": "Review ID" }, { "name": "URL", "description": "Review URL" }, { "name": "Title", "description": "Review Title" }, { "name": "Date", "description": "Publication date" }, { "name": "Author(s)", "description": "Review author(s)" }, { "name": "DOI", "description": "Review DOI" }, { "name": "Original article title", "description": "Original article title" }, { "name": "Original article author(s)", "description": "Original article author(s)" }, { "name": "Original journal", "description": "Original journal" }, { "name": "Original article number", "description": "Original article number" }, { "name": "Content", "description": "Review content (HTML)" }, { "name": "Tags", "description": "Tags to the review" }, { "name": "Fig1", "description": "Fig1 caption (Link to the Fig1 file in simple search)" }, { "name": "Fig2", "description": "Fig2 caption (Link to the Fig2 file in simple search)" }, { "name": "Fig3", "description": "Fig3 caption (Link to the Fig3 file in simple search)" }, { "name": "Fig4", "description": "Fig4 caption (Link to the Fig4 file in simple search)" }, { "name": "doc file", "description": "doc file name (Link to the file in simple search)" }, { "name": "txt file", "description": "txt file name (Link to the file in simple search)" } ] }, { "path": "en\/first-authors\/data-2.html", "name": "Figure collection", "database_name": "First Author's", "doi": "", "description": "It is the collection of figures in reviews.\r\nFigure itself is provided in jpeg format. Thumbnails are provided in png format.", "files": [ { "file_name": "format_jpg.zip (jpg format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/first_authors\/LATEST\/format_jpg.zip", "file_size": "459 MB" }, { "file_name": "format_png.zip (png format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/first_authors\/LATEST\/format_png.zip", "file_size": "113 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/frnadb\/data-1.html", "name": "fRNAdb Summary", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-001", "description": "Functional RNA Database is a human curated catalog of functional RNAs acquired from journal papers. Each RNA is associated to a base sequence, genomic locus, putative secondary structure, citation, etc.", "files": [ { "file_name": "frnadb_summary.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/frnadb_summary.zip", "file_size": "46.5 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/frnadb_summary#en", "data_acquisition": "Main RNA information was acquired from journal papers and existing RNA databases. Computational prediction results were used for genomic loci and secondary structures. Citation information was extracted from PubMed database by searching titles\/abstracts including corresponding family names.", "analysis": "", "data_number": "510,055 entries", "details": [ { "name": "ID", "description": "Entry ID" }, { "name": "Accession", "description": "Accession" }, { "name": "Description", "description": "Description" }, { "name": "SO name", "description": "Sequence Ontology" }, { "name": "Organism", "description": "Organism" }, { "name": "Xref", "description": "Cross Reference" }, { "name": "Length", "description": "Sequence Length" }, { "name": "Sequence", "description": "Sequence" }, { "name": "Second Structure Thumbnail", "description": "Thumbnail of RNA secondary structure image" }, { "name": "Second Structure (PNG)", "description": "RNA secondary structure image (PNG)" }, { "name": "Second Structure (PDF)", "description": "RNA secondary structure image (PDF)" } ] }, { "path": "en\/frnadb\/data-2.html", "name": "Database Dump", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-002", "description": "Dump data from database in the original site:\r\n- fRNAdb.pdf: description of database schema\r\n- fRNAdb_schema.sql: database schema\r\n- fRNAdb_table.7z: dump data (original)\r\n- fRNAdbtsv.zip: dump data (tab separeted text)", "files": [ { "file_name": "Database_Dump", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/Database_Dump", "file_size": "673 MB" } ], "togodb_url": "", "data_acquisition": "Main RNA information was acquired from journal papers and existing RNA databases. Computational prediction results were used for genomic loci and secondary structures. Citation information was extracted from PubMed database by searching titles\/abstracts including corresponding family names.", "analysis": "", "data_number": "4 files", "details": [] }, { "path": "en\/frnadb\/data-3.html", "name": "Sequence Data", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-003", "description": "Functional RNA sequence files (FASTA)\r\n- sequence.zip: Aggregation of the following files\r\n- mirna.zip: miRNA sequences\r\n- ncrna.zip: ncRNA sequences\r\n- shortread.zip: Sequences from short read sequencer\r\n- Other: Sequences of 10 species", "files": [ { "file_name": "Sequence Data", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/Sequence_Data", "file_size": "102 MB" } ], "togodb_url": "", "data_acquisition": "Acquired from journal papers and existing RNA databases.", "analysis": "", "data_number": "14 files", "details": [] }, { "path": "en\/frnadb\/data-4.html", "name": "Mapping Information", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-004", "description": "Mapping results on genomes of 4 species\r\n- dm3_*.zip: Drosophila_melanogaster\r\n- hg18_*.zip: Homo_sapiens\r\n- mm9_*.zip: Mus_musculus\r\n- rn3_*.zip: Rattus_norvegicus", "files": [ { "file_name": "Mapping_Information", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/Mapping_Information", "file_size": "120 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "12 files", "details": [] }, { "path": "en\/frnadb\/data-5.html", "name": "RNA secondary structure image", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-005", "description": "RNA secondary structure images\r\n- png.zip: RNA secondary structure images (PNG)\r\n- pdf.zip: RNA secondary structure images (PDF)\r\n- thumbnail.zip: Thumbnails of RNA secondary structure images", "files": [ { "file_name": "RNA_secondary_structure_image", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/RNA_secondary_structure_image", "file_size": "9.6 GB" } ], "togodb_url": "", "data_acquisition": "From \"Sequence Data\"", "analysis": "Predicted by using CentroidFold (only when possible)", "data_number": "3 files (Each zip file contains 338,167 image files.)", "details": [] }, { "path": "en\/frnadb\/data-6.html", "name": "Supplementary Data", "database_name": "fRNAdb", "doi": "10.18908\/lsdba.nbdc00452-006", "description": "- xref.zip: Entry ID, Accession, Mapping Position in genome (only Homo sapiens)\r\n- count_taxon.tsv: list of all species and the number of entries in fRNAdb", "files": [ { "file_name": "Supplementary_Data", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/frnadb\/LATEST\/Supplementary_Data", "file_size": "3.8 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "2 files", "details": [] }, { "path": "en\/gclust\/data-1.html", "name": "Amino acid sequences of predicted proteins and their annotation for 95 organism species.", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-001", "description": "Amino acid sequences of predicted proteins and their annotation for 95 organism species. The data are given in a CSV format text file.", "files": [ { "file_name": "gclust_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/gclust_seq.zip", "file_size": "152MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/gclust_seq#en", "data_acquisition": "Protein sequences of a total of 95 organism species were obtained from NCBI, JGI and CGP.", "analysis": "", "data_number": "698,557 entries", "details": [ { "name": "Sequence ID", "description": "ID of a sequence" }, { "name": "Cluster ID", "description": "ID of cluster. gclust_cluster is referenced." }, { "name": "Annotation in original database", "description": "Annotation at the original website" }, { "name": "Species", "description": "Species name" }, { "name": "Length", "description": "Amino acid sequence length" }, { "name": "Sequence", "description": "Amino acid sequence" } ] }, { "path": "en\/gclust\/data-2.html", "name": "Cluster based on sequence comparison of homologous proteins of 95 organism species", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-002", "description": "Clustering was performed by the method in which the round-robin BLAST search of the above amino acid sequence data is performed, the E-value and the overlap score (the All-against-all BLASTP search of the above amino acid sequence data, and heuristic estimation of a similarity threshold for homologs of each protein by entropy-optimized organism count method (Bioinformatics 2009 Mar 1;25(5):599-605.). The data are given in a CSV format text file.", "files": [ { "file_name": "gclust_cluster.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/gclust_cluster.zip", "file_size": "8.72MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/gclust_cluster#en", "data_acquisition": "Sequence data stated in \"Amino acid sequences of predicted proteins and their annotation for 95 organism species\".", "analysis": "All-against-all BLASTP search of the above amino acid sequence data, and heuristic estimation of a similarity threshold for homologs of each protein by entropy-optimized organism count method (Bioinformatics 2009 Mar 1;25(5):599-605.).", "data_number": "206,764 entries", "details": [ { "name": "Cluster ID", "description": "ID of cluster" }, { "name": "Representative sequence ID", "description": "ID of a sequence that represents the cluster. gclust_seq is referenced." }, { "name": "Link to cluster sequences", "description": "Link to the list of sequences belonging to the cluster (empty space)" }, { "name": "Link to related sequences", "description": "Link to the list of sequences that are similar to the cluster, but not clustered" }, { "name": "Sequence length", "description": "Amino acid sequence length" }, { "name": "Representative annotation", "description": "Representative annotation of the cluster" }, { "name": "Number of Sequences", "description": "Number of sequences contained in the cluster" }, { "name": "Homologs", "description": "Number of sequences contained in the cluster" }, { "name": "Clustering threshold", "description": "The threshold of E-value used for clustering" }, { "name": "Plants (7species) (%)", "description": "The appearance rate of this cluster in the plant and algal group (including 7 species)" }, { "name": "Other bikonts (9 species) (%)", "description": "The appearance rate of this cluster in other Bikonta (Chromalveolata, Excavata) group (including 9 species)" }, { "name": "Cyano (25species) (%)", "description": "The appearance rate of this cluster in the cyanobacteria group (including 25 species)" }, { "name": "Photo Bact (15species) (%)", "description": "The appearance rate of this cluster in the photosynthetic bacteria group (including 15 species)" }, { "name": "Other Bact (31 species) (%)", "description": "The appearance rate of this cluster in the non-photosynthetic bacteria group (including 31 species)" }, { "name": "Opisthokonts (8species) (%)", "description": "The appearance rate of this cluster in the opisthokont group (including 8 species)" }, { "name": "Number of Sequences for each species", "description": "The number of sequences by organism species contained in the cluster" }, { "name": "Species not appearing in this cluster", "description": "Organism species not contained in the cluster" } ] }, { "path": "en\/gclust\/data-3.html", "name": "Proteins in similarity relationship with the cluster", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-003", "description": "Protein sequences that are similar to any clustered sequence of 95 organisms species, but not clustered. The data are given in a CSV format text file.", "files": [ { "file_name": "gclust_related.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/gclust_related.zip", "file_size": "69MB" } ], "togodb_url": "", "data_acquisition": "Sequence data stated in \"Amino acid sequences of predicted proteins and their annotation for 95 organism species\".", "analysis": "", "data_number": "14,444,047 entries", "details": [ { "name": "Cluster ID", "description": "ID of cluster" }, { "name": "Sequence ID", "description": "ID of a sequence" } ] }, { "path": "en\/gclust\/data-4.html", "name": "Amino acid sequences used for clusterintg (Multi FASTA format)", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-004", "description": "Amino acid sequences of predicted proteins and their annotation for 95 organism species. FASTA format file.", "files": [ { "file_name": "all95.fa.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/all95.fa.zip", "file_size": "161MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/gclust\/data-5.html", "name": "Sequence ID and annotation information", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-005", "description": "A tab-delimited text file specifying the ID, length and annotation information of the amino acid sequences of the predicted proteins for 95 organism species.", "files": [ { "file_name": "all95.p.table.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/all95.p.table.zip", "file_size": "7.28MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Field 1", "description": "ID of amino acid sequence (Sequence ID)" }, { "name": "Field 2", "description": "Length of amino acid sequence" }, { "name": "Field 3", "description": "Annotation of amino acid sequence" } ] }, { "path": "en\/gclust\/data-6.html", "name": "Prefix list for each organism", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-006", "description": "List of prefixes for organisms used in Gclust. Each prefix is applied to the top of the sequence ID according to each organism. The first line specifies the number of organism species (95). From the second line, the prefix of each organism is listed on each line, and \"\/\/END\" is entered on the last line.", "files": [ { "file_name": "prefix_all95", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/prefix_all95", "file_size": "1KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "ATH", "description": "Arabidopsis thaliana" }, { "name": "CME", "description": "Cyanidioschyzon merolae" }, { "name": "CRE", "description": "Chlamydomonas reinhardtii" }, { "name": "OSA", "description": "Oryza sativa" }, { "name": "OTAU", "description": "Ostreococcus tauri" }, { "name": "PPT", "description": "Physcomitrella patens" }, { "name": "PoTR", "description": "Populus tricocarpa" }, { "name": "DPTM", "description": "Paramecium tetraurelia" }, { "name": "GTH", "description": "Guillardia theta" }, { "name": "NGR", "description": "Naegleria gruberi" }, { "name": "PFA", "description": "Plasmodium falciparum" }, { "name": "PHRA", "description": "Phytophthora ramorum" }, { "name": "PHSO", "description": "Phytophthora sojae" }, { "name": "PTR", "description": "Phaeodactylum tricornutum" }, { "name": "TET", "description": "Tetrahymena thermophila SB210" }, { "name": "TPS", "description": "Thalassiosira pseudonana" }, { "name": "Ana", "description": "Anabaena sp. PCC 7120" }, { "name": "Ava", "description": "Anabaena variabilis ATCC 29413" }, { "name": "Glv", "description": "Gloeobacter violaceus" }, { "name": "Npun", "description": "Nostoc punctiforme sp. PCC73102" }, { "name": "Pm1", "description": "Prochlorococcus marinus MED4" }, { "name": "Pm2", "description": "Prochlorococcus marinus MIT9313" }, { "name": "Pm3", "description": "Prochlorococcus marinus SS120" }, { "name": "Pm4", "description": "Prochlorococcus marinus MIT9312" }, { "name": "Pm5", "description": "Prochlorococcus marinus NATL2A" }, { "name": "Pm6", "description": "Prochlorococcus marinus MIT9301" }, { "name": "Pm7", "description": "Prochlorococcus marinus MIT9303" }, { "name": "Pm8", "description": "Prochlorococcus marinus MIT9315" }, { "name": "Pm9", "description": "Prochlorococcus marinus NATL1A" }, { "name": "PmA", "description": "Prochlorococcus marinus AS9601" }, { "name": "S63", "description": "Synechococcus sp. PCC 6301" }, { "name": "S79", "description": "Synechococcus sp. PCC 7942" }, { "name": "S81", "description": "Synechococcus sp. WH8102" }, { "name": "S93", "description": "Synechococcus sp. CC9311" }, { "name": "S96", "description": "Synechococcus sp. CC9605" }, { "name": "Syn", "description": "Synechocystis sp. PCC 6803" }, { "name": "Tel", "description": "Thermosynechococcus elongatus" }, { "name": "Ter", "description": "Trichodesmium erythraeum 405 1" }, { "name": "YelA", "description": "Cyanobacterium Yellowstone A-prime" }, { "name": "YelB", "description": "Cyanobacterium Yellowstone B-prime" }, { "name": "Caur", "description": "Chloroflexus aurantiacus" }, { "name": "Cch", "description": "Chlorobium chlorochromatii CaD3" }, { "name": "Clim", "description": "Chlorobium limicola DSM 245" }, { "name": "Cph", "description": "Chlorobium phaeobacteroides DSM 266" }, { "name": "Ctep", "description": "Clorobium tepidum" }, { "name": "Pvi", "description": "Prostheocochloris vibrioformis DSM 265" }, { "name": "Rde", "description": "Roseobacter denitrificans Och 114" }, { "name": "Rpa1", "description": "Rhodopseudomonas plustris BisA53" }, { "name": "Rpa2", "description": "Rhodopseudomonas plustris BisB4" }, { "name": "Rpa3", "description": "Rhodopseudomonas plustris BisB18" }, { "name": "Rpa4", "description": "Rhodopseudomonas plustris HaA2" }, { "name": "Rpal", "description": "Rhodopseudomonas plustris" }, { "name": "Rrub", "description": "Rhodospirillum rubrum ATCC 11170" }, { "name": "Rsh", "description": "Rhodobacter sphaeroides ATCC 17029" }, { "name": "Rsp", "description": "Rhodobacter sphaeroides 2.4.1" }, { "name": "Afu", "description": "Archaeoglobus fulgidus DSM 4304" }, { "name": "Ape", "description": "Aeropyrum pernix K1" }, { "name": "Atu", "description": "Agrobacterium tumefaciens str. C58" }, { "name": "Bja", "description": "Bradyrhizobium japonicum USDA 110" }, { "name": "Bma", "description": "Burkholderia mallei ATCC 23344" }, { "name": "Bms", "description": "Brucella suis 1330" }, { "name": "Bpe", "description": "Bordetella pertussis Tohama I" }, { "name": "Bsu", "description": "Bacillus subtilis Marburg 168" }, { "name": "Ccr", "description": "Caulobacter crescentus CB15" }, { "name": "Cvi", "description": "Chromobacterium violaceum ATCC 12472" }, { "name": "Eba", "description": "Azoarcus sp EbN1" }, { "name": "Eco", "description": "Escherichia coli K-12" }, { "name": "Fal", "description": "Frankia alni ACN14a" }, { "name": "Fra", "description": "Frankia sp. CcI3" }, { "name": "Gox", "description": "Gluconobacter_oxydans_621H" }, { "name": "Hal", "description": "Halobacterium sp. NRC-1" }, { "name": "Mac", "description": "Methanosarcina acetivorans str. C2A" }, { "name": "Mes", "description": "Mesorhizobium sp. BNC1" }, { "name": "Mlo", "description": "Mesorhizobium loti MAFF303099" }, { "name": "Mtu", "description": "Mycobacterium tuberculosis H37Rv" }, { "name": "Neq", "description": "Nanoarchaeum equitans Kin4-M" }, { "name": "Pho", "description": "Pyrococcus horikoshii OT3" }, { "name": "Pst", "description": "Pseudomonas syringae pv. tomato str. DC3000" }, { "name": "Rhe", "description": "Rhizobium_etli_CFN_42" }, { "name": "Rle", "description": "Rhizobium leguminosarum" }, { "name": "Rso", "description": "Ralstonia solanacearum GMI1000" }, { "name": "Sco", "description": "Streptomyces coelicolor A3(2)" }, { "name": "Sep", "description": "Staphylococcus epidermidis ATCC 12228" }, { "name": "Sme", "description": "Sinorhizobium meliloti 1021" }, { "name": "Sto", "description": "Sulfolobus tokodaii str. 7" }, { "name": "Vvy", "description": "Vibrio vulnificus YJ016" }, { "name": "CEL", "description": "Caenorhabditis elegans" }, { "name": "DCGR", "description": "Candida glabrata CBS138" }, { "name": "DKLA", "description": "Kluyveromyces lactis NRRL Y-1140" }, { "name": "DME", "description": "Drosophila melanogaster" }, { "name": "HSA", "description": "Homo sapiens" }, { "name": "SPO", "description": "Schyzosaccharomyces pombe" }, { "name": "S99", "description": "Synechococcus sp. CC9902" }, { "name": "NCR", "description": "Neurospora crassa 74-OR23-1A" }, { "name": "SCE", "description": "Saccharomyces cerevisiae" } ] }, { "path": "en\/gclust\/data-7.html", "name": "Designation of organism group", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-007", "description": "The definition for grouping 95 species of organism is specified. The first line specifies the number of organism species, and \"\/\/END\" is entered on the final line. The line starting with \"#\" is a line for comment. Data are provided in a tab-delimited text file format.", "files": [ { "file_name": "grp_def1", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/grp_def1", "file_size": "1KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Field 1", "description": "Prefix of the sequence ID of organism" }, { "name": "Field 2", "description": "Group (Numbers from 1 to 6)" } ] }, { "path": "en\/gclust\/data-8.html", "name": "Parameters for Organism Grouping", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-008", "description": "The file designated with the threshold for the ratio of organism species showing homology in the organism species in each organism group when allocation to the organism group is made. For example, when the designated value is 0.5, the cluster is determined as belonging to the \"Plants\" group if the sequences of four or more organism species out of seven species in this organism group exist in the cluster.", "files": [ { "file_name": "pat_def1", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/pat_def1", "file_size": "1KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Field 1", "description": "Group number" }, { "name": "Field 2", "description": "Designated value for allocation to organism group" }, { "name": "Field 3", "description": "Group name" } ] }, { "path": "en\/gclust\/data-9.html", "name": "Clustering results", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-009", "description": "Results of running Gclust program. The data include such information as the requirements for running the program, the cluster ID, the threshold used for cluster grouping, the ID of the sequence belonging to the cluster and the sequence ID of the related group.", "files": [ { "file_name": "all95m8.hom.1.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/all95m8.hom.1.zip", "file_size": "140MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/gclust\/data-10.html", "name": "Table of Cluster and Organism Species Number", "database_name": "Gclust Server", "doi": "10.18908\/lsdba.nbdc00464-010", "description": "Cluster, representative sequence ID of cluster, its length, the number of sequences contained in the cluster, organism species, the number of sequences belonging to the cluster for each of 95 organism species, compiled into a tab-delimited text file format table.", "files": [ { "file_name": "all95.tbl.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/gclust\/LATEST\/original\/all95.tbl.zip", "file_size": "4.53MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Number", "description": "Cluster ID" }, { "name": "ID", "description": "Sequence ID" }, { "name": "Length", "description": "Sequence length" }, { "name": "seqs", "description": "Number of sequences belonging to cluster" }, { "name": "homologs", "description": "Number of sequences belonging to cluster" }, { "name": "ATH", "description": "Number of sequences belonging to cluster in the Arabidopsis thaliana sequence" }, { "name": "OSA", "description": "Number of sequences belonging to cluster in the Oryza sativa sequence" }, { "name": "PoTR", "description": "Number of sequences belonging to cluster in the Populus tricocarpa sequence" }, { "name": "PPT", "description": "Number of sequences belonging to cluster in the Physcomitrella patens sequence" }, { "name": "CRE", "description": "Number of sequences belonging to cluster in the Chlamydomonas reinhardtii sequence" }, { "name": "OTAU", "description": "Number of sequences belonging to cluster in the Ostreococcus tauri sequence" }, { "name": "CME", "description": "Number of sequences belonging to cluster in the Cyanidioschyzon merolae sequence" }, { "name": "GTH", "description": "Number of sequences belonging to cluster in the Guillardia theta sequence" }, { "name": "PFA", "description": "Number of sequences belonging to cluster in the Plasmodium falciparum sequence" }, { "name": "PTR", "description": "Number of sequences belonging to cluster in the Phaeodactylum tricornutum sequence" }, { "name": "TPS", "description": "Number of sequences belonging to cluster in the Thalassiosira pseudonana sequence" }, { "name": "Ter", "description": "Number of sequences belonging to cluster in the Trichodesmium erythraeum 405 1 sequence" }, { "name": "Ana", "description": "Number of sequences belonging to cluster in the Anabaena sp. PCC 7120 sequence" }, { "name": "Ava", "description": "Number of sequences belonging to cluster in the Anabaena variabilis ATCC 29413 sequence" }, { "name": "Npun", "description": "Number of sequences belonging to cluster in the Nostoc punctiforme sp. PCC73102 sequence" }, { "name": "Syn", "description": "Number of sequences belonging to cluster in the Synechocystis sp. PCC 6803 sequence" }, { "name": "Glv", "description": "Number of sequences belonging to cluster in the Gloeobacter violaceus sequence" }, { "name": "Tel", "description": "Number of sequences belonging to cluster in the Thermosynechococcus elongatus sequence" }, { "name": "YelA", "description": "Number of sequences belonging to cluster in the Cyanobacterium Yellowstone A-prime sequence" }, { "name": "YelB", "description": "Number of sequences belonging to cluster in the Cyanobacterium Yellowstone B-prime sequence" }, { "name": "S63", "description": "Number of sequences belonging to cluster in the Synechococcus sp. PCC 6301 sequence" }, { "name": "S79", "description": "Number of sequences belonging to cluster in the Synechococcus sp. PCC 7942 sequence" }, { "name": "S81", "description": "Number of sequences belonging to cluster in the Synechococcus sp. WH8102 sequence" }, { "name": "S93", "description": "Number of sequences belonging to cluster in the Synechococcus sp. CC9311 sequence" }, { "name": "S96", "description": "Number of sequences belonging to cluster in the Synechococcus sp. CC9605 sequence" }, { "name": "S99", "description": "Number of sequences belonging to cluster in the Synechococcus sp. CC9902 sequence" }, { "name": "Pm1", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MED4 sequence" }, { "name": "Pm2", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MIT9313 sequence" }, { "name": "Pm3", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus SS120 sequence" }, { "name": "Pm4", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MIT9312 sequence" }, { "name": "Pm5", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus NATL2A sequence" }, { "name": "Pm6", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MIT9301 sequence" }, { "name": "Pm7", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MIT9303 sequence" }, { "name": "Pm8", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus MIT9315 sequence" }, { "name": "Pm9", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus NATL1A sequence" }, { "name": "PmA", "description": "Number of sequences belonging to cluster in the Prochlorococcus marinus AS9601 sequence" }, { "name": "Atu", "description": "Number of sequences belonging to cluster in the Agrobacterium tumefaciens str. C58 sequence" }, { "name": "Bja", "description": "Number of sequences belonging to cluster in the Bradyrhizobium japonicum USDA 110 sequence" }, { "name": "Bms", "description": "Number of sequences belonging to cluster in the Brucella suis 1330 sequence" }, { "name": "Ccr", "description": "Number of sequences belonging to cluster in the Caulobacter crescentus CB15 sequence" }, { "name": "Gox", "description": "Number of sequences belonging to cluster in the Gluconobacter_oxydans_621H sequence" }, { "name": "Mes", "description": "Number of sequences belonging to cluster in the Mesorhizobium sp. BNC1 sequence" }, { "name": "Mlo", "description": "Number of sequences belonging to cluster in the Mesorhizobium loti MAFF303099 sequence" }, { "name": "Rhe", "description": "Number of sequences belonging to cluster in the Rhizobium_etli_CFN_42 sequence" }, { "name": "Rle", "description": "Number of sequences belonging to cluster in the Rhizobium leguminosarum sequence" }, { "name": "Sme", "description": "Number of sequences belonging to cluster in the Sinorhizobium meliloti 1021 sequence" }, { "name": "Rpa1", "description": "Number of sequences belonging to cluster in the Rhodopseudomonas plustris BisA53 sequence" }, { "name": "Rpa2", "description": "Number of sequences belonging to cluster in the Rhodopseudomonas plustris BisB4 sequence" }, { "name": "Rpa3", "description": "Number of sequences belonging to cluster in the Rhodopseudomonas plustris BisB18 sequence" }, { "name": "Rpa4", "description": "Number of sequences belonging to cluster in the Rhodopseudomonas plustris HaA2 sequence" }, { "name": "Rpal", "description": "Number of sequences belonging to cluster in the Rhodopseudomonas plustris sequence" }, { "name": "Rrub", "description": "Number of sequences belonging to cluster in the Rhodospirillum rubrum ATCC 11170 sequence" }, { "name": "Rde", "description": "Number of sequences belonging to cluster in the Roseobacter denitrificans Och 114 sequence" }, { "name": "Rsh", "description": "Number of sequences belonging to cluster in the Rhodobacter sphaeroides ATCC 17029 sequence" }, { "name": "Rsp", "description": "Number of sequences belonging to cluster in the Rhodobacter sphaeroides 2.4.1 sequence" }, { "name": "Eco", "description": "Number of sequences belonging to cluster in the Escherichia coli K-12 sequence" }, { "name": "Pst", "description": "Number of sequences belonging to cluster in the Pseudomonas syringae pv. tomato str. DC3000 sequence" }, { "name": "Vvy", "description": "Number of sequences belonging to cluster in the Vibrio vulnificus YJ016 sequence" }, { "name": "Bsu", "description": "Number of sequences belonging to cluster in the Bacillus subtilis Marburg 168 sequence" }, { "name": "Sep", "description": "Number of sequences belonging to cluster in the Staphylococcus epidermidis ATCC 12228 sequence" }, { "name": "Fal", "description": "Number of sequences belonging to cluster in the Frankia alni ACN14a sequence" }, { "name": "Fra", "description": "Number of sequences belonging to cluster in the Frankia sp. CcI3 sequence" }, { "name": "Mtu", "description": "Number of sequences belonging to cluster in the Mycobacterium tuberculosis H37Rv sequence" }, { "name": "Sco", "description": "Number of sequences belonging to cluster in the Streptomyces coelicolor A3(2) sequence" }, { "name": "Rso", "description": "Number of sequences belonging to cluster in the Ralstonia solanacearum GMI1000 sequence" }, { "name": "Cvi", "description": "Number of sequences belonging to cluster in the Chromobacterium violaceum ATCC 12472 sequence" }, { "name": "Bma", "description": "Number of sequences belonging to cluster in the Burkholderia mallei ATCC 23344 sequence" }, { "name": "Bpe", "description": "Number of sequences belonging to cluster in the Bordetella pertussis Tohama I sequence" }, { "name": "Eba", "description": "Number of sequences belonging to cluster in the Azoarcus sp EbN1 sequence" }, { "name": "Caur", "description": "Number of sequences belonging to cluster in the Chloroflexus aurantiacus sequence" }, { "name": "Cch", "description": "Number of sequences belonging to cluster in the Chlorobium chlorochromatii CaD3 sequence" }, { "name": "Clim", "description": "Number of sequences belonging to cluster in the Chlorobium limicola DSM 245 sequence" }, { "name": "Cph", "description": "Number of sequences belonging to cluster in the Chlorobium phaeobacteroides DSM 266 sequence" }, { "name": "Ctep", "description": "Number of sequences belonging to cluster in the Clorobium tepidum sequence" }, { "name": "Pvi", "description": "Number of sequences belonging to cluster in the Prostheocochloris vibrioformis DSM 265 sequence" }, { "name": "Afu", "description": "Number of sequences belonging to cluster in the Archaeoglobus fulgidus DSM 4304 sequence" }, { "name": "Hal", "description": "Number of sequences belonging to cluster in the Halobacterium sp. NRC-1 sequence" }, { "name": "Mac", "description": "Number of sequences belonging to cluster in the Methanosarcina acetivorans str. C2A sequence" }, { "name": "Pho", "description": "Number of sequences belonging to cluster in the Pyrococcus horikoshii OT3 sequence" }, { "name": "Ape", "description": "Number of sequences belonging to cluster in the Aeropyrum pernix K1 sequence" }, { "name": "Sto", "description": "Number of sequences belonging to cluster in the Sulfolobus tokodaii str. 7 sequence" }, { "name": "Neq", "description": "Number of sequences belonging to cluster in the Nanoarchaeum equitans Kin4-M sequence" }, { "name": "SCE", "description": "Number of sequences belonging to cluster in the Saccharomyces cerevisiae sequence" }, { "name": "SPO", "description": "Number of sequences belonging to cluster in the Schyzosaccharomyces pombe sequence" }, { "name": "PHRA", "description": "Number of sequences belonging to cluster in the Phytophthora ramorum sequence" }, { "name": "PHSO", "description": "Number of sequences belonging to cluster in the Phytophthora sojae sequence" }, { "name": "DCGR", "description": "Number of sequences belonging to cluster in the Candida glabrata CBS138 sequenc" }, { "name": "DKLA", "description": "Number of sequences belonging to cluster in the Kluyveromyces lactis NRRL Y-1140 sequence" }, { "name": "NCR", "description": "Number of sequences belonging to cluster in the Neurospora crassa 74-OR23-1A sequence" }, { "name": "DPTM", "description": "Number of sequences belonging to cluster in the Paramecium tetraurelia sequence" }, { "name": "TET", "description": "Number of sequences belonging to cluster in the Tetrahymena thermophila SB210 sequence" }, { "name": "NGR", "description": "Number of sequences belonging to cluster in the Naegleria gruberi sequence" }, { "name": "HSA", "description": "Number of sequences belonging to cluster in the Homo sapiens sequence" }, { "name": "DME", "description": "Number of sequences belonging to cluster in the Drosophila melanogaster sequence" }, { "name": "CEL", "description": "Number of sequences belonging to cluster in the Caenorhabditis elegans sequence" }, { "name": "Annotations", "description": "Annotation" } ] }, { "path": "en\/lsdb-gene-thesaurus\/data-1.html", "name": "Gene Name Thesaurus", "database_name": "Gene Name Thesaurus", "doi": "10.18908\/lsdba.nbdc00966-001", "description": "Curators who have expertize in biological research edit gene names found in various databases and articles to show associations between them.", "files": [ { "file_name": "dictionary.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/lsdb_gene_thesaurus\/LATEST\/dictionary.zip", "file_size": "4.6MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/lsdb_gene_thesaurus#en", "data_acquisition": "We extracted synonyms described in databases such as Entrez Gene, Swiss-Prot and HGNC.", "analysis": "1. Collect gene names automatically from synonym information fields in various gene\/genome databases.\r\n2. The curators who have expertise in biological research confirm the name variation for genes and associate them. They also delete names which are confusing to associate (polysemy, acronyms for different genes etc.).\r\n3. Extract words describe gene names from MEDLINE abstracts and collect unregistered names.\r\n4. Evaluate detection performance of gene names in the dictionary.\r\n5. Add non-detected words to the dictionary and repeat 4-5 using other literature set.", "data_number": "Gene family\r\nNumber of genes: 12,110\r\nNumber of names: 27,923\r\n\r\nHuman\r\nNumber of genes: 27,959\r\nNumber of names: 145,623\r\n\r\nMouse\r\nNumber of genes: 48,545\r\nNumber of names: 173,375\r\n\r\nRat\r\nNumber of genes: 17,319\r\nNumber of names: 61,801\r\n\r\nZebrafish\r\nNumber of genes: 24,230\r\nNumber of names: 60,270\r\n\r\nFruit fly\r\nNumber of genes: 30,708\r\nNumber of names: 96,934\r\n\r\nNematode\r\nNumber of genes: 25,304\r\nNumber of names: 96,220\r\n\r\nBudding yeast\r\nNumber of genes: 7,359\r\nNumber of names: 29,533\r\n\r\nFission yeast\r\nNumber of genes: 7,943\r\nNumber of names: 15,431\r\n\r\nBacillus subtilis\r\nNumber of genes: 4,206\r\nNumber of names: 14,816", "details": [ { "name": "SWISS-PROT_ID", "description": "ID of SWISS-PROT" }, { "name": "EntrezGene_ID", "description": "ID of EntrezGene" }, { "name": "Other_ID", "description": "ID of databases other than above" }, { "name": "Gene_Name", "description": "Gene name" } ] }, { "path": "en\/genius\/data-1.html", "name": "HTML Source", "database_name": "GENIUS II", "doi": "10.18908\/lsdba.nbdc00471-001", "description": "HTML Source of the original site (terminated). Note that links to CGI don't work.", "files": [ { "file_name": "HTML_Source.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/HTML_Source.tar.gz", "file_size": "41MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/genius\/data-2.html", "name": "ORF List", "database_name": "GENIUS II", "doi": "10.18908\/lsdba.nbdc00471-002", "description": "This is the ORF list of 234 genomes. You can access to ORF sequences and these alignments information.", "files": [ { "file_name": "genius_orf_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/genius_orf_list.zip", "file_size": "15 MB" }, { "file_name": "Analysis_Result.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/Analysis_Result.tar.gz", "file_size": "28 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/genius_orf_list#en", "data_acquisition": "PDB, RefSeq, nr-aa, PROSITE, CATH", "analysis": "PDB structures were assigned to nr-aa protein sequences using PSI-BLAST search. Hit regions which met a similarity threshold calculated using CATH structure information were gathered as intermediate sequences, and genome ORF sequences were assigned to these intermediate sequences by BLAST search. Thus, PDB structures were linked to genome ORF sequences via intermediate sequences.", "data_number": "817789", "details": [ { "name": "ORF Name", "description": "ORF Name" }, { "name": "ORF ID", "description": "ORF ID" }, { "name": "Superkingdom", "description": "Superkingdom of the species which contains this ORF" }, { "name": "Species", "description": "The species which contains this ORF" }, { "name": "Chromosome", "description": "The chromosome (Refseq ID) which contains this ORF" }, { "name": "Alignment (PDB & Intermediate Sequence)", "description": "PDB ID and its corresponding intermediate sequence ID\r\nIt links to the alignment information." }, { "name": "Alignment (ORF & Intermediate Sequence)", "description": "ORF Name and its corresponding intermediate sequence ID\r\nIt links to the alignment information." }, { "name": "Region in PDB (3D)", "description": "The position of PDB 3D structure corresponding this ORF" }, { "name": "Prosite Motifs (in ORF)(in PDB)", "description": "The PROSITE motif corresponding this ORF" } ] }, { "path": "en\/genius\/data-3.html", "name": "ORF Sequence", "database_name": "GENIUS II", "doi": "10.18908\/lsdba.nbdc00471-003", "description": "ORF sequence (amino acid)", "files": [ { "file_name": "genius_orf_sequence.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/genius_orf_sequence.zip", "file_size": "164 MB" }, { "file_name": "ORF_Sequence.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/ORF_Sequence.tar.gz", "file_size": "182 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/genius_orf_sequence#en", "data_acquisition": "RefSeq", "analysis": "", "data_number": "783495", "details": [ { "name": "Chromosome", "description": "The chromosome (Refseq ID) which contains this ORF" }, { "name": "ORF ID", "description": "ORF ID" }, { "name": "Header", "description": "FASTA header of this sequence" }, { "name": "Sequence", "description": "Sequence" } ] }, { "path": "en\/genius\/data-4.html", "name": "PDB Alignment", "database_name": "GENIUS II", "doi": "10.18908\/lsdba.nbdc00471-004", "description": "It links to the PSI-BLAST alingment information between PDB and intermediate sequences", "files": [ { "file_name": "genius_pdb_alignment.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/genius_pdb_alignment.zip", "file_size": "23 KB" }, { "file_name": "PDB_Alignment.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/PDB_Alignment.tar.gz", "file_size": "4.3 GB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/genius_pdb_alignment#en", "data_acquisition": "PDB, nr-aa", "analysis": "We conducted PSI-BLAST search between PDB and intermediate sequences (nr-aa).", "data_number": "4181", "details": [ { "name": "Query", "description": "PSI-BLAST search query (PDB ID)" }, { "name": "Alignment", "description": "It links to the alignment result file." } ] }, { "path": "en\/genius\/data-5.html", "name": "ORF Alignment", "database_name": "GENIUS II", "doi": "10.18908\/lsdba.nbdc00471-005", "description": "It links to the alingment information between ORF and intermediate sequences", "files": [ { "file_name": "genius_orf_alignment.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/genius_orf_alignment.zip", "file_size": "170 MB" }, { "file_name": "ORF_Alignment.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/genius\/LATEST\/ORF_Alignment.tar.gz", "file_size": "168 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/genius_orf_alignment#en", "data_acquisition": "RefSeq, nr-aa", "analysis": "We conducted BLAST search between ORF and intermediate sequences (nr-aa).", "data_number": "", "details": [ { "name": "Chromosome", "description": "The chromosome (RefSeq ID) which contains this ORF" }, { "name": "Query", "description": "BLAST search query (ORF ID)" }, { "name": "Alignment", "description": "Alignment result" } ] }, { "path": "en\/genlibi\/data-1.html", "name": "Genetic and bibliographic information", "database_name": "GenLibi", "doi": "10.18908\/lsdba.nbdc01093-001", "description": "Information of gene functions and their related diseases and phenotypes that were obtained from the JST bibliographic information.", "files": [ { "file_name": "genlibi_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/genlibi\/LATEST\/genlibi_en.zip", "file_size": "12 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/genlibi_en", "data_acquisition": "Articles related to genes were obtained from the bibliography database (JDream II) which was run by JST.", "analysis": "Information on genes and its ralated diseases and phenotypes was extracted from the contents of the articles.", "data_number": "216 entries", "details": [ { "name": "Gene ID", "description": "ID of the gene" }, { "name": "Gene Symbol", "description": "Symbol of the gene" }, { "name": "Gene Name", "description": "Name of the gene" }, { "name": "Organism", "description": "Organism of the gene" }, { "name": "Phenotype from JST bibliography", "description": "Names of the diseases or the phenotypes that were extracted from the articles related to the gene" }, { "name": "MeSH Tree", "description": "MeSH trees of the MeSH terms that are corresponding to the diseases or the phenotypes" }, { "name": "JST bibliography database", "description": "IDs of the articles provided from the JST bibliographic information system (JDream II)" } ] }, { "path": "en\/getdb\/data-1.html", "name": "Expression information data table (Strain List) of Drosophila GAL4 enhancer trap lines", "database_name": "GETDB", "doi": "10.18908\/lsdba.nbdc00236-001", "description": "A table showing the insert position of the Drosophila GAL4 enhancer trap element and the data on the adjacent downstream sequence for each clone. 5,555 clones.", "files": [ { "file_name": "getdb.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/getdb\/LATEST\/getdb.zip", "file_size": "345KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/getdb#en", "data_acquisition": "Data of Drosophila GAL4 enhancer trap lines", "analysis": "", "data_number": "4,250 entries", "details": [ { "name": "Line information", "description": "" }, { "name": "DGRC Number", "description": "Line number of DGRC (Drosophila Genetic Resource Center) (Link to DGRC in TogoDB)" }, { "name": "Genotype", "description": "Genotype" }, { "name": "Insertion Site", "description": "Insert site(s) on the physical map. For two or more insert sites, use semicolon to delimit each site (see http:\/\/www.dgrc.kit.jp\/~jdd\/chromosome\/index.html). (Link to the DGRC genome viewer is created, and the download file has link tag.)" }, { "name": "Map Viewer", "description": "DGRC Number (TogoDB has link to the DGRC genome viewer.)" }, { "name": "Related Genes", "description": "Name of related gene" }, { "name": "Original Number", "description": "Line number in GETDB" }, { "name": "Chr.", "description": "Chromosome number" }, { "name": "Comments", "description": "Comment" }, { "name": "Balancer", "description": "Name of balancer chromosome" }, { "name": "Link to Clone Table", "description": "Link to clone list (Empty column in downloaded file)" }, { "name": "Num of clones", "description": "Number of clones" }, { "name": "Cluster id", "description": "Cluster ID (two or more)" }, { "name": "Link to Cluster Table", "description": "Cluster ID. Two or more IDs will be delimited by %7C (\"|\" decoded by UTF8). (Link to cluster table is available in TogoDB.)" }, { "name": "Num of clusters", "description": "Number of clusters" }, { "name": "Stock Request", "description": "Link to placing an order for the stock (Empty column in the downloaded file.)" }, { "name": "Expression information", "description": "" }, { "name": "Embryonic Expression", "description": "Information on expression in embryo" }, { "name": "Larval GFP", "description": "Information on expression of GFP in larva" }, { "name": "Larval X-gal", "description": "Information on expression of X-gal in larva" }, { "name": "Adult GFP", "description": "Information on expression of GFP in adult" }, { "name": "Lethality", "description": "Lethality" }, { "name": "Also known as", "description": "Genotype alias" }, { "name": "Original Comments", "description": "Original Comment (Comment by GETDB)" }, { "name": "Fluorescence expression image", "description": "" }, { "name": "Disc(Image)", "description": "Expression image in imaginal disc" }, { "name": "Disc (Number)", "description": "Number of expression images in imaginal disc" }, { "name": "Embryo(Image)", "description": "Expression image in embryo" }, { "name": "Embryo (Number)", "description": "Number of expression images in embryo" }, { "name": "Larval GFP(Image)", "description": "Fluorescence expression image in GFP-dyed larva" }, { "name": "Larval GFP (Number)", "description": "Number of fluorescence expression images in GFP-dyed larva" }, { "name": "Adult(Image)", "description": "Expression image in adult" }, { "name": "Adult (Number)", "description": "Number of expression images in adult" } ] }, { "path": "en\/getdb\/data-2.html", "name": "Genome mapping data table of Drosophila GAL4 enhancer trap lines (Clone List)", "database_name": "GETDB", "doi": "10.18908\/lsdba.nbdc00236-002", "description": "A table showing the insert position of the Drosophila GAL4 enhancer trap element and the data on the adjacent downstream sequence for each clone. 5,555 clones.", "files": [ { "file_name": "getdb_clone.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/getdb\/LATEST\/getdb_clone.zip", "file_size": "1.4MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/getdb_clone#en", "data_acquisition": "", "analysis": "", "data_number": "5,555 entries", "details": [ { "name": "Clone Name", "description": "Name of the clone of the genome sequence adjacent to the 5'-end of the Drosophila GAL4 enhancer trap element" }, { "name": "DGRC Number", "description": "Line number (Link to Strain Table in TogoDB)" }, { "name": "Cluster Id", "description": "Cluster ID of genome insert coordinate (Link to Cluster Table in TogoDB)" }, { "name": "Strand", "description": "Insert direction to genome sequence (*)" }, { "name": "Insertion Point", "description": "Insert position on genome sequence (*)" }, { "name": "Chr. Band", "description": "Chromosome band" }, { "name": "Flanking Sequence", "description": "Adjacent sequence downstream of the insert point." } ] }, { "path": "en\/getdb\/data-3.html", "name": "Clustering Table of the genome insert site of Drosophila GAL4 enhancer trap lines (Cluster List)", "database_name": "GETDB", "doi": "10.18908\/lsdba.nbdc00236-003", "description": "Cluster data in which the insert positions of the Drosophila GAL4 enhancer trap element are clustered by the closeness of their positions from each other. 2,099 clusters.", "files": [ { "file_name": "getdb_cluster.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/getdb\/LATEST\/getdb_cluster.zip", "file_size": "56KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/getdb_cluster#en", "data_acquisition": "", "analysis": "Mapping by Blast (using the genome sequence (Release 3.1) sequenced by Berkeley Drosophila Genome Project (BDGP)\/Celera as the target genome)", "data_number": "2,099 entries", "details": [ { "name": "ClusterId", "description": "Cluster ID of genome insert coordinate" }, { "name": "Cluster Member(Clone Name : Cluster Id)", "description": "Clone name corresponding to each of the insert point sequences belonging to the cluster" }, { "name": "Cluster Size", "description": "Number of insert coordinates belonging to the cluster." }, { "name": "Link to Clone Table", "description": "Cluster ID. (Link to CloneTable in TogoDB.)" }, { "name": "Link to Strain Table", "description": "Cluster ID. (Link to Strain Table in TogoDB)" }, { "name": "Chr. Band", "description": "Chromosome band" }, { "name": "Insertion Point (Min)", "description": "Minimum value in the cluster of insert positions on genome sequence" }, { "name": "Insertion Point (Max)", "description": "Maximum value in the cluster of insert positions on genome sequence" }, { "name": "Max-Min", "description": "Maximum value minus minimum value of insert positions on genome sequence" } ] }, { "path": "en\/getdb\/data-4.html", "name": "Expression image data of Drosophila GAL4 enhancer trap lines", "database_name": "GETDB", "doi": "10.18908\/lsdba.nbdc00236-004", "description": "3,075 expression image data by developmental stages of Drosophila\r\nImages are classified into the following four developmental stages.\r\n- Expression image in imaginal disc\r\n- Expression image in embryo\r\n- Fluorescence expression image in GFP-dyed larva\r\n- Expression image in adult\r\nThe image file is provided in the JPEG format. The file name is composed of \r\n\"the number corresponding to the line\"_\"a single alphabet denoting the developmental phase (imaginal disc (d), embryo (e), larva (g), adult (a))\"\"serial number of the images classified by developmental stages in the line\".jpg.\r\n(Example: 4310_d1.jpg) Correspondence between \"the number corresponding to the line\" and the DGRC Number is shown in \"dgrcnum_imagenum.csv\" in the ZIP file.", "files": [ { "file_name": "getdb_images.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/getdb\/LATEST\/getdb_images.zip", "file_size": "247MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "3,075", "details": [] }, { "path": "en\/gggenome\/data-1.html", "name": "GGGenome dataset", "database_name": "GGGenome dataset", "doi": "", "description": "It is data for GGGenome. Each data is compressed in tgz file. It consists of reference sequence file (fasta format) and index files for GGGenome.\r\n\r\nReference sequence file:\r\n- *.fa\r\n\r\nIndex files for GGGenome:\r\n- *.dna4\r\n- *.doc\r\n- *.fmidx\r\n- *.sa", "files": [ { "file_name": "data", "file_url": "https:\/\/biosciencedbc.jp\/archive\/gggenome\/data\/", "file_size": "17 GB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "1 entry", "details": [] }, { "path": "en\/jam-coral-img\/data-1.html", "name": "img", "database_name": "Image collection in the Coral Reef Network WEB System", "doi": "10.18908\/lsdba.nbdc02655-001", "description": "Pictures and videos taken in the coral reefs of the Ryukyu Islands.", "files": [], "togodb_url": "", "data_acquisition": "Pictures were provided by citizen divers and videos were collected from a small remotely-operated vehicle \"Niraikanai 150\".", "analysis": "", "data_number": "image and video: 2411 files", "details": [ { "name": "JPG", "description": "" }, { "name": "flv", "description": "" } ] }, { "path": "en\/jam-coral-img\/data-2.html", "name": "sango_web.xml", "database_name": "Image collection in the Coral Reef Network WEB System", "doi": "10.18908\/lsdba.nbdc02655-002", "description": "metadata file of the picture and videos in the IMG folder (data 1)", "files": [], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "1170", "details": [ { "name": "id", "description": "Identifier" }, { "name": "title", "description": "Title" }, { "name": "description", "description": "Comment" }, { "name": "j_name", "description": "Japanese name" }, { "name": "s_name", "description": "Scientific name" }, { "name": "type", "description": "Type of subject" }, { "name": "person", "description": "Author" }, { "name": "date", "description": "Date" }, { "name": "area", "description": "Location name" }, { "name": "point", "description": "More detailed location name" }, { "name": "depth", "description": "Water depth" }, { "name": "weather", "description": "Weather condition" }, { "name": "thumImg", "description": "Thumbnail filename of the picture and\/or the video" }, { "name": "bigImg", "description": "File name of the picture" }, { "name": "movie", "description": "File name of the video" } ] }, { "path": "en\/asteraceae-chr-index\/data-1.html", "name": "Index to Chromosome numbers in Asteraceae", "database_name": "Index to Chromosome numbers in Asteraceae", "doi": "10.18908\/lsdba.nbdc02601-001", "description": "The title of Asteraceae “Index to Chromosome numbers in Asteraceae” has been used for the representative of families in Asterales due to the largest and most familiar for many researchers. It is included the published data of all members in whole of Asterales, instead of being restricted to just members of Asteraceae: Alangiaceae, Alseuosmiaceae, Argophyllaceae, Calyceraceae, Campanulaceae, Carpodetaceae, Goodeniaceae, Menyanthaceae, Pentaphragmataceae, Phellinaceae, Rousseaceae, Stylidiaceae (all of them are placed in Asterales at present “2021, December\"\"). This Database includes taxon name, chromosome number (n and 2n), DNA contents, genbank accession numbers (for the nuclear or chloroplast DNA sequences：You can know that taxa used for molecular phylogenetic analyses), habit (life form) and size of plant, reproductive system, collection locality (Nation), Author (s) and the title of paper and published journal names.\r\nThe classification of the Asteraceae (= Compositae) follows on Susanna, A. et al (2020) is followed in this database.　Sixteen subfamilies (Barnadesioideae, Famatinanthioideae, Stifftioideae, Mutisioideae, Gochnatioideae, Wunderlichioideae, Hacastocleideideae, Perytyoideae, Tarchonanthoideae, Dicomoideae, Carduoideae, Gymnarrhenoideae, Vernonioideae, Cichorioideae, Corymboideae, Asteroideae.) + 49 tribes + 116 subtribes are included.", "files": [ { "file_name": "index_chromosome_number_asteraceae.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/asteraceae-chr-index\/LATEST\/index_chromosome_number_asteraceae.zip", "file_size": "13 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/db\/index_chr_num_asteraceae", "data_acquisition": "", "analysis": "", "data_number": "223,225", "details": [ { "name": "No.", "description": "Number, it will be changed in each update" }, { "name": "Family \/ Subfamily", "description": "Family \/ Subfamily" }, { "name": "Tribe \/ Subtribe", "description": "Tribe \/ Subtribe" }, { "name": "Genus", "description": "Genus" }, { "name": "Species \/ Subspecies", "description": "Species \/ Subspecies" }, { "name": "Variety", "description": "Variety" }, { "name": "chromosome number n", "description": "chromosome number n=（No. of plants examined)" }, { "name": "chromosome number 2n", "description": "chromosome number 2n=(total karyotypic length)（No. of plants examined)" }, { "name": "Life form", "description": "Life form" }, { "name": "Breeding system", "description": "Breeding system" }, { "name": "Collected Locality", "description": "Collected Locality" }, { "name": "Author name ＆ Published year", "description": "Author name ＆ Published year" }, { "name": "Author", "description": "Author" }, { "name": "Year", "description": "Year" }, { "name": "Title", "description": "Title" }, { "name": "Journal", "description": "Journal" }, { "name": "Vol.(Number)", "description": "Vol.(Number)" }, { "name": "Page", "description": "Page" } ] }, { "path": "en\/inoh\/data-1.html", "name": "Signal Transduction Pathway Data", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-007.V003", "description": "Signal transduction pathway data is well-annotated, machine-processable data collected from literature.", "files": [ { "file_name": "inoh_signal_transduction_pathway.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/inoh_signal_transduction_pathway.zip", "file_size": "5.7KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/inoh_signal_transduction_pathway#en", "data_acquisition": "It is collected from literature manually.", "analysis": "", "data_number": "72 entries", "details": [ { "name": "Pathway Name", "description": "Name of signal transduction pathway" }, { "name": "INOH format", "description": "Link to INOH format file" }, { "name": "BioPAX level2 format", "description": "Link to BioPAX level2 format file" }, { "name": "BioPAX level3 format", "description": "Link to BioPAX level3 format file" }, { "name": "PubMed ID", "description": "Link to PubMed" } ] }, { "path": "en\/inoh\/data-2.html", "name": "Metabolic Pathway Data", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-008.V003", "description": "Metabolic pathway data is well-annotated, machine-processable data collected from literature.", "files": [ { "file_name": "inoh_metabolic_pathway.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/inoh_metabolic_pathway.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/inoh_metabolic_pathway#en", "data_acquisition": "It is collected from literature manually.", "analysis": "", "data_number": "29 entries", "details": [ { "name": "Pathway Name", "description": "Name of metabolic pathway" }, { "name": "INOH format", "description": "Link to INOH format file" }, { "name": "BioPAX level2 format", "description": "Link to BioPAX level2 format file" }, { "name": "BioPAX level3 format", "description": "Link to BioPAX level3 format file" } ] }, { "path": "en\/inoh\/data-3.html", "name": "MoleculeRole Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-001.V003", "description": "MoleculeRole Ontology is an ontology for proteins\/chemicals.\r\nIt is used to annotate protein family names, generic\/concrete protein names and chemical names in the INOH pathway data.", "files": [ { "file_name": "inoh_moleculerole_ontology.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/inoh_moleculerole_ontology.zip", "file_size": "673KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/inoh_moleculerole_ontology#en", "data_acquisition": "It is collected from literature manually.", "analysis": "", "data_number": "9,217 entries", "details": [ { "name": "inoh_id", "description": "ID of the term" }, { "name": "alt_id", "description": "Altanative ID of the term" }, { "name": "name", "description": "Name of the term" }, { "name": "synonym", "description": "Synonym of the term" }, { "name": "def", "description": "Definition of the term" }, { "name": "xref_analog", "description": "Cross-reference to other ontology term" }, { "name": "comment", "description": "Comment of the term" }, { "name": "linkage", "description": "Image file that represents \"is_a\" and \"part_of\" relations between terms." }, { "name": "inoh_client", "description": "Link to start the INOH Client application." }, { "name": "is_a", "description": "Definition of \"is_a\" relation." }, { "name": "relationship", "description": "Definition of \"part_of\" relation." }, { "name": "is_obsolete", "description": "The flag that indicates whether the term is obsolete or not.\r\n\"true\" indicates that the term is obsolete." } ] }, { "path": "en\/inoh\/data-4.html", "name": "Event Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-003.V003", "description": "Event Ontology is an ontology of pathways.\r\nIt classifies pathways, sub-pathways and other biological phenomena to form a DAG structure.", "files": [ { "file_name": "inoh_event_ontology.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/inoh_event_ontology.zip", "file_size": "188KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/inoh_event_ontology#en", "data_acquisition": "It is collected from literature manually.", "analysis": "", "data_number": "3,828 entries", "details": [ { "name": "inoh_id", "description": "ID of the term" }, { "name": "alt_id", "description": "Altanative ID of the term" }, { "name": "name", "description": "Name of the term" }, { "name": "synonym", "description": "Synonym of the term" }, { "name": "def", "description": "Definition of the term" }, { "name": "xref_analog", "description": "Cross-reference to other ontology term" }, { "name": "comment", "description": "Comment of the term" }, { "name": "linkage", "description": "Image file that represents \"is_a\" and \"part_of\" relations between terms." }, { "name": "inoh_client", "description": "Link to start the INOH Client application." }, { "name": "is_a", "description": "Definition of \"is_a\" relation." }, { "name": "relationship", "description": "Definition of \"part_of\" relation." }, { "name": "is_obsolete", "description": "The flag that indicates whether the term is obsolete or not.\r\n\"true\" indicates that the term is obsolete." } ] }, { "path": "en\/inoh\/data-5.html", "name": "Location Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-005.V003", "description": "Location Ontology is an ontology of cellular location.", "files": [ { "file_name": "inoh_location_ontology.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/inoh_location_ontology.zip", "file_size": "5.3KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/inoh_location_ontology#en", "data_acquisition": "It is collected from literature manually.", "analysis": "", "data_number": "52 entries", "details": [ { "name": "inoh_id", "description": "ID of the term" }, { "name": "alt_id", "description": "Altanative ID of the term" }, { "name": "name", "description": "Name of the term" }, { "name": "synonym", "description": "Synonym of the term" }, { "name": "def", "description": "Definition of the term" }, { "name": "xref_analog", "description": "Cross-reference to other ontology term" }, { "name": "comment", "description": "Comment of the term" }, { "name": "linkage", "description": "Image file that represents \"is_a\" and \"part_of\" relations between terms." }, { "name": "inoh_client", "description": "Link to start the INOH Client application." }, { "name": "is_a", "description": "Definition of \"is_a\" relation." }, { "name": "relationship", "description": "Definition of \"part_of\" relation." }, { "name": "is_obsolete", "description": "The flag that indicates whether the term is obsolete or not.\r\n\"true\" indicates that the term is obsolete." } ] }, { "path": "en\/inoh\/data-6.html", "name": "Linkage image file of MoleculeRole Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-002.V003", "description": "Linkage image file of MoleculeRole Ontology.\r\n9,217 PNG files are compressed into a ZIP file.", "files": [ { "file_name": "IMR.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/ontology\/images\/IMR.zip", "file_size": "17.9MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "9,217 entries", "details": [] }, { "path": "en\/inoh\/data-7.html", "name": "Linkage image file of Event Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-004.V003", "description": "Linkage image file of Event Ontology.\r\n3,829 PNG files are compressed into a ZIP file.", "files": [ { "file_name": "IEV.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/ontology\/images\/IEV.zip", "file_size": "15.6MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "3,829 entries", "details": [] }, { "path": "en\/inoh\/data-8.html", "name": "Linkage image file of Location Ontology", "database_name": "INOH", "doi": "10.18908\/lsdba.nbdc00107-006.V003", "description": "Linkage image file of Location Ontology.\r\n53 PNG files are compressed into a ZIP file.", "files": [ { "file_name": "ILC.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/inoh\/LATEST\/ontology\/images\/ILC.zip", "file_size": "119KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "53 entries", "details": [] }, { "path": "en\/jedisystem-oceansdb\/data-1.html", "name": "JEDI System\/OCEANS_ADCP", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-001.V001", "description": "Multilayer water current by Acoustic Doppler Current Profiler (ADCP) and directional waves by Acoustic Wave and Current Profiler (AWAC)", "files": [ { "file_name": "OCEANS_adcp1.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_adcp1.zip", "file_size": "446 MB" } ], "togodb_url": "", "data_acquisition": "Nortek Aquadopp Profiler (AquaPro), 60 seconds intervals, 20 layers (AquaPro\/RawBinary\/, AquaPro\/ASCIIoutput\/)\r\nNortek Acoustic Wave and Current Profiler (AWAC - 400kHz), 60 seconds intervals (AWAC\/RawBinary', AWAC\/ASCIIconvertedRAW\/)", "analysis": "", "data_number": "prf: 920 files, pra: 917 files; wpr: 7 files, ASCIIconvertedRAW: 6 sets", "details": [ { "name": "AquaPro\/RawBinary\/*.prf", "description": "AquaPro raw binary files" }, { "name": "AquaPro\/ASCIIoutput\/*.pra", "description": "AquaPro ASCII output files" }, { "name": "pra file format", "description": "" }, { "name": "Header line", "description": "" }, { "name": "Month", "description": "[1-12]" }, { "name": "Day", "description": "[1-31]" }, { "name": "Year", "description": "" }, { "name": "Hour", "description": "[0-23]" }, { "name": "Minute", "description": "[0-59]" }, { "name": "Second", "description": "[0-59]" }, { "name": "Error code", "description": "" }, { "name": "Status code", "description": "" }, { "name": "Battrey voltage", "description": "[V]" }, { "name": "Sound speed", "description": "[m\/s]" }, { "name": "Heading", "description": "[degrees]" }, { "name": "Pitch", "description": "[degrees]" }, { "name": "Roll", "description": "[degrees]" }, { "name": "Pressure", "description": "[dbar]" }, { "name": "Temperture", "description": "[degrees C]" }, { "name": "Analog input 1", "description": "" }, { "name": "Analog input 2", "description": "" }, { "name": "Number of beams", "description": "" }, { "name": "Number of cells", "description": "" }, { "name": "Data lines (repeat below）", "description": "" }, { "name": "Cell number", "description": "" }, { "name": "Velocity (Beam 1)", "description": "X|East [m\/s]" }, { "name": "Velocity (Beam 2)", "description": "Y|North [m\/s]" }, { "name": "Velocity (Beam 3)", "description": "Z|Up [m\/s]" }, { "name": "Amplitude (Beam 1)", "description": "[counts]" }, { "name": "Amplitude (Beam 2)", "description": "[counts]" }, { "name": "Amplitude (Bean 3)", "description": "[counts]" }, { "name": "AWAC\/RawBinary\/*.wpr", "description": "AWAC raw binary files" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.a[123]", "description": "AWAC amplitude data (Beam 1, 2, 3)" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.csv", "description": "AWAC profile data (comma sepalated values format)" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.dat", "description": "AWAC velocity data" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.hdr", "description": "AWAC header file (each file format are described by ASCII)" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.nmea", "description": "AWAC raw data in NMEA format" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.sen", "description": "AWAC sensor data" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.ssl", "description": "AWAC system state file" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.v[123]", "description": "AWAC velocity data (Beam 1|X|East, Beam 2|Y|North, Beam 3|Z|Up)" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.wad", "description": "AWAC raw wave data" }, { "name": "AWAC\/ASCIIconvertedRAW\/*.whd", "description": "AWAC wave header data" } ] }, { "path": "en\/jedisystem-oceansdb\/data-2.html", "name": "JEDI System\/OCEANS_ADV", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-002.V001", "description": "3D velocity data for small scale (turbulence)", "files": [ { "file_name": "OCEANS_adv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_adv.zip", "file_size": "22 GB" } ], "togodb_url": "", "data_acquisition": "Nortek Vector Current Meter (Acoustic Doppler Velocimeter), 8Hz", "analysis": "", "data_number": "Raw\/vec: 984 files, Raw\/vea: 974 files; Processed\/txt: 943 files", "details": [ { "name": "Raw\/*.vec", "description": "Raw data (binary)" }, { "name": "Raw\/*.vea", "description": "Raw data (ASCII)" }, { "name": "Processed\/*.txt", "description": "1min. Processed data (ASCII)" }, { "name": "Format of txt file", "description": "" }, { "name": "date", "description": "Date (YYYY\/MM\/DD)" }, { "name": "time", "description": "Time (hh:mm:ss)" }, { "name": "depth_m", "description": "Depth [meter]" }, { "name": "press_dbar", "description": "Pressure [dbar]" }, { "name": "temp_degC", "description": "Temperature [degrees C]" }, { "name": "velE_m\/s", "description": "Velocity (East) [m\/s]" }, { "name": "velN_m\/s", "description": "Velocity (North) [m\/s]" }, { "name": "velU_m\/s", "description": "Velocity (Up) [m\/s]" }, { "name": "corrE_%", "description": "Correlation (East) [%]" }, { "name": "corrN_%", "description": "Correlation (North) [%]" }, { "name": "corrU_%", "description": "Correlation (Up) [%]" } ] }, { "path": "en\/jedisystem-oceansdb\/data-3.html", "name": "JEDI System\/OCEANS_ChlorTurbit", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-003.V001", "description": "Chlorophyll and Turbidity data by logger sensor with wiper", "files": [ { "file_name": "OCEANS_ChlorTurbid.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_ChlorTurbid.zip", "file_size": "514 MB" } ], "togodb_url": "", "data_acquisition": "JFE INFINITY-CLW (logger version chlorophyll and turbidity sensor with wipter)", "analysis": "", "data_number": "1426", "details": [ { "name": "Date", "description": "[YYYY\/MM\/DD]" }, { "name": "Time", "description": "[hh:mm:ss.sss]" }, { "name": "pval", "description": "" }, { "name": "Temperature", "description": "[degrees C]" }, { "name": "Chlorophyll", "description": "[ug\/l] (microgram per litter)" }, { "name": "Turbidity", "description": "[FTU] (Formazin Turbidity Unit)" }, { "name": "Power voltage", "description": "[V]" } ] }, { "path": "en\/jedisystem-oceansdb\/data-4.html", "name": "JEDI System\/OCEANS_CondTemp", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-004.V001", "description": "Electric conductivity and temperature by logger sensor with wiper", "files": [ { "file_name": "OCEANS_CondTemp.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_CondTemp.zip", "file_size": "626 MB" } ], "togodb_url": "", "data_acquisition": "JFE INFINITY-CTW (logger version conductivity and temperature sensor with wiper), 1Hz", "analysis": "", "data_number": "1427", "details": [ { "name": "Date", "description": "[YYYY\/MM\/DD]" }, { "name": "Time", "description": "[hh:mm:ss.sss]" }, { "name": "pval", "description": "" }, { "name": "Conductivity", "description": "[mS\/cm]" }, { "name": "Temperature", "description": "[degrees C]" }, { "name": "Salinity", "description": "" } ] }, { "path": "en\/jedisystem-oceansdb\/data-5.html", "name": "JEDI System\/OCEANS_DO", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-005.V001", "description": "Dissolved Oxygen (DO) concentration and temperature by optical DO sensor with wiper", "files": [ { "file_name": "OCEANS_DO.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_DO.zip", "file_size": "443 MB" } ], "togodb_url": "", "data_acquisition": "JFE RINKO W (Optical DO sensor with wiper), 0.2Hz", "analysis": "", "data_number": "1426", "details": [ { "name": "Date", "description": "[YYYY,MM,DD]" }, { "name": "Time", "description": "[hh:mm:ss.sss]" }, { "name": "pval", "description": "" }, { "name": "Temperature", "description": "[degrees C]" }, { "name": "Dissolved Oxygen Concentration", "description": "[%]" }, { "name": "Power voltage", "description": "[V]" } ] }, { "path": "en\/jedisystem-oceansdb\/data-6.html", "name": "JEDI System\/OCEANS_HYDROPHONE", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-006.V001", "description": "Sound by marine mammals", "files": [ { "file_name": "OCEANS_hydrophone_2014.zip, OCEANS_hydrophone_2015.zip, OCEANS_hydrophone_2016.zip, OCEANS_hydrophone_2017.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_hydrophone\/", "file_size": "236 GB" } ], "togodb_url": "", "data_acquisition": "Hydrophone(png and wav)", "analysis": "", "data_number": "wav: 40377 files; png: 40376 files", "details": [ { "name": "PNG", "description": "Portable Network Graphics format" }, { "name": "WAV", "description": "RIFF waveform Audio Format" } ] }, { "path": "en\/jedisystem-oceansdb\/data-7.html", "name": "JEDI System\/OCEANS_PAR", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-007.V001", "description": "Photosynthetically Available Radiation (PAR) by light intensity sensor", "files": [ { "file_name": "OCEANS_PAR.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_PAR.zip", "file_size": "748 M" } ], "togodb_url": "", "data_acquisition": "JFE COMPACT-LW (ALW-CMP; light intensity sensor)", "analysis": "", "data_number": "1200", "details": [ { "name": "Date", "description": "[YYYY\/MM\/DD]" }, { "name": "Time", "description": "[hh:mm:ss.sss]" }, { "name": "real", "description": "" }, { "name": "N1", "description": "" }, { "name": "N2", "description": "" }, { "name": "N3", "description": "" }, { "name": "N4", "description": "" }, { "name": "N5", "description": "" }, { "name": "N6", "description": "" }, { "name": "p_label (pg)", "description": "" }, { "name": "Photo Quantum", "description": "[umol\/m2\/s] (micro-mol\/m2\/sec)" }, { "name": "v_label (v)", "description": "" }, { "name": "Power voltage", "description": "[V]" } ] }, { "path": "en\/jedisystem-oceansdb\/data-8.html", "name": "JEDI System\/OCEANS_SUNA", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-008.V001", "description": "Nitrate data by Submersible Underwater Nutrient Analyzer (SUNA)", "files": [ { "file_name": "OCEANS_suna.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_suna.zip", "file_size": "1.6 GB" } ], "togodb_url": "", "data_acquisition": "Sea-Bird Submersible Underwater Nutrient Analyzer (SUNA), 5 min. intervals", "analysis": "", "data_number": "675", "details": [ { "name": "date", "description": "Date [YYYY\/MM\/DD]" }, { "name": "time", "description": "Time [hh:mm:ss.sss]" }, { "name": "id", "description": "SATSLF0932" }, { "name": "timefield", "description": "YYYY+day of year (e.g., 2016332 = Nov.27, 2016)" }, { "name": "nitrate_um", "description": "Nitrate [umol\/L] (micro-mol per litter)" }, { "name": "nitrate_mg", "description": "Nitrate [mg\/L] (microgram per litter)" }, { "name": "Error", "description": "" }, { "name": "t_lamp", "description": "" }, { "name": "t_spec", "description": "" }, { "name": "humidity", "description": "Humidity" }, { "name": "volt_12", "description": "" }, { "name": "volt_reg", "description": "" }, { "name": "volt_main", "description": "" }, { "name": "spec_ave", "description": "" }, { "name": "dark_ave", "description": "" }, { "name": "ch1-226", "description": "" }, { "name": "chksum", "description": "Checksum" } ] }, { "path": "en\/jedisystem-oceansdb\/data-9.html", "name": "JEDI System\/OCEANS_tstring1", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-009.V001", "description": "20-layer temperature by Thermistor-chain", "files": [ { "file_name": "OCEANS_tstring1.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_tstring1.zip", "file_size": "1.8 GB" } ], "togodb_url": "", "data_acquisition": "20-layer temperature data by PME (Precision Measurement Engineering Inc.) Thermistor Chain", "analysis": "", "data_number": "966", "details": [ { "name": "date", "description": "Date [YYYY\/MM\/DD]" }, { "name": "time", "description": "Time [hh:mm:ss.sss]" }, { "name": "T01", "description": "Temperature at layer 1" }, { "name": "T02", "description": "Temperature at layer 2" }, { "name": "T03", "description": "Temperature at layer 3" }, { "name": "T04", "description": "Temperature at layer 4" }, { "name": "T05", "description": "Temperature at layer 5" }, { "name": "T06", "description": "Temperature at layer 6" }, { "name": "T07", "description": "Temperature at layer 7" }, { "name": "T08", "description": "Temperature at layer 8" }, { "name": "T09", "description": "Temperature at layer 9" }, { "name": "T10", "description": "Temperature at layer 10" }, { "name": "T11", "description": "Temperature at layer 11" }, { "name": "T12", "description": "Temperature at layer 12" }, { "name": "T13", "description": "Temperature at layer 13" }, { "name": "T14", "description": "Temperature at layer 14" }, { "name": "T15", "description": "Temperature at layer 15" }, { "name": "T16", "description": "Temperature at layer 16" }, { "name": "T17", "description": "Temperature at layer 17" }, { "name": "T18", "description": "Temperature at layer 18" }, { "name": "T19", "description": "Temperature at layer 19" }, { "name": "T20", "description": "Temperature at layer 20" }, { "name": "D01", "description": "unknown" } ] }, { "path": "en\/jedisystem-oceansdb\/data-10.html", "name": "JEDI System\/OCEANS_WaveHeight", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-010.V001", "description": "Wave height data by water pressure principle logger version wave height meter", "files": [ { "file_name": "OCEANS_WaveHeight.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_WaveHeight.zip", "file_size": "583 MB" } ], "togodb_url": "", "data_acquisition": "JFE water pressure principle logger version wave height meter, 1Hz", "analysis": "", "data_number": "1426", "details": [ { "name": "Date", "description": "[YYYY\/MM\/DD]" }, { "name": "Time", "description": "[hh:mm:ss.sss]" }, { "name": "pval", "description": "" }, { "name": "Depth", "description": "[meter]" }, { "name": "Temperature", "description": "[degrees C]" }, { "name": "Power voltage", "description": "[V]" } ] }, { "path": "en\/jedisystem-oceansdb\/data-11.html", "name": "JEDI System\/OCEANS_webcam", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-011.V001", "description": "Underwater images (snapshot) by web camera", "files": [ { "file_name": "OCEANS_ webcam_2014.zip, OCEANS_ webcam_2015.zip, OCEANS_ webcam_2016.zip, OCEANS_ webcam_2017.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/OCEANS_webcam\/", "file_size": "159 GB" } ], "togodb_url": "", "data_acquisition": "PTZ (Panoramic\/Tilt\/Zoom) and WHOI (Woods Hole Oceanographic Institution) stereo camera", "analysis": "", "data_number": "567770", "details": [ { "name": "JPG", "description": "image file（JPEG format）" } ] }, { "path": "en\/jedisystem-oceansdb\/data-12.html", "name": "JEDI System\/OCEANS_CPICS", "database_name": "JEDI System\/OCEANS DB", "doi": "10.18908\/lsdba.nbdc02629-012.V001", "description": "Plankton image dataset classified and varridate by WHOI (Woods Hole Oceanographic Institution) CPICS (Conti9nuous Plankton Imaging and Classification System)", "files": [ { "file_name": "OCEANS_CPICS_Validated.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jedisystem-oceansdb\/LATEST\/CPICS_Validated.zip", "file_size": "21 GB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/oceans_cpis_validated#en", "data_acquisition": "WHOI microCPICS (5micro-m to 1mm) for phytoplankton, WHOI CPICS (200micro-m to 2cm) for zooplankton", "analysis": "", "data_number": "1916165", "details": [ { "name": "institutionCode", "description": "institution code" }, { "name": "collectionCode", "description": "collection code" }, { "name": "catalogNumber", "description": "number" }, { "name": "occurrenceID", "description": "ID for a plankton image in the dataset" }, { "name": "occurrenceStatus", "description": "biological occurrence status" }, { "name": "basisOfRecord", "description": "basis of the record" }, { "name": "eventDate", "description": "date time in ISO 8601 fomrmat [yyyy-mm-ddThh:mm:ss+|–hh:mm]" }, { "name": "decimalLatitude", "description": "geographic latitude in decimal degrees" }, { "name": "decimalLongitude", "description": "geographic longitude in decimal degrees" }, { "name": "minimumDepthInMeters", "description": "the lesser depth of a range of depth below the sea surface" }, { "name": "maximumDepthInMeters", "description": "the greater depth of a range of depth below the sea surface" }, { "name": "label", "description": "biological name or object name" }, { "name": "associatedMedia", "description": "file name of the image" } ] }, { "path": "en\/jpostdb\/data-1.html", "name": "Identified protein data", "database_name": "jPOST database", "doi": "10.18908\/lsdba.nbdc01594-02-001", "description": "This is the re-analysis summary results of proteome data in jPOST repository. They are idetified with UniProt protein data.", "files": [ { "file_name": "jpostdb_protein.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpostdb\/LATEST\/jpostdb_protein.zip", "file_size": "11.8MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpostdb_protein", "data_acquisition": "", "analysis": "", "data_number": "530455", "details": [ { "name": "protein_id", "description": "jPOST internal protein ID" }, { "name": "accession", "description": "UniProt ID" }, { "name": "symbol", "description": "UniProt protein symbol" }, { "name": "name", "description": "protein name" }, { "name": "protein_type", "description": "protein type(Leading protein, Spectrum same-set protein Spectrum sub-set protein, Spectrum subsumable protein)" }, { "name": "pep_count", "description": "identified peptide count" }, { "name": "psm_count", "description": "peptide from psm(peptide specrum match) count" }, { "name": "uniq_pep_count", "description": "unique peptide count" } ] }, { "path": "en\/jpostdb\/data-2.html", "name": "PSM peptide data", "database_name": "jPOST database", "doi": "10.18908\/lsdba.nbdc01594-02-002", "description": "Peptide data from protein spectrum match.", "files": [ { "file_name": "jpostdb_psm.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpostdb\/LATEST\/jpostdb_psm.zip", "file_size": "64.6MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpostdb_psm", "data_acquisition": "protein spectrum match", "analysis": "", "data_number": "4936877", "details": [ { "name": "psm_id", "description": "Internal PSM ID" }, { "name": "sequence", "description": "peptide sequence" }, { "name": "accession", "description": "UniProt ID" }, { "name": "exp_mz", "description": "M\/Z value(ratio between mass m and chage z) obtained by experiment" }, { "name": "calc_mz", "description": "M\/Z value(ratio between mass m and chage z) value obtained by calculation" }, { "name": "charge", "description": "charge" }, { "name": "jpost_score", "description": "jPOST score" } ] }, { "path": "en\/jpostdb\/data-3.html", "name": "PSM peptide modification", "database_name": "jPOST database", "doi": "10.18908\/lsdba.nbdc01594-02-003", "description": "Modification data of PSM peptide", "files": [ { "file_name": "jpostdb_psm_modification.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpostdb\/LATEST\/jpostdb_psm_modification.zip", "file_size": "3035177" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpostdb_psm_modification", "data_acquisition": "protein spectrum match", "analysis": "", "data_number": "3035177", "details": [ { "name": "psm_id", "description": "Internal PSM ID" }, { "name": "modification", "description": "modification type" }, { "name": "site", "description": "modification site" }, { "name": "position", "description": "position in peptide sequence" } ] }, { "path": "en\/jpostdb\/data-4.html", "name": "jPOST database RDF", "database_name": "jPOST database", "doi": "10.18908\/lsdba.nbdc01594-02-004", "description": "jPOST database in RDF format. See https:\/\/rdfportal.org\/dataset\/jpost about RDF schema.", "files": [], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/jpost\/data-1.html", "name": "Metadata", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-000.V002", "description": "The main body of jPOST repository metadata", "files": [ { "file_name": "jpost_metadata.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_metadata.zip", "file_size": "80 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_metadata#en", "data_acquisition": "", "analysis": "", "data_number": "334 entries", "details": [ { "name": "jPOST ID", "description": "Project ID" }, { "name": "PXID", "description": "ProtemoeXchange (PX) ID" }, { "name": "Project title", "description": "Project title" }, { "name": "Keywords", "description": "Keywords" }, { "name": "Description", "description": "Description" }, { "name": "Mode", "description": "Data analysis mode (\"Complete\" or \"Partial\")" }, { "name": "PubMed ID(s)", "description": "PubMed ID(s) if articles are published" }, { "name": "PubMed Info", "description": "References if articles are published" }, { "name": "Principal investigator", "description": "Principal investigator" }, { "name": "Created date", "description": "Data registration date" }, { "name": "Announcement date", "description": "Data publication date" }, { "name": "Note", "description": "Note" }, { "name": "Contact", "description": "Contact" }, { "name": "Revision", "description": "Revision" }, { "name": "Files", "description": "Registered file list (Only simple search)" } ] }, { "path": "en\/jpost\/data-2.html", "name": "File list", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-001.V002", "description": "The list of files registered in jPOST repository", "files": [ { "file_name": "jpost_file_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_file_list.zip", "file_size": "414 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_file_list#en", "data_acquisition": "", "analysis": "", "data_number": "36,143 entries", "details": [ { "name": "jPOST ID", "description": "Project ID" }, { "name": "File ID", "description": "File ID" }, { "name": "File Name", "description": "File Name" }, { "name": "Download", "description": "Download link (Only simple search)" }, { "name": "File size", "description": "File size" }, { "name": "Profiles", "description": "The list of profiles in this file (Only simple search)" } ] }, { "path": "en\/jpost\/data-3.html", "name": "Profile list", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-003.V002", "description": "The list of expeerimental profiles such as sample or enzymes etc.\r\nIt is refered from \"metadata\".", "files": [ { "file_name": "jpost_profile_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_profile_list.zip", "file_size": "236 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_profile_list#en", "data_acquisition": "", "analysis": "", "data_number": "55,403 entries", "details": [ { "name": "jPOST ID", "description": "Project ID" }, { "name": "File ID", "description": "File ID" }, { "name": "Profile plex", "description": "Profile name" }, { "name": "Sample - ID", "description": "Sample ID" }, { "name": "Sample - Title", "description": "Sample name" }, { "name": "Fractionation - ID", "description": "Fractionation ID" }, { "name": "Fractionation - Title", "description": "Fractionation name" }, { "name": "Enzyme\/Mod. - ID", "description": "Enzyme\/Mod. reaction ID" }, { "name": "Enzyme\/Mod. - Title", "description": "Enzyme\/Mod. reaction name" }, { "name": "MS mode - ID", "description": "MS mode ID" }, { "name": "MS mode - Title", "description": "MS mode name" } ] }, { "path": "en\/jpost\/data-4.html", "name": "Sample list", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-004.V002", "description": "The list of experimental samples It is refered from \"profile list\".", "files": [ { "file_name": "jpost_sample_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_sample_list.zip", "file_size": "21 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_sample_list#en", "data_acquisition": "", "analysis": "", "data_number": "989 entries", "details": [ { "name": "ID", "description": "Sample ID" }, { "name": "Title", "description": "Sample name" }, { "name": "Species", "description": "Species" }, { "name": "Tissue", "description": "Tissue" }, { "name": "Cell type", "description": "Cell type" }, { "name": "Disease", "description": "Disease" }, { "name": "Note", "description": "Note" } ] }, { "path": "en\/jpost\/data-5.html", "name": "Fractionation list", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-005.V002", "description": "The list of fractionations It is refered from \"profile list\".", "files": [ { "file_name": "jpost_fractionation_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_fractionation_list.zip", "file_size": "13 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_fractionation_list#en", "data_acquisition": "", "analysis": "", "data_number": "280 entries", "details": [ { "name": "ID", "description": "Fractionation ID" }, { "name": "Title", "description": "Fractionation name" }, { "name": "Subcellular", "description": "Subcellular" }, { "name": "Protein", "description": "Protein" }, { "name": "Peptide", "description": "Peptide" }, { "name": "Note", "description": "Note" } ] }, { "path": "en\/jpost\/data-6.html", "name": "Enzyme\/Mod. List", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-006.V002", "description": "The list of enzyme\/mod.\r\nIt is refered from \"profile list\".", "files": [ { "file_name": "jpost_enzyme_mod_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_enzyme_mod_list.zip", "file_size": "7.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_enzyme_mod_list#en", "data_acquisition": "", "analysis": "", "data_number": "245 entries", "details": [ { "name": "ID", "description": "Enzyme\/Mod. reaction ID" }, { "name": "Title", "description": "Enzyme\/Mod. reaction name" }, { "name": "Enzyme", "description": "Enzyme" }, { "name": "Fixed modification", "description": "Modification prepared before the experiment" }, { "name": "Variable modification", "description": "Other modifications" }, { "name": "Taxonomy", "description": "Taxonomy" }, { "name": "Note", "description": "Note" } ] }, { "path": "en\/jpost\/data-7.html", "name": "MS mode List", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-007.V002", "description": "The list of MS mode It is refered from \"profile list\".", "files": [ { "file_name": "jpost_ms_mode_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpost\/LATEST\/jpost_ms_mode_list.zip", "file_size": "6.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jpost_ms_mode_list#en", "data_acquisition": "", "analysis": "", "data_number": "231 entries", "details": [ { "name": "ID", "description": "MS mode ID" }, { "name": "Title", "description": "MS mode name" }, { "name": "Instrument", "description": "Instrument" }, { "name": "Instrument mode", "description": "Instrument mode" }, { "name": "Purpose", "description": "Purpose" }, { "name": "Quantification platform", "description": "Quantification platform" }, { "name": "Plex", "description": "Plex" }, { "name": "Label", "description": "Label" }, { "name": "Note", "description": "Note" } ] }, { "path": "en\/jpost\/data-8.html", "name": "Data directory", "database_name": "jPOST repository", "doi": "10.18908\/lsdba.nbdc01594-008.V002", "description": "Data registered in jPOST and published. Those contain mass spectrometry (MS) raw data, peak lists, analyzed data and metadata etc.", "files": [ { "file_name": "jpostrepos", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/jpostrepos\/", "file_size": "11 TB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "36,333 files", "details": [] }, { "path": "en\/jsnp\/data-1.html", "name": "Polymorphism Sequence", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-001", "description": "Information on polymorphisms (SNPs and insertions\/deletions) and their flanking sequences\r\nDerived from \"Flat files\" ftp:\/\/ftp.hgc.jp\/pub\/hgc\/db\/snp\/imsSNP140508.fas and ftp:\/\/ftp.hgc.jp\/pub\/hgc\/db\/snp\/imsIND140508.fas", "files": [ { "file_name": "jsnp_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_seq.zip", "file_size": "10.6 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jsnp_seq#en", "data_acquisition": "From \"Screening Information\"", "analysis": "", "data_number": "197,195 entries", "details": [ { "name": "Database Name", "description": "database name\r\nJSNP_SNP: single nucleotide polymorphism\r\nJSNP_InsDel_IND: insertion\/deletion\r\nJSNP_InsDel_MIC: microsatelite" }, { "name": "JSNP ID", "description": "JSNP ID\r\nID starting with IMS-JST: from IMS and JST\r\nID starting with ssj: from RIKEN SNP Research Center or from Tokyo Women's Medical University" }, { "name": "Allele Frequency", "description": "(only in SimpleSearch pages) link to Allele Frequency of the same JSNP ID" }, { "name": "Screening Information", "description": "(only in SimpleSearch pages) link to Screening Information of the same JSNP ID" }, { "name": "Mapping Information", "description": "(only in SimpleSearch pages) link to Mapping Information of the same JSNP ID" }, { "name": "Integrated List", "description": "(only in SimpleSearch pages) link to Integrated List of the same JSNP ID" }, { "name": "dbSNP ss#", "description": "dbSNP ss (submitted SNP) number assigned" }, { "name": "dbSNP rs#", "description": "dbSNP rs (reference SNP) number assigned" }, { "name": "5' Flanking Sequence", "description": "5' flanking sequence" }, { "name": "Observed", "description": "allele observed" }, { "name": "3' Flanking Sequence", "description": "3' flanking sequence" }, { "name": "Offset in Flanking Sequence", "description": "position of the polymorphism in the flanking sequence" }, { "name": "Total Length", "description": "total length of the flanking sequence" }, { "name": "Accession No.", "description": "accession No. of the sequence for polymorphism screening" }, { "name": "Offset in Record", "description": "position of the polymorphism in the sequence for polymorphism screening" }, { "name": "Comment Type", "description": "1: the polymorphism overlaps with a repetitive sequence\r\n2: the flanking sequence overlaps with a repetitive sequence" }, { "name": "Gene Symbol", "description": "gene where the polymorphism is found\r\n(information from LocusLink, GenBank and Unigene)" }, { "name": "JSNP previous ID", "description": "JSNP previous ID\r\n(IDs of IMS-JST104817 to IMS-JST105472 and IMS-JST075266 to IMS-JST075585 are reassigned with ssj IDs)" }, { "name": "JSNP reference ID", "description": "JSNP reference ID\r\n(where multiple JSNP IDs are assigned to the same polymorphism)" } ] }, { "path": "en\/jsnp\/data-2.html", "name": "Allele Frequency", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-002", "description": "Polymorphism allele frequencies in Japanese.\r\nOut of 84651 polymorphisms, 13 and 39 SNPs are assayed in three (POP_*) and two (RIKEN_japanese_*) panels, respectively.\r\nDerived from \"Flat files\" ftp:\/\/ftp.hgc.jp\/pub\/hgc\/db\/snp\/alleleFreq140508.txt", "files": [ { "file_name": "jsnp_allele_freq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_allele_freq.zip", "file_size": "1.4 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jsnp_allele_freq#en", "data_acquisition": "Multiplex PCR were done using the same primers as those for polymorphism screening, and templates from Japanese shown in Panel_ID description. Genotypes were determined with the invader assay (JBIC-allele and RIKEN_japanese_*), TaqMan assay (RIKEN-allele) or direct sequencing \/ allelic discrimination chemistries \/ restriction enzyme genotyping (POP_*).", "analysis": "", "data_number": "84,716 entries", "details": [ { "name": "JSNP ID", "description": "JSNP ID" }, { "name": "Panel_ID", "description": "ID of the pool of Japanese individuals where the frequency was examined\r\n- JBIC-allele - 752 anonymous unrelated Japanese volunteers\r\n- RIKEN-allele - 893 anonymous unrelated Japanese volunteers\r\n- POP_102 - 144 unrelated Japanese volunteers with rheumatoid arthritis under informed consent\r\n- POP_103 - 16 unrelated Japanese volunteers with adult-onset Still's disease under informed consent\r\n- POP_104 - 92 healthy unrelated Japanese volunteers under informed consent\r\n- RIKEN_japanese_normal_weight - 711 unrelated japanese normal weight volunteers ( body mass index = 30kg\/m2 )" }, { "name": "dbSNP ss#", "description": "dbSNP ss (submitted SNP) number assigned" }, { "name": "dbSNP rs#", "description": "dbSNP rs (reference SNP) number assigned" }, { "name": "allele-1", "description": "allele-1" }, { "name": "allele-2", "description": "allele-2" }, { "name": "allele-1 frequency", "description": "allele-1 frequency" }, { "name": "allele-2 frequency", "description": "allele-2 frequency" }, { "name": "the number of chromosomes examined", "description": "the number of chromosomes where the frequency was examined (sample size)" } ] }, { "path": "en\/jsnp\/data-3.html", "name": "Screening Information", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-003", "description": "Information from polymorphism screening experiments.\r\nDerived from \"Each Type of variation Found in Location in Gene\" in \"Data Contributions\" http:\/\/snp.ims.u-tokyo.ac.jp\/data_roots.html .", "files": [ { "file_name": "jsnp_screen.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_screen.zip", "file_size": "15.6 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jsnp_screen#en", "data_acquisition": "Exons, promotor regions and introns selected from human genomic sequences in GenBank and RefSeq were PCR amplified using DNA from 24 (IMS-JST), 48 (RIKEN) or 40 (TJWU) individuals as templates, and sequenced with capillary sequencers.", "analysis": "PolyPhred was used to assist verification of SNPs by eye inspection.", "data_number": "197,195 entries", "details": [ { "name": "JSNP ID", "description": "JSNP ID" }, { "name": "In Gene", "description": "type of gene region where the polymorphism\r\n- promoter*1: annotated in GenBank entries\r\n- promoter*2: predicted by GENSCAN\r\n- promoter*3: putative promoter (1.5kb upstream of the initiation position of mRNA records in the RefSeq)\r\n- CDS*1: annotated in GenBank entries either positively or passively\r\n- CDS*2: predicted by GENSCAN\r\n- CDS*3: extracted by homology search with cDNA\r\n- exon*1: annotated in GenBank entries either positively or passively\r\n- exon*3: extracted by homology search with mRNA\/cDNA\/Unigene records\r\n- intron*1: annotated in GenBank entries or intervened by Exon*1 and CDS*1\r\n- intron*2: intervened by CDS*2\r\n- intron*3: intervened by exon*3 and CDS*3\r\n- others: surrounding regions of genes" }, { "name": "Type", "description": "type of polymorphisms\r\n- SNP: single nucleotide polymorphism\r\n- IND: insertion\/deletion\r\n- MIC: microsatelite" }, { "name": "Frequencies", "description": "minor allele frequencies in dbSNP; number in brackets means JSNP original allele frequency" }, { "name": "allele", "description": "allele observed" }, { "name": "dbSNP ss#", "description": "dbSNP ss (submitted SNP) number assigned" }, { "name": "dbSNP rs#", "description": "dbSNP rs (reference SNP) number assigned" }, { "name": "HGVbase-ID", "description": "ID in HGCbase" }, { "name": "5' assay", "description": "5' flanking sequence" }, { "name": "3' assay", "description": "3' flanking sequence" }, { "name": "Screened Accession", "description": "accession No. of the sequence for polymorphism screening" }, { "name": "Screened Position", "description": "position of the polymorphism in the sequence for polymorphism screening" }, { "name": "Screened Symbol", "description": "gene name related to the sequence for polymorphism screening" }, { "name": "Screened OMIM-ID", "description": "OMIM ID related to the sequence for polymorphism screening" } ] }, { "path": "en\/jsnp\/data-4.html", "name": "Mapping Information", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-004", "description": "Information from mapping polymorphisms on the genome.\r\nDerived from \"Dump JSNP\" http:\/\/snp.ims.u-tokyo.ac.jp\/map\/cgi-bin\/Dump\/snp_region_filter.cgi .", "files": [ { "file_name": "jsnp_dump.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_dump.zip", "file_size": "24 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jsnp_dump#en", "data_acquisition": "From \"Screening Information\" and \"Allele Frequency\"", "analysis": "The location of the SNPs are mapped to the RefSeq （GRCh37） contig sequence, masked by MaskerAid, using BLAST with the SNP flanking sequence, after e-PCR preformed with the primers for amplification to extract their screened regions.", "data_number": "980,939 entries", "details": [ { "name": "snp_id", "description": "ID of JSNP" }, { "name": "snp_type", "description": "snp type: SNP or IND (insertion\/deletion)" }, { "name": "5_flank_seq", "description": "5'-flanking sequence of the snp" }, { "name": "na_var", "description": "nucleic acids variation" }, { "name": "3_flank_seq", "description": "3'-flanking sequence of the snp" }, { "name": "for_primer", "description": "forward primer sequence for e-PCR" }, { "name": "back_primer", "description": "backward primer sequence" }, { "name": "product_size", "description": "PCR product size" }, { "name": "freq_minor", "description": "minor allele frequency of the snp (-1: no frequency information) from JSNP" }, { "name": "freq_major", "description": "major allele frequency of the snp from JSNP" }, { "name": "chr", "description": "chromosome number that the snp is mapped" }, { "name": "chr_start", "description": "start position of the snp in the chromosome" }, { "name": "chr_end", "description": "end position of the snp in the chromosome" }, { "name": "chr_direct", "description": "direction of the flanking sequences against the chromosome" }, { "name": "contig_acc", "description": "ACC of genomic contig (RefSeq NT) that the snp is mapped" }, { "name": "contig_start", "description": "start position of the snp in the genomic contig" }, { "name": "contig_end", "description": "end position of the snp in the genomic contig" }, { "name": "contig_direct", "description": "direction of the flanking sequences against the genomic contig" }, { "name": "hit_count", "description": "number of hit (mapped positions of the snp against genome)" }, { "name": "gene_na_acc", "description": "ACC of a gene (RefSeq NM\/XM) that the snp is mapped" }, { "name": "gene_aa_acc", "description": "ACC of the gene (RefSeq NP\/XP) that the snp is mapped" }, { "name": "symbol", "description": "symbol of gene that the snp is mapped" }, { "name": "locus_id", "description": "ID of gene (LocusLink) that the snp is mapped" }, { "name": "gene_direct", "description": "direction of the flanking sequences against the direction of the gene:\r\nif the directions of the flanking sequences and of the gene are the same, this is \"+\"; otherwise \"-\"." }, { "name": "str_type", "description": "gene structure that the snp is mapped: CDS, exon, intron, 5'-UTR, 3'-UTR" }, { "name": "aa_var", "description": "amino acids variation" }, { "name": "codon_var", "description": "codon variation" }, { "name": "codon_posi", "description": "snp postion in the codon" }, { "name": "dbsnp_rs_id", "description": "dbSNP rs (reference SNP) number assigned" }, { "name": "dbsnp_ss_id", "description": "dbSNP ss (submitted SNP) number assigned" } ] }, { "path": "en\/jsnp\/data-5.html", "name": "Integrated List", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-005", "description": "List of data from \"Mapping Information\" and \"Screening Information\" put together every polymorphism (unless the polymorphism is mapped on two or more chromosomes).\r\nDerived from \"Show List by Chromosome\" of \"Show List of SNPs\" http:\/\/snp.ims.u-tokyo.ac.jp\/search_list.html .", "files": [ { "file_name": "jsnp_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_list.zip", "file_size": "17.9 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/jsnp_list#en", "data_acquisition": "From \"Screening Information\" and\"Mapping Information\"", "analysis": "", "data_number": "198,236 entries", "details": [ { "name": "JSNP ID", "description": "JSNP ID" }, { "name": "Chromosome", "description": "Chromosome number" }, { "name": "Location", "description": "cytogenetic band" }, { "name": "Evidence of Location", "description": "information source of cytogenic band\r\n- GenBank \"\/chromosome\" and \"\/map\"\r\n- EntrezGene \"CHR\" and \"MAP\"\r\n- UniGene \"CHROMOSOME\" and \"CYTOBAND\"" }, { "name": "In Gene", "description": "Type of gene region\r\n- promoter*1: Annotated in GenBank entries\r\n- promoter*2: Predicted by GENSCAN\r\n- promoter*3: Putative promoter (1.5kb upstream of the initiation position of mRNA records in the RefSeq)\r\n- CDS*1: Annotated in GenBank entries either positively or passively\r\n- CDS*2: Predicted by GENSCAN\r\n- CDS*3: Extracted by homology search with cDNA\r\n- exon*1: Annotated in GenBank entries either positively or passively\r\n- exon*3: Extracted by homology search with mRNA\/cDNA\/Unigene records\r\n- intron*1: Annotated in GenBank entries or intervened by Exon*1 and CDS*1\r\n- intron*2: Intervened by CDS*2\r\n- intron*3: Intervened by exon*3 and CDS*3\r\n- others: surrounding regions of genes" }, { "name": "Type", "description": "type of polymorphisms\r\n- SNP: single nucleotide polymorphism\r\n- IND: insertion\/deletion\r\n- MIC: microsatelite" }, { "name": "Frequencies", "description": "minor allele frequencies in dbSNP, number in brackets means JSNP original allele frequency" }, { "name": "allele", "description": "allele observed" }, { "name": "dbSNP ss#", "description": "dbSNP ss (submitted SNP) number assigned" }, { "name": "dbSNP rs#", "description": "dbSNP rs (reference SNP) number assigned" }, { "name": "HGVBase-ID", "description": "ID in HGCbase" }, { "name": "5' assay", "description": "5' flanking sequence" }, { "name": "3' assay", "description": "3' flanking sequence" }, { "name": "Mapping Accession", "description": "accession No. of the mapped sequence" }, { "name": "Mapping Position", "description": "position of the polymorphism in the mapped sequence" }, { "name": "Mapping Symbol", "description": "gene name relevant to the mapped sequence" }, { "name": "Mapping OMIM-ID", "description": "OMIM ID relevant to the mapped sequence" }, { "name": "Screened Accession", "description": "accession No. of the sequence for polymorphism screening" }, { "name": "Screened Position", "description": "position of the polymorphism in the sequence for polymorphism screening" }, { "name": "Screened Symbol", "description": "gene name relevant to the sequence for polymorphism screening" }, { "name": "Screened OMIM-ID", "description": "OMIM ID relevant to the sequence for polymorphism screening" } ] }, { "path": "en\/jsnp\/data-6.html", "name": "Flat Files", "database_name": "JSNP", "doi": "10.18908\/lsdba.nbdc00114-006", "description": "Information on polymorphisms (SNPs and insertions\/deletions) and their flanking sequences, and polymorphism allele frequencies in Japanese.\r\nProvided as \"Flat files\" ftp:\/\/ftp.hgc.jp\/pub\/hgc\/db\/snp\/ .", "files": [ { "file_name": "jsnp_flat_files", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/jsnp\/LATEST\/jsnp_flat_files\/", "file_size": "128 MB" } ], "togodb_url": "", "data_acquisition": "Equivalent to \"Polymorphism Sequence\" and \"Allele Frequency\" .", "analysis": "", "data_number": "11 files", "details": [] }, { "path": "en\/kaiko-cdna\/data-1.html", "name": "EST Table", "database_name": "KAIKOcDNA", "doi": "10.18908\/lsdba.nbdc00951-001", "description": "List of silkworm ESTs (cDNAs) consisting of publicly available data in addition to sequences registered to public database as of September 2011.", "files": [ { "file_name": "kaiko_cdna_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko-cdna\/LATEST\/kaiko_cdna_main.zip", "file_size": "157 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_cdna_main#en", "data_acquisition": "", "analysis": "Each EST was annotated by homology search (BLAST) against six protein databases. ESTs were grouped based on all-against-all BLASTN. For each cluster (group), a representative sequence was chosen, which contains the most upstream region between contigs in each cluster. Each representative sequence was annotated by InterProScan.", "data_number": "532,655 entries", "details": [ { "name": "Accession Number", "description": "Accession number of EST" }, { "name": "Clone Name", "description": "Clone name of EST" }, { "name": "Length", "description": "Sequence length (bp)" }, { "name": "GO check_date", "description": "Date of InterProScan run" }, { "name": "GO Iprscan Value", "description": "Link to result of InterProScan" }, { "name": "GO ID", "description": "Assigned GO IDs" }, { "name": "NR blast_date", "description": "Date of BLAST search (DB: NCBI nr)" }, { "name": "NR value", "description": "Result of BLAST search (DB: NCBI nr)" }, { "name": "NR definition", "description": "Definition of homologous sequence (DB: NCBI nr)" }, { "name": "Drosophila blast_date", "description": "Date of BLAST search (DB: D. melanogaster proteins)" }, { "name": "Drosophila value", "description": "Result of BLAST search (DB: D. melanogaster proteins)" }, { "name": "Drosophila definition", "description": "Definition of homologous sequence (DB: D. melanogaster proteins)" }, { "name": "C.elegans blast_date", "description": "Date of BLAST search (DB: C.elegans proteins)" }, { "name": "C.elegans value", "description": "Result of BLAST search (DB: C.elegans proteins)" }, { "name": "C.elegans definition", "description": "Definition of homologous sequence (DB: C.elegans proteins)" }, { "name": "Anopheles blast_date", "description": "Date of BLAST search (DB: A. gambiae proteins)" }, { "name": "Anopheles value", "description": "Result of BLAST search (DB: A. gambiae proteins)" }, { "name": "Anopheles definition", "description": "Definition of homologous sequence (DB: Anopheles)" }, { "name": "Apis blast_date", "description": "Date of BLAST search (DB: A. mellifera proteins)" }, { "name": "Apis value", "description": "Result of BLAST search (DB: A. mellifera proteins)" }, { "name": "Apis definition", "description": "Definition of homologous sequence (DB: A. mellifera proteins)" }, { "name": "Tribolium blast_date", "description": "Date of BLAST search (DB: T. castaneum proteins)" }, { "name": "Tribolium value", "description": "Result of BLAST search (DB: T. castaneum proteins)" }, { "name": "Tribolium definition", "description": "Definition of homologous sequence (DB: T. castaneum proteins)" }, { "name": "Cluster Size", "description": "Number of sequences in cluster" }, { "name": "Rep ID", "description": "Accession number of the representative sequence" }, { "name": "cDNA library name", "description": "cDNA library name" }, { "name": "Sequence", "description": "Sequence" } ] }, { "path": "en\/kaiko-cdna\/data-2.html", "name": "Cluster Table", "database_name": "KAIKOcDNA", "doi": "10.18908\/lsdba.nbdc00951-002", "description": "List of number of identical cDNA sequences that make up cluster.", "files": [ { "file_name": "kaiko_cdna_cluster.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko-cdna\/LATEST\/kaiko_cdna_cluster.zip", "file_size": "453 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_cdna_cluster#en", "data_acquisition": "EST Table data", "analysis": "The clones those sequences have more than 95% identity each other in a region over 100bp were considered to be the same cluster. Number of clones which belong to each cluster was classified in every cDNA library.", "data_number": "59,729 entries", "details": [ { "name": "Rep ID", "description": "Accession number of the representative EST of each cluster" }, { "name": "Cluster Size", "description": "Number of total clones in each cluster" }, { "name": "an--", "description": "Number of identical clones (cDNA library an--)" }, { "name": "bmmt", "description": "Number of identical clones (cDNA library bmmt)" }, { "name": "bmov", "description": "Number of identical clones (cDNA library bmov)" }, { "name": "bmte", "description": "Number of identical clones (cDNA library bmte)" }, { "name": "BmN-", "description": "Number of identical clones (cDNA library BmN-)" }, { "name": "br--", "description": "Number of identical clones (cDNA library br--)" }, { "name": "brP-", "description": "Number of identical clones (cDNA library brP-)" }, { "name": "brS-", "description": "Number of identical clones (cDNA library brS-)" }, { "name": "caL-", "description": "Number of identical clones (cDNA library caL-)" }, { "name": "ce--", "description": "Number of identical clones (cDNA library ce--)" }, { "name": "ceN-", "description": "Number of identical clones (cDNA library ceN-)" }, { "name": "cesb", "description": "Number of identical clones (cDNA library cesb)" }, { "name": "dpe-", "description": "Number of identical clones (cDNA library dpe-)" }, { "name": "e100", "description": "Number of identical clones (cDNA library e100)" }, { "name": "e4", "description": "Number of identical clones (cDNA library e4)" }, { "name": "e96h", "description": "Number of identical clones (cDNA library e96h)" }, { "name": "epM-", "description": "Number of identical clones (cDNA library epM-)" }, { "name": "epV3", "description": "Number of identical clones (cDNA library epV3)" }, { "name": "F1mg", "description": "Number of identical clones (cDNA library F1mg)" }, { "name": "famL", "description": "Number of identical clones (cDNA library famL)" }, { "name": "fbf", "description": "Number of identical clones (cDNA library fbf)" }, { "name": "fbm", "description": "Number of identical clones (cDNA library fbm)" }, { "name": "fbpv", "description": "Number of identical clones (cDNA library fbpv)" }, { "name": "fbS2", "description": "Number of identical clones (cDNA library fbS2)" }, { "name": "fcaL", "description": "Number of identical clones (cDNA library fcaL)" }, { "name": "fcP8", "description": "Number of identical clones (cDNA library fcP8)" }, { "name": "fe8d", "description": "Number of identical clones (cDNA library fe8d)" }, { "name": "ffbm", "description": "Number of identical clones (cDNA library ffbm)" }, { "name": "FJsb", "description": "Number of identical clones (cDNA library FJsb)" }, { "name": "fmgV", "description": "Number of identical clones (cDNA library fmgV)" }, { "name": "fner", "description": "Number of identical clones (cDNA library fner)" }, { "name": "ftes", "description": "Number of identical clones (cDNA library ftes)" }, { "name": "fufe", "description": "Number of identical clones (cDNA library fufe)" }, { "name": "fwgP", "description": "Number of identical clones (cDNA library fwgP)" }, { "name": "heS0", "description": "Number of identical clones (cDNA library heS0)" }, { "name": "heS3", "description": "Number of identical clones (cDNA library heS3)" }, { "name": "J150", "description": "Number of identical clones (cDNA library J150)" }, { "name": "JFsb", "description": "Number of identical clones (cDNA library JFsb)" }, { "name": "maV3", "description": "Number of identical clones (cDNA library maV3)" }, { "name": "MFB-", "description": "Number of identical clones (cDNA library MFB-)" }, { "name": "mg", "description": "Number of identical clones (cDNA library mg)" }, { "name": "msgV", "description": "Number of identical clones (cDNA library msgV)" }, { "name": "MSV3", "description": "Number of identical clones (cDNA library MSV3)" }, { "name": "mxg-", "description": "Number of identical clones (cDNA library mxg-)" }, { "name": "n", "description": "Number of identical clones (cDNA library n)" }, { "name": "Nnor", "description": "Number of identical clones (cDNA library Nnor)" }, { "name": "NRPG", "description": "Number of identical clones (cDNA library NRPG)" }, { "name": "NV02", "description": "Number of identical clones (cDNA library NV02)" }, { "name": "NV06", "description": "Number of identical clones (cDNA library NV06)" }, { "name": "NV12", "description": "Number of identical clones (cDNA library NV12)" }, { "name": "ovS0", "description": "Number of identical clones (cDNA library ovS0)" }, { "name": "ovS3", "description": "Number of identical clones (cDNA library ovS3)" }, { "name": "P5PG", "description": "Number of identical clones (cDNA library P5PG)" }, { "name": "pg--", "description": "Number of identical clones (cDNA library pg--)" }, { "name": "phe-", "description": "Number of identical clones (cDNA library phe-)" }, { "name": "prgv", "description": "Number of identical clones (cDNA library prgv)" }, { "name": "prW-", "description": "Number of identical clones (cDNA library prW-)" }, { "name": "ps4M", "description": "Number of identical clones (cDNA library ps4M)" }, { "name": "psV3", "description": "Number of identical clones (cDNA library psV3)" }, { "name": "PSV3", "description": "Number of identical clones (cDNA library PSV3)" }, { "name": "tesS", "description": "Number of identical clones (cDNA library tesS)" }, { "name": "tesV", "description": "Number of identical clones (cDNA library tesV)" }, { "name": "vg4M", "description": "Number of identical clones (cDNA library vg4M)" }, { "name": "wd--", "description": "Number of identical clones (cDNA library wd--)" }, { "name": "wdV1", "description": "Number of identical clones (cDNA library wdV1)" }, { "name": "wdV3", "description": "Number of identical clones (cDNA library wdV3)" }, { "name": "ws0", "description": "Number of identical clones (cDNA library ws0)" }, { "name": "ws2", "description": "Number of identical clones (cDNA library ws2)" }, { "name": "ws3", "description": "Number of identical clones (cDNA library ws3)" }, { "name": "wv4", "description": "Number of identical clones (cDNA library wv4)" }, { "name": "swa", "description": "Number of identical clones (cDNA library swa)" }, { "name": "swb", "description": "Number of identical clones (cDNA library swb)" }, { "name": "swc", "description": "Number of identical clones (cDNA library swc)" }, { "name": "swd", "description": "Number of identical clones (cDNA library swd)" }, { "name": "swe", "description": "Number of identical clones (cDNA library swe)" }, { "name": "swf", "description": "Number of identical clones (cDNA library swf)" }, { "name": "swg", "description": "Number of identical clones (cDNA library swg)" }, { "name": "swh", "description": "Number of identical clones (cDNA library swh)" }, { "name": "swj", "description": "Number of identical clones (cDNA library swj)" }, { "name": "swk", "description": "Number of identical clones (cDNA library swk)" }, { "name": "swl", "description": "Number of identical clones (cDNA library swl)" }, { "name": "swp", "description": "Number of identical clones (cDNA library swp)" }, { "name": "BmP", "description": "Number of identical clones (cDNA library BmP)" }, { "name": "L1", "description": "Number of identical clones (cDNA library L1)" }, { "name": "L2", "description": "Number of identical clones (cDNA library L2)" }, { "name": "L3", "description": "Number of identical clones (cDNA library L3)" }, { "name": "L4", "description": "Number of identical clones (cDNA library L4)" }, { "name": "L5", "description": "Number of identical clones (cDNA library L5)" }, { "name": "L6", "description": "Number of identical clones (cDNA library L6)" }, { "name": "L7", "description": "Number of identical clones (cDNA library L7)" }, { "name": "L8", "description": "Number of identical clones (cDNA library L8)" }, { "name": "L9", "description": "Number of identical clones (cDNA library L9)" }, { "name": "L10", "description": "Number of identical clones (cDNA library L10)" }, { "name": "L11", "description": "Number of identical clones (cDNA library L11)" }, { "name": "L12", "description": "Number of identical clones (cDNA library L12)" }, { "name": "L13", "description": "Number of identical clones (cDNA library L13)" }, { "name": "L14", "description": "Number of identical clones (cDNA library L14)" }, { "name": "L15", "description": "Number of identical clones (cDNA library L15)" }, { "name": "L16", "description": "Number of identical clones (cDNA library L16)" }, { "name": "Other", "description": "Number of identical clones (other cDNA libraries)" } ] }, { "path": "en\/kaiko-cdna\/data-3.html", "name": "ORF Table", "database_name": "KAIKOcDNA", "doi": "10.18908\/lsdba.nbdc00951-003", "description": "List of open reading frames of the representative ESTs.", "files": [ { "file_name": "kaiko_cdna_orf.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko-cdna\/LATEST\/kaiko_cdna_orf.zip", "file_size": "11 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_cdna_orf#en", "data_acquisition": "EST Table data", "analysis": "", "data_number": "200,077 entries", "details": [ { "name": "Rep ID", "description": "Accession number of the representative EST" }, { "name": "ORF Name", "description": "Name of ORF" }, { "name": "Frame", "description": "Number of Frame" }, { "name": "ORF Number", "description": "Number of ORF" }, { "name": "Threshold", "description": "Threshold of sequence length (including the stop codon)" }, { "name": "Length", "description": "Sequence length (bp)" }, { "name": "Sequence", "description": "Amino acid Sequence" } ] }, { "path": "en\/kaiko-cdna\/data-4.html", "name": "InterProScan Result", "database_name": "KAIKOcDNA", "doi": "10.18908\/lsdba.nbdc00951-004", "description": "List of the result of InterProScan target the representative EST.", "files": [ { "file_name": "kaiko_cdna_interpro.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko-cdna\/LATEST\/kaiko_cdna_interpro.zip", "file_size": "3.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_cdna_interpro#en", "data_acquisition": "ORF Table data", "analysis": "ORFs of the representative ESTs in the clusters were annotated by InterProScan.", "data_number": "112,731 entries", "details": [ { "name": "Rep ID", "description": "Accession number of the representative EST" }, { "name": "ORF Name", "description": "Name of ORF" }, { "name": "CRC64", "description": "Value of CRC64 in each sequence" }, { "name": "Length", "description": "Sequence length (bp)" }, { "name": "Analysis", "description": "Database\/Program used for analysis" }, { "name": "Signature Accession", "description": "Signature accession" }, { "name": "Signature Description", "description": "Signature description" }, { "name": "Start location", "description": "Start location of Motif" }, { "name": "Stop location", "description": "Stop location of Motif" }, { "name": "Score", "description": "E-value of matching score to the functional site sequence" }, { "name": "Status", "description": "Status of match to the functional site sequence (T: match)" }, { "name": "InterPro accession", "description": "Assigned InterPro ID" }, { "name": "InterPro description", "description": "Description of assigned InterPro ID" }, { "name": "GO terms", "description": "Assigned GO terms" } ] }, { "path": "en\/kaiko-cdna\/data-5.html", "name": "cDNA library Table", "database_name": "KAIKOcDNA", "doi": "10.18908\/lsdba.nbdc00951-005", "description": "List of Bombyx mori cDNA libraries.", "files": [ { "file_name": "kaiko_cdna_library.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko-cdna\/LATEST\/kaiko_cdna_library.zip", "file_size": "4.8 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_cdna_library#en", "data_acquisition": "", "analysis": "", "data_number": "99 entries", "details": [ { "name": "Registered library name", "description": "Registered name of the partial cDNA library" }, { "name": "Library synonym", "description": "Another name for cDNA library (original name)" }, { "name": "Local library name", "description": "Local library name" }, { "name": "Strain\/Race", "description": "Strain\/race" }, { "name": "Organ\/Tissue", "description": "Organ \/ tissue" }, { "name": "Developmental stage", "description": "Developmental stage" }, { "name": "Sex", "description": "Sex" }, { "name": "Vector", "description": "Vector" }, { "name": "Cloning sites", "description": "Cloning site" }, { "name": "Sequence direction", "description": "Direction of sequencing" }, { "name": "Accession number", "description": "Range of accession numbers" }, { "name": "Clone name", "description": "Naming rule of clones" }, { "name": "Note", "description": "Note" } ] }, { "path": "en\/kegg-medicus\/data-1.html", "name": "Drug", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-001.V005", "description": "KEGG DRUG is a comprehensive drug information resource for approved drugs in Japan, USA, and Europe unified based on the chemical structures and\/or the chemical components, and associated with target, metabolizing enzyme, and other molecular interaction network information.", "files": [ { "file_name": "kegg_medicus_drug_en.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_drug_en.csv.zip", "file_size": "8.0 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_drug_en", "data_acquisition": "", "analysis": "", "data_number": "11,938 entries", "details": [ { "name": "D number", "description": "Unique identifier of the KEGG DRUG entry." }, { "name": "Classification", "description": "Shown when the drug is Mixture, Crude or Formula." }, { "name": "Name", "description": "The generic name and selected trade names of the drug." }, { "name": "Component", "description": "Component" }, { "name": "Formula", "description": "The molecular formula of the drug structure." }, { "name": "Exact mass", "description": "The exact mass of the drug structure." }, { "name": "Mol weight", "description": "The molecular weight of the drug structure." }, { "name": "Structural formula", "description": "Chemical structural formula. (Simple search only)" }, { "name": "Sequence", "description": "Sequence data when the drug is a peptide or a polyketide." }, { "name": "Sequence type", "description": "Sequence type (NRP, PK, Peptide)." }, { "name": "Source", "description": "Biological source when the drug is derived from a natural product." }, { "name": "Upper DGroup", "description": "Upper DGroup." }, { "name": "Remark", "description": "This field contains Therapeutic category, ATC code, and also identical entries in the COMPOUND database." }, { "name": "Efficacy", "description": "Efficacy and activity of the drug." }, { "name": "Disease", "description": "The desease healed by the drug." }, { "name": "Comment", "description": "Free text comment." }, { "name": "Target", "description": "Target information of the drug with appropriate links to human genes and KEGG Orthology." }, { "name": "Metabolism", "description": "Information about drug metabolizing enzyme and transporter." }, { "name": "Interaction", "description": "Other interaction information, including CYP induction and inhibition, genomic biomarkers, etc." }, { "name": "Other DBs", "description": "Links to outside databases." }, { "name": "KCF data", "description": "The KCF (KEGG Chemical Function) representation of the chemical structure can be displayed here. It contains the KEGG atom type information for use in chemical structure comparisons." } ] }, { "path": "en\/kegg-medicus\/data-2.html", "name": "Environ", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-002.V005", "description": "KEGG ENVIRON is a collection of crude drugs, essential oils, and other health-promoting substances, which are mostly natural products. KEGG ENVIRON supplements KEGG DRUG that contains officially approved drugs.", "files": [ { "file_name": "kegg_medicus_environ_en.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_environ_en.csv.zip", "file_size": "73.2 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_environ_en", "data_acquisition": "", "analysis": "", "data_number": "850 entries", "details": [ { "name": "E number", "description": "Unique identifier of the KEGG ENVIRON entry." }, { "name": "Name", "description": "Name of the natural product." }, { "name": "Category", "description": "Category (Crude drug, Essential oil or Medicinal herb)." }, { "name": "Component", "description": "Chemical components and corresponding C\/D numbers." }, { "name": "Source", "description": "Biological source with links to NCBI taxonomy IDs." }, { "name": "Remark", "description": "D number of the same crude drug, etc. when available." }, { "name": "Comment", "description": "Free text comment." }, { "name": "Other DBs", "description": "Links to outside databases." } ] }, { "path": "en\/kegg-medicus\/data-3.html", "name": "Disease", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-003.V005", "description": "The KEGG DISEASE database is a collection of human diseases, each represented as a list of disease genes, environmental factors, pathogens, etc. with links to corresponding KEGG objects, thus enabling computational processing and analysis of disease data.", "files": [ { "file_name": "kegg_medicus_disease_en.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_disease.csv.zip", "file_size": "2.8 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_disease_en", "data_acquisition": "", "analysis": "", "data_number": "2,577 entries", "details": [ { "name": "H number", "description": "Unique identifier of the KEGG DISEASE entry." }, { "name": "Name", "description": "Disease names including alternative names." }, { "name": "Sub Group", "description": "Sub group of the disease" }, { "name": "Super Group", "description": "Super group of the disease [H number]" }, { "name": "Description", "description": "A brief summary of the disease." }, { "name": "Category", "description": "The category of the disease." }, { "name": "Network", "description": "The network whici contains the disease" }, { "name": "Gene", "description": "Known disease genes with links to the KEGG GENES and KO databases." }, { "name": "Pathogen", "description": "Known pathogens with links to the KEGG GENOME and VGENOME databases." }, { "name": "Env factor", "description": "Known other environmental factors with links to the KEGG COMPOUND and other databases." }, { "name": "Carcinogen", "description": "Known carcinogens with links to the KEGG COMPOUND and other databases." }, { "name": "Drug", "description": "Typical therapeutic drugs with links to the KEGG DRUG database." }, { "name": "Comment", "description": "Free text comment." }, { "name": "Other DBs", "description": "Links to outside databases." }, { "name": "Reference", "description": "Reference information." } ] }, { "path": "en\/kegg-medicus\/data-4.html", "name": "DGroup", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-004.V005", "description": "KEGG DGROUP is a database for structurally and functionally related groups of drugs, especially from the viewpoint of drug interaction networks.", "files": [ { "file_name": "kegg_medicus_dgroup_en.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_dgroup_en.csv.zip", "file_size": "598 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_dgroup_en", "data_acquisition": "", "analysis": "", "data_number": "2,398 entries", "details": [ { "name": "DG number", "description": "Unique identifier of the KEGG DGROUP entry." }, { "name": "Classification", "description": "Shown when the group is \"Chemical\"." }, { "name": "Name", "description": "Name of the DGroup." }, { "name": "Stem", "description": "Stem of drugs in the DGroup." }, { "name": "Structural formula", "description": "Chemical structural formula. (Simple search only)" }, { "name": "Member", "description": "List of drugs and D numbers in the DGroup." }, { "name": "Upper DGroup", "description": "Upper DGroup." }, { "name": "Remark", "description": "ATC code." }, { "name": "Comment", "description": "Free text comment." } ] }, { "path": "en\/kegg-medicus\/data-5.html", "name": "Network", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-004.V005", "description": "KEGG NETWORK is a database to capture knowledge of diseases and drugs in terms of perturbed molecular networks. It accumulates variations of molecular interaction\/reaction networks in terms of \"network variation maps\" consisting of \"network elements\". Each network element is identified by the N number.\r\nIn this archive, \"Network Map\" is divided into another data.", "files": [ { "file_name": "kegg_medicus_network.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_network.csv.zip", "file_size": "615 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_network", "data_acquisition": "", "analysis": "", "data_number": "1,241 entries", "details": [ { "name": "N number", "description": "Unique identifier of the KEGG NETWORK entry (Network)." }, { "name": "Name", "description": "Name of the molecular network." }, { "name": "Definition", "description": "Definition of the molecular network." }, { "name": "Definition expressed by ID", "description": "Above definition is expressed by element ID." }, { "name": "Upper group", "description": "Maps contains the molecular network." }, { "name": "Type", "description": "Molecular network type" }, { "name": "Disease", "description": "Related disease." }, { "name": "Gene", "description": "Genes contained in the molecular network." }, { "name": "Variant", "description": "Variants contained in the molecular network." }, { "name": "Metabolite", "description": "Metabolites contained in the molecular network." }, { "name": "Perturbant", "description": "Perturbants contained in the molecular network." }, { "name": "Reference", "description": "Reference information." } ] }, { "path": "en\/kegg-medicus\/data-6.html", "name": "Network Map", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-006.V005", "description": "KEGG NETWORK is a database to capture knowledge of diseases and drugs in terms of perturbed molecular networks. It accumulates variations of molecular interaction\/reaction networks in terms of \"network variation maps\" consisting of \"network elements\". Each map is identified by the nt number.\r\nIn this archive, \"Network\" is divided into another data.", "files": [ { "file_name": "kegg_medicus_map.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_map.csv.zip", "file_size": "52 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_map", "data_acquisition": "", "analysis": "", "data_number": "133 entries", "details": [ { "name": "nt number", "description": "Unique identifier of the KEGG NETWORK entry (Network Map)." }, { "name": "Name", "description": "Name of the molecular network." }, { "name": "Map name", "description": "Name of the network map." }, { "name": "Disease", "description": "Related disease." }, { "name": "Other DBs", "description": "Links to outside databases." }, { "name": "Member", "description": "Molecular networks contained in the map." } ] }, { "path": "en\/kegg-medicus\/data-7.html", "name": "Variant", "database_name": "KEGG MEDICUS", "doi": "10.18908\/lsdba.nbdc01185-007.V005", "description": "The KEGG VARIANT database is a collection of human gene variants that can be associated with human diseases and drugs. Each variant is identified by the human gene ID followed by \"v\" and a number.", "files": [ { "file_name": "kegg_medicus_variant.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kegg-medicus\/LATEST\/kegg_medicus_variant.csv.zip", "file_size": "195 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kegg_medicus_variant", "data_acquisition": "", "analysis": "", "data_number": "458 entries", "details": [ { "name": "Variant ID", "description": "Unique identifier of the KEGG VARIANT entry." }, { "name": "Name", "description": "Name of the variant." }, { "name": "Gene", "description": "Gene name" }, { "name": "Organism", "description": "Organism" }, { "name": "Variation", "description": "Variation names and links to outside databases." }, { "name": "Map", "description": "Molocular network maps which contain the variant." }, { "name": "Network", "description": "Molocular network which contain the variant." }, { "name": "Reference", "description": "Reference information." } ] }, { "path": "en\/kome\/data-1.html", "name": "Main", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-001", "description": "List of datasets", "files": [ { "file_name": "kome_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_main.zip", "file_size": "1.3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_main#en", "data_acquisition": "", "analysis": "", "data_number": "33 entries", "details": [ { "name": "Category", "description": "Category of the dataset" }, { "name": "Title", "description": "Title of the dataset" }, { "name": "Description", "description": "Description of the dataset" }, { "name": "Sequence data file", "description": "Name of the fasta file" }, { "name": "Data file (CSV)", "description": "Name of the CSV file" }, { "name": "Data file (TogoDB)", "description": "Name of the dataset on Simple search website (TogoDB)" } ] }, { "path": "en\/kome\/data-2.html", "name": "Basical information", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-002", "description": "Basic Information about full-length cDNA clones", "files": [ { "file_name": "kome_basical_information.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_basical_information.zip", "file_size": "607 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_basical_information#en", "data_acquisition": "The full-length cDNA clones were sequenced by RIKEN and FAIS.", "analysis": "After an all-against-all Blastn search, clones with Expect values less than 1e-180 were grouped into the same cluster.", "data_number": "37,132 entries", "details": [ { "name": "ACCESSION_NO", "description": "DDBJ accession number of the full-length cDNA clone. All the clones in the database were registered in DDBJ." }, { "name": "CLONE_ID", "description": "ID number assigned to each full-length cDNA clone" }, { "name": "BELONG", "description": "Initial of the research institute where the clone was sequenced. (R: RIKEN, F: FAIS)" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "CLUSTER_ID", "description": "Cluster ID of the full-length cDNA clone.\r\nCluster IDs were numbered serially." }, { "name": "LENGTH", "description": "Length of the full-length cDNA sequence" }, { "name": "POLYA_CUT_LENGTH", "description": "Length of the full-length cDNA sequence excluding the poly(A) region" }, { "name": "SEQ_QUALITY", "description": "Ratio of non-N residues contained in the full-length cDNA sequence" }, { "name": "POLYA_CUT_SEQ_QUALITY", "description": "Ratio of non-N residues contained in the full-length cDNA sequence excluding the poly(A) region" }, { "name": "SEQ_ACCURACY", "description": "Sequence accuracy calculated as the average of accuracies of individual bases after a sequencing run." }, { "name": "LIBRARY", "description": "Information about the full-length cDNA library, such as tissues which the library derived from and their treatment conditions." } ] }, { "path": "en\/kome\/data-3.html", "name": "Mapping data", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-003", "description": "Mapping information with the japonica rice genome sequences obtained from the International Rice Genome Sequencing Project (IRGSP)", "files": [ { "file_name": "kome_mapping_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_mapping_data.zip", "file_size": "723 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_mapping_data#en", "data_acquisition": "", "analysis": "Mapped the full-length cDNA clones to the japonica rice genome BAC contigs.", "data_number": "30,643 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BAC_ACCESSION_NO", "description": "Accession number of the mapped BAC contigs" }, { "name": "CHROMOSOME", "description": "Chromosome number of the mapped BAC contigs" }, { "name": "BAC_START_POS", "description": "Alignment start position on the mapped BAC contigs" }, { "name": "BAC_END_POS", "description": "Alignment end position on the mapped BAC contigs" }, { "name": "CDNA_START_POS", "description": "Alignment start position on the mapped cDNA clone" }, { "name": "CDNA_END_POS", "description": "Alignment end position on the mapped cDNA clone" }, { "name": "STRAND", "description": "Strand direction of the mapped cDNA clone" }, { "name": "TU_ID", "description": "ID of the mapped TU (Transcriptional Unit)" } ] }, { "path": "en\/kome\/data-4.html", "name": "Mapping data detail", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-004", "description": "Detailed mapping information with the japonica rice genome sequences from the International Rice Genome Sequencing Project (IRGSP)", "files": [ { "file_name": "kome_mapping_data_detail.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_mapping_data_detail.zip", "file_size": "2.3 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_mapping_data_detail#en", "data_acquisition": "", "analysis": "Mapped the full-length cDNA clones to the japonica rice genome BAC contigs.", "data_number": "154,484 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BAC_ACCESSION_NO", "description": "Accession number of the mapped BAC contigs" }, { "name": "CHROMOSOME", "description": "Chromosome number of the mapped BAC contigs" }, { "name": "BAC_START_POS", "description": "Exon start position on the mapped BAC contigs" }, { "name": "BAC_END_POS", "description": "Exon end position on the mapped BAC contigs" }, { "name": "CDNA_START_POS", "description": "Exon start position on the mapped cDNA clone" }, { "name": "CDNA_END_POS", "description": "Exon end position on the mapped cDNA clone" }, { "name": "STRAND", "description": "Strand direction of the mapped cDNA clone" }, { "name": "TU_ID", "description": "ID of the mapped TU (Transcriptional Unit)" } ] }, { "path": "en\/kome\/data-5.html", "name": "Mapping Pseudomolecule data", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-005", "description": "Mapping information with the TIGR japonica Pseudomolecules", "files": [ { "file_name": "kome_mapping_pseudomolecule_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_mapping_pseudomolecule_data.zip", "file_size": "719 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_mapping_pseudomolecule_data#en", "data_acquisition": "", "analysis": "Mapped the full-length cDNA clones to the TIGR japonica Pseudomolecules.", "data_number": "30,892 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "HIT_NUMBER", "description": "Number of the sites where the cDNA clones were mapped" }, { "name": "PSEUDOMOLECULE", "description": "Name of the mapped pseudomolecule" }, { "name": "CHROMOSOME", "description": "Chromosome number of the mapped pseudomolecule" }, { "name": "CHR_START_POS", "description": "Alignment start position on the mapped pseudomolecule" }, { "name": "CHR_END_POS", "description": "Alignment end position on the mapped pseudomolecule" }, { "name": "CDNA_START_POS", "description": "Alignment start position on the mapped cDNA clone" }, { "name": "CDNA_END_POS", "description": "Alignment end position on the mapped cDNA clone" }, { "name": "STRAND", "description": "Strand direction of the mapped cDNA clone" }, { "name": "TU_ID", "description": "ID of the mapped TU (Transcriptional Unit)" } ] }, { "path": "en\/kome\/data-6.html", "name": "Mapping Pseudomolecule data detail", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-006", "description": "Detailed mapping information with the TIGR japonica Pseudomolecules", "files": [ { "file_name": "kome_mapping_pseudomolecule_data_detail.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_mapping_pseudomolecule_data_detail.zip", "file_size": "2.5 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_mapping_pseudomolecule_data_detail#en", "data_acquisition": "", "analysis": "The full-length cDNA clones were mapped to the TIGR japonica Pseudomolecules.", "data_number": "161,654 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "HIT_NUMBER", "description": "Number of the sites where the cDNA clones were mapped" }, { "name": "PSEUDOMOLECULE", "description": "Accession number of the mapped pseudomolecule" }, { "name": "CHROMOSOME", "description": "Chromosome number of the mapped pseudomolecule" }, { "name": "CHR_START_POS", "description": "Exon start position on the mapped pseudomolecule" }, { "name": "CHR_END_POS", "description": "Exon end position on the mapped pseudomolecule" }, { "name": "CDNA_START_POS", "description": "Exon start position on the mapped cDNA clone" }, { "name": "CDNA_END_POS", "description": "Exon end position on the mapped cDNA clone" }, { "name": "STRAND", "description": "Strand direction of the mapped cDNA clone" }, { "name": "TU_ID", "description": "ID of the mapped TU (Transcriptional Unit)" } ] }, { "path": "en\/kome\/data-7.html", "name": "GenBank blastn search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-007", "description": "Results of blastn searches against GenBank nucleotide sequences", "files": [ { "file_name": "kome_genbank_blastn_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_genbank_blastn_search_result.zip", "file_size": "24 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_genbank_blastn_search_result#en", "data_acquisition": "Performed blastn searches against Genbank nucleotide sequences.", "analysis": "Performed homology searches against sequences obtained from NCBI GenBank Release 150.0 (15\/08\/2005) using the blastn program (blast2.2.12).\r\nSequences used in the searches were located in the following 10 out of 18 GenBank divisions.\r\n1. PRI - primate sequences\r\n2. ROD - rodent sequences\r\n3. MAM - other mammalian sequences\r\n4. VRT - other vertebrate sequences\r\n5. INV - invertebrate sequences\r\n6. PLN - plant, fungal, and algal sequences\r\n7. BCT - bacterial sequences\r\n8. VRL - viral sequences\r\n9. PHG - bacteriophage sequences\r\n13. PAT - patent sequences\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "1,144,403 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the blast search result" }, { "name": "ACCESSION", "description": "Accession number of the GenBank entry" }, { "name": "DEFINITION", "description": "Definition of the GenBank clone" }, { "name": "DIVISION", "description": "GenBank division" }, { "name": "SCORE", "description": "Score in the blastn search result" }, { "name": "EXPECT", "description": "Expect value in the blastn search result" }, { "name": "IDENTITIES", "description": "Identities in the blastn search result" }, { "name": "STRAND1_1", "description": "Strand direction of the subject sequence" }, { "name": "STRAND1_2", "description": "Strand direction of the query sequence" } ] }, { "path": "en\/kome\/data-8.html", "name": "GenBank blastx search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-008", "description": "Results of blastx searches against GenBank amino acid sequences", "files": [ { "file_name": "kome_genbank_blastx_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_genbank_blastx_search_result.zip", "file_size": "34 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_genbank_blastx_search_result#en", "data_acquisition": "Performed blastx searches against Genbank amino acid sequences.", "analysis": "Performed homology searches against sequences obtained from NCBI GenBank Release 150.0 (15\/08\/2005) using the blastx program (blast2.2.12).\r\nSequences useed in the searches were located in the following 10 out of 18 GenBank divisions.\r\n1. PRI - primate sequences\r\n2. ROD - rodent sequences\r\n3. MAM - other mammalian sequences\r\n4. VRT - other vertebrate sequences\r\n5. INV - invertebrate sequences\r\n6. PLN - plant, fungal, and algal sequences\r\n7. BCT - bacterial sequences\r\n8. VRL - viral sequences\r\n9. PHG - bacteriophage sequences\r\n13. PAT - patent sequences\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "1,247,656 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the blastx search result" }, { "name": "ACCESSION", "description": "Accession number of the GenBank entry" }, { "name": "DEFINITION", "description": "Definition of the GenBank clone" }, { "name": "DIVISION", "description": "GenBank division" }, { "name": "SCORE", "description": "Score in the blastx search result" }, { "name": "EXPECT", "description": "Expect value in the blastx search result" }, { "name": "IDENTITIES", "description": "Identities in the blastx search result" }, { "name": "FRAME", "description": "Reading frame of the full-length cDNA clone" } ] }, { "path": "en\/kome\/data-9.html", "name": "Genome annotations", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-009", "description": "Extracted the hits related to rice genomes from GenBank blastn\/blastx results.", "files": [ { "file_name": "kome_genome_annotation.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_genome_annotation.zip", "file_size": "514 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_genome_annotation#en", "data_acquisition": "Performed blastn searches against Genbank nucleotide sequences and blastx searches against Genbank amino sequences.", "analysis": "Showing the entries related to rice genomes in GenBank blastn\/blastx results.\r\n\"Related to rice genomes\" is defined as follows:\r\nThe word \"Oryza sativa\" or \"rice\" is included in the definition of the entry and the word \"BAC\", \"PAC\", \"chromosome Genomic\", or \"Genomic sequence\" is included in the entry.", "data_number": "23,768 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BLAST_TYPE", "description": "Type of BLAST program (blastn or blastx)" }, { "name": "HIT_ACCESSION", "description": "Accession number of the GenBank entry" }, { "name": "DIVISION", "description": "GenBank division" }, { "name": "DEFINITION", "description": "Definition of the GenBank clone" }, { "name": "RANK", "description": "Ranking in the blast search result" }, { "name": "SCORE", "description": "Score in the blast search result" }, { "name": "EXPECT", "description": "Expect value in the blast search result" } ] }, { "path": "en\/kome\/data-10.html", "name": "Product annotations", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-010", "description": "Extracted the hits related to protein gene products or protein functions from GenBank blastn\/blastx results.", "files": [ { "file_name": "kome_product_annotation.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_product_annotation.zip", "file_size": "815 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_product_annotation#en", "data_acquisition": "Performed blastn searches against Genbank nucleotide sequences and blastx searches against Genbank amino acid sequences.", "analysis": "Showing the entries related to protein gene products or protein functions in GenBank blastn\/blastx results.\r\n\"Related to protein gene products or protein functions\" is defined as follows:\r\nThe word \"mRNA\", \"Protein\" or \"Gene\" is included in the entry.", "data_number": "24,184 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BLAST_TYPE", "description": "Type of BLAST program (blastn or blastx)" }, { "name": "HIT_ACCESSION", "description": "Accession number of the GenBank entry" }, { "name": "DIVISION", "description": "GenBank division" }, { "name": "DEFINITION", "description": "Definition of the GenBank clone" }, { "name": "RANK", "description": "Ranking in the blast search result" }, { "name": "SCORE", "description": "Score in the blast search result" }, { "name": "EXPECT", "description": "Expect value in the blast search result" } ] }, { "path": "en\/kome\/data-11.html", "name": "Japonica genome blast search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-011", "description": "Results of blastn searches against japonica genome sequences", "files": [ { "file_name": "kome_japonica_genome_blast_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_japonica_genome_blast_search_result.zip", "file_size": "802 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_japonica_genome_blast_search_result#en", "data_acquisition": "Genome contig sequences of japonica rice used for the searches were obtained from the TIGR Rice Genome Database at the time of Oct. 1st, 2005.", "analysis": "Performed blastn (blast 2.2.12) searches against the japonica rice genome sequences.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "35,778 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BAC_ACCESSION_NO", "description": "Accession number of the GenBank entry" }, { "name": "DEFINITION", "description": "Definition in the GenBank entry" }, { "name": "EXPECT", "description": "Expect value in the blastn search result" }, { "name": "SCORE", "description": "Score in the blastn search result" } ] }, { "path": "en\/kome\/data-12.html", "name": "Indica genome blast search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-012", "description": "Results of blastn searches against indica genome sequences (top hits only)", "files": [ { "file_name": "kome_indica_genome_blast_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_indica_genome_blast_search_result.zip", "file_size": "338 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_indica_genome_blast_search_result#en", "data_acquisition": "Genome sequences of indica rice used for the searches were obtained from the BGI-RIS.", "analysis": "Performed blastn (blast 2.2.12) searches against the indica rice genome sequences.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "35,736 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "INDICA_ACCESSION", "description": "Accession number of the GenBank entry" }, { "name": "DEFINITION", "description": "Definition in the GenBank entry" }, { "name": "EXPECT", "description": "Expect value in the blastn search result" }, { "name": "SCORE", "description": "Score in the blastn search result" }, { "name": "STRAND", "description": "Strand direction of the cDNA clone" } ] }, { "path": "en\/kome\/data-13.html", "name": "RMOS blastn result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-013", "description": "Results of blastn searches against the Rice EST Microarray (G-Array)", "files": [ { "file_name": "kome_rmos_blastn_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_rmos_blastn_result.zip", "file_size": "74 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_rmos_blastn_result#en", "data_acquisition": "Rice genome sequences used for the searches were obtained from the Rice Microarray Opening Site (RMOS).", "analysis": "Performed blastn (blast 2.2.12) searches against the probe sequences on the Rice EST Microarray (G-Array).\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "5,024 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "ARRAY_ELEMENT", "description": "Element number of the G-Array probe" }, { "name": "PROBE_ACCESSION", "description": "Accession number of the G-Array probe" }, { "name": "PROBE_CLONE_NAME", "description": "Clone name of the G-Array probe" }, { "name": "EXPECT", "description": "Expect value in the blastn search result" }, { "name": "SCORE", "description": "Score in the blastn search result" } ] }, { "path": "en\/kome\/data-14.html", "name": "Tos17 link result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-014", "description": "Relation with Tos17 mutant clones", "files": [ { "file_name": "kome_tos17_link_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_tos17_link_result.zip", "file_size": "49 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_tos17_link_result#en", "data_acquisition": "The flanking sequences of Tos17-induced insertion mutants obtained from the Rice Tos17 Insertion Mutant Database were used.", "analysis": "We predicted that there would be relations between the overlapped regions that emerge by mapping both the Tos17 flanking seqeunces and the full-length cDNA clones to the rice genome BAC contigs.\r\nThe blastn searches were performed with threshold Expect value of less than 1e-100 for the mapping.", "data_number": "2,864 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "FULL_CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "TOS_NAME", "description": "Name of the Tos17 clone" }, { "name": "BAC_ACCESSION_NO", "description": "Accession number of the mapped BAC clone" }, { "name": "TOS_INSERT_POSITION", "description": "Insert position of the Tos17 clone on the BAC contigs" }, { "name": "cDNA_START_POSITION", "description": "Mapping start position of the cDNA clone on the BAC contigs" }, { "name": "cDNA_END_POSITION", "description": "Mapping end position of the cDNA clone on the BAC contigs" } ] }, { "path": "en\/kome\/data-15.html", "name": "PLACE search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-015", "description": "Results of signal search against PLACE.\r\nPLACE: cis-acting regulatory DNA elements Database", "files": [ { "file_name": "kome_place_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_place_search_result.zip", "file_size": "43 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_place_search_result#en", "data_acquisition": "The full-length cDNA clones were mapped to japonica rice genome sequences.\r\nThe cis-acting regulatory DNA elements were obtained from PLACE 22.0.", "analysis": "After mapping the cDNA clones to the japonica rice genome sequences, Cis-element analysis were performed against 1000-bp upstream regions of the site where the full-length cDNA clones were mapped.", "data_number": "5,158,379 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "HIT_NO", "description": "Ranking in the sigscan search result" }, { "name": "SIGNAL_NAME", "description": "Name of the signal element" }, { "name": "SIGNAL_TYPE", "description": "Signal type" }, { "name": "LOCATION", "description": "Signal position" }, { "name": "STRAND", "description": "Strand direction of the query cDNA sequence" }, { "name": "SIGNAL_SEQ", "description": "Signal sequence" }, { "name": "SIGNAL_ID", "description": "Signal element ID in PLACE" } ] }, { "path": "en\/kome\/data-16.html", "name": "ORF information", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-016", "description": "Information about the longest ORFs", "files": [ { "file_name": "kome_orf_infomation.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_orf_infomation.zip", "file_size": "526 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_orf_infomation#en", "data_acquisition": "Showing information about the predicted ORFs of the full-length cDNA clones, such as start and end positions.", "analysis": "The longest ORF is predicted by finding all the start and stop codons from the cDNA sequence and picking a pair of start and stop codons that makes the longest distance.", "data_number": "37,073 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "FRAME_NO", "description": "Frame number" }, { "name": "START_POSITION", "description": "Start position of the longest ORF" }, { "name": "STOP_POSITION", "description": "End position of the longest ORF" }, { "name": "LENGTH", "description": "Length of the longest ORF" }, { "name": "OCCUPATION", "description": "Ratio of the ORF length to the cDNA sequence length" } ] }, { "path": "en\/kome\/data-17.html", "name": "Arabidopsis CDS blastp result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-017", "description": "Results of blastp searches against Arabidopsis thaliana CDSs", "files": [ { "file_name": "kome_arabidopsis_cds_blastp_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_arabidopsis_cds_blastp_result.zip", "file_size": "3.6 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_arabidopsis_cds_blastp_result#en", "data_acquisition": "Predicted CDSs of Arabidopsis thaliana used for the searches were obtained from the TIGR Arabidopsis thaliana Database ver. 5.", "analysis": "Performed blastp searches with the full-length cDNA sequences against predicted CDSs of Arabidopsis thaliana.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "137,642 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "MIPS_CODE", "description": "MIPS code in the Arabidopsis thaliana database" }, { "name": "DEFINITION", "description": "Definition of CDS in the Arabidopsis thaliana database" }, { "name": "EXPECT", "description": "Expect value in the blastp search result" }, { "name": "SCORE", "description": "Score in the blastp search result" } ] }, { "path": "en\/kome\/data-18.html", "name": "PIR search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-018", "description": "Results of blastx searches against the PIR protein database", "files": [ { "file_name": "kome_pir_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_pir_search_result.zip", "file_size": "29 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_pir_search_result#en", "data_acquisition": "PIR Release 80.00 (December 31, 2004) was used for the searches.", "analysis": "Performed blastx searches against the PIR protein database.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "1,549,409 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the blastx search result" }, { "name": "PIR_ACCESSION", "description": "Accession number in the PIR protein database" }, { "name": "DEFINITION", "description": "Definition of the protein in the PIR protein database" }, { "name": "EXPECT", "description": "Expect value in the blastx search result" }, { "name": "SCORE", "description": "Score in the blastx search result" } ] }, { "path": "en\/kome\/data-19.html", "name": "SwissProt search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-019", "description": "Results of blastx searches against the Swiss-Prot database", "files": [ { "file_name": "kome_swissprot_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_swissprot_search_result.zip", "file_size": "30 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_swissprot_search_result#en", "data_acquisition": "The Swiss-Prot database was used for the searches.", "analysis": "Performed blastx searches against the Swiss-Prot database.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "1,286,530 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the blastx search result" }, { "name": "DEFINITION", "description": "Definition of the protein in the Swiss-Prot database" }, { "name": "ENTRY_NAME", "description": "Name of the protein in the Swiss-Prot database" }, { "name": "EXPECT", "description": "Expect value in the blastx search result" }, { "name": "SCORE", "description": "Score in the blastx search result" } ] }, { "path": "en\/kome\/data-20.html", "name": "UniProt search blastx result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-020", "description": "Results of blastx searches against the UniProt database", "files": [ { "file_name": "kome_uniprot_search_blastx_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_uniprot_search_blastx_result.zip", "file_size": "1.4 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_uniprot_search_blastx_result#en", "data_acquisition": "UniProt Knowledgebase Release 6.3 was used for the searches.", "analysis": "Performed blastx searches against the UniProt database.\r\nThe results are filtered with Expect values lower than 1e-10.", "data_number": "42,146 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the blastx search result" }, { "name": "UNIPROT ID", "description": "UniProt ID" }, { "name": "DEFINITION", "description": "Definition of the protein in the UniProt database" }, { "name": "EXPECT", "description": "Expect value in the blastx search result" }, { "name": "SCORE", "description": "Score in the blastx search result" } ] }, { "path": "en\/kome\/data-21.html", "name": "InterPro search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-021", "description": "Results of motif searches against the InterPro database", "files": [ { "file_name": "kome_interpro_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_interpro_search_result.zip", "file_size": "2.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_interpro_search_result#en", "data_acquisition": "InterPro release 8.0 was used for the searches.", "analysis": "Performed motif searches against the InterPro database.\r\nThe following 9 programs were used to find motifs.\r\nBlastProDom\r\nFPrintScan\r\nHMMPfam\r\nHMMPIR\r\nHMMSmart\r\nHMMTigr\r\nProfileScan\r\nScanRegExp\r\nSuperFamily", "data_number": "110,589 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "INTERPRO_ID", "description": "ID of the motif in the InterPro database" }, { "name": "INTERPRO_NAME", "description": "Name of the motif in the InterPro database" }, { "name": "METHOD", "description": "Motif search program" }, { "name": "ACCESSION_ID", "description": "Accession number of the motif" }, { "name": "SHORT_NAME", "description": "Short name of the motif" }, { "name": "LOCATION", "description": "Location of the motif" }, { "name": "EXPECT", "description": "Expect value in the search result" } ] }, { "path": "en\/kome\/data-22.html", "name": "Blocks search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-022", "description": "Results of motif searches against the Blocks Database", "files": [ { "file_name": "kome_blocks_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_blocks_search_result.zip", "file_size": "60 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_blocks_search_result#en", "data_acquisition": "Blocks Database Version 14.0 (October 2003) was used for the searches.", "analysis": "Performed motif searches against the Blocks Database using BLIMPS Version 3.6.", "data_number": "1,603,600 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the search result" }, { "name": "ACCESSION", "description": "Accession number of the motif in the Blocks Database" }, { "name": "DESCRIPTION", "description": "Description of the motif in the Blocks Database" }, { "name": "STRENGTH", "description": "Strength in the BLIMPS result" }, { "name": "SCORE", "description": "Score in the BLIMPS result" }, { "name": "RF", "description": "Reading frame (Always 0 since the sequence is in amino acids)" }, { "name": "POSITION", "description": "Position of the motif" }, { "name": "MOTIF_SEQ", "description": "Amino acid sequence of the motif" }, { "name": "MOTIF_LENGTH", "description": "Length of the amino acid sequence of the motif" } ] }, { "path": "en\/kome\/data-23.html", "name": "GO classification GenBank", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-023", "description": "Results of GO (Gene Ontology) term classifications done based on GenBank homology searches", "files": [ { "file_name": "kome_go_classification_genbank.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_go_classification_genbank.zip", "file_size": "4.9 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_go_classification_genbank#en", "data_acquisition": "The results of GenBank homology searches were used for GO term classifications.", "analysis": "The GO term classifications were done based on the results of blastx searches against 10 GeneBank divisions.", "data_number": "1,655,603 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "GO_ACCESSION", "description": "Accession number of the GO term" } ] }, { "path": "en\/kome\/data-24.html", "name": "GO classification InterPro", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-024", "description": "Results of GO (Gene Ontology) term classifications done based on InterPro motif searches", "files": [ { "file_name": "kome_go_classification_interpro.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_go_classification_interpro.zip", "file_size": "645 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_go_classification_interpro#en", "data_acquisition": "The results of InterPro motif searches were used for GO term classifications.", "analysis": "The GO term classifications were done based on the results of InterPro motif searches.", "data_number": "181,478 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "GO_ACCESSION", "description": "Accession number of the GO term" } ] }, { "path": "en\/kome\/data-25.html", "name": "GO classification Arabidopsis", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-025", "description": "Results of GO (Gene Ontology) term classifications done based on homology searches against predicted CDSs of Arabidopsis thaliana", "files": [ { "file_name": "kome_go_classification_arabidopsis.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_go_classification_arabidopsis.zip", "file_size": "418 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_go_classification_arabidopsis#en", "data_acquisition": "The results of blast searches against predicted CDSs of Arabidopsis thaliana were used for GO term classifications.", "analysis": "The GO term classifications were done based on the results of blast searches against predicted CDSs of Arabidopsis thaliana.", "data_number": "94,013 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "GO_ACCESSION", "description": "Accession number of the GO term" } ] }, { "path": "en\/kome\/data-26.html", "name": "Memsat search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-026", "description": "Results of transmembrane region predictions", "files": [ { "file_name": "kome_memsat_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_memsat_search_result.zip", "file_size": "209 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_memsat_search_result#en", "data_acquisition": "The MEMSAT program was used for the predictions.", "analysis": "Performed transmembrane region predictions using the MEMSAT program.", "data_number": "37,073 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "COUNT", "description": "Number of transmembrane regions" }, { "name": "WAY", "description": "Direction of 5' end" } ] }, { "path": "en\/kome\/data-27.html", "name": "pSort search result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-027", "description": "Results of protein subcellular localization predictions", "files": [ { "file_name": "kome_psort_search_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_psort_search_result.zip", "file_size": "823 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_psort_search_result#en", "data_acquisition": "PSORT version 5.8 was used for the predictions.", "analysis": "Performed subcellular localization predictions using the PSORT program.", "data_number": "147,789 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RANK", "description": "Ranking in the PSORT prediction result" }, { "name": "TARGET", "description": "Target organelle of the predicted signal sequence" }, { "name": "CERTAINTY", "description": "Certainty in the PSORT prediction result" }, { "name": "SCORE", "description": "Score in the WoLF PSORT prediction result" } ] }, { "path": "en\/kome\/data-28.html", "name": "RPD link result", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-028", "description": "Results of homology searches against the Rice Proteome Database", "files": [ { "file_name": "kome_rpd_link_result.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_rpd_link_result.zip", "file_size": "14 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_rpd_link_result#en", "data_acquisition": "Performed blastn searches with the full-length cDNA clones against the Rice Proteome Database.", "analysis": "", "data_number": "1,258 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "RPD_ID", "description": "ID of the protein in the Rice Proteome Database that is homologous to the clone" }, { "name": "SCORE", "description": "Score in the blastn search result" }, { "name": "COVERAGE", "description": "Query coverage between the protein in the Rice Proteome Database and the clone" } ] }, { "path": "en\/kome\/data-29.html", "name": "Nucleotide Sequence", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-029", "description": "Nucleotide sequences of the full-length cDNA clones (trimmed sequences)", "files": [ { "file_name": "CSV: kome_ine_full_sequence_db.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_ine_full_sequence_db.zip", "file_size": "19 MB" }, { "file_name": "FASTA: kome_ine_full_sequence_db.fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_ine_full_sequence_db.fasta.zip", "file_size": "21 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_ine_full_sequence_db#en", "data_acquisition": "", "analysis": "", "data_number": "37,132 entries", "details": [ { "name": "ACCESSION", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_ID", "description": "ID of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "CLUSTER_ID", "description": "Cluster ID" }, { "name": "BELONG", "description": "Initial of the research institute where the clone was sequenced. (R: RIKEN, F: FAIS)" }, { "name": "SEQUENCE", "description": "Nucleotide sequence" } ] }, { "path": "en\/kome\/data-30.html", "name": "Trimming information", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-030", "description": "Nucleotide sequences that the regions predicted to be poly(A) sites and vector-derived sites were trimmed.\r\n161 out of 32,127 sequences were trimmed as above.", "files": [ { "file_name": "kome_trimming_information.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_trimming_information.zip", "file_size": "63 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_trimming_information#en", "data_acquisition": "", "analysis": "", "data_number": "161 entries", "details": [ { "name": "ACCESSION_NO", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "BELONG", "description": "Initial of the research institute where the clone was sequenced. (R: RIKEN, F: FAIS)" }, { "name": "SEQ_DATA", "description": "Sequence after trimming" }, { "name": "TRIM_TOP", "description": "Length of the sequence trimmed from 5' end" }, { "name": "TRIM_END", "description": "Length of the sequence trimmed from 3' end" }, { "name": "TRIM_LENGTH", "description": "Length of the sequence after trimming" } ] }, { "path": "en\/kome\/data-31.html", "name": "Amino Acid Sequence", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-031", "description": "Amino acid sequences of the full-length cDNA clones deduced from the longest ORFs.", "files": [ { "file_name": "CSV: kome_ine_full_sequence_amino_db.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_ine_full_sequence_amino_db.zip", "file_size": "7.4 MB" }, { "file_name": "FASTA: kome_ine_full_sequence_amino_db.fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_ine_full_sequence_amino_db.fasta.zip", "file_size": "7.7 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_ine_full_sequence_amino_db#en", "data_acquisition": "", "analysis": "", "data_number": "37,073 entries", "details": [ { "name": "ACCESSION", "description": "Accession number of the full-length cDNA clone" }, { "name": "CLONE_ID", "description": "ID of the full-length cDNA clone" }, { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "CLUSTER_ID", "description": "Cluster ID" }, { "name": "BELONG", "description": "Initial of the research institute where the clone was sequenced. (R: RIKEN, F: FAIS)" }, { "name": "SEQUENCE", "description": "Amino acid sequence" } ] }, { "path": "en\/kome\/data-32.html", "name": "OPS index", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-032", "description": "Index of OPS (Oryza Partial Sequence).\r\nRelationships between clone names and EST names are listed.", "files": [ { "file_name": "kome_ops_index.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_ops_index.zip", "file_size": "2.6 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_ops_index#en", "data_acquisition": "", "analysis": "", "data_number": "382,787 entries", "details": [ { "name": "CLONE_NAME", "description": "Name of the full-length cDNA clone" }, { "name": "3'EST_NAME", "description": "3' EST name" }, { "name": "5'EST_NAME", "description": "5' EST name" } ] }, { "path": "en\/kome\/data-33.html", "name": "All 3' EST", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-033", "description": "3' EST sequences", "files": [ { "file_name": "CSV: kome_est_3end_all.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_est_3end_all.zip", "file_size": "70 MB" }, { "file_name": "FASTA: kome_est_3end_all.fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_est_3end_all.fasta.zip", "file_size": "76 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_est_3end_all#en", "data_acquisition": "", "analysis": "", "data_number": "536,885 entries", "details": [ { "name": "3'EST_NAME", "description": "3' EST name" }, { "name": "SEQUENCE", "description": "3' EST sequence" } ] }, { "path": "en\/kome\/data-34.html", "name": "All 5' EST", "database_name": "KOME", "doi": "10.18908\/lsdba.nbdc00120-034", "description": "5' EST sequences", "files": [ { "file_name": "CSV: kome_est_5end_all.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_est_5end_all.zip", "file_size": "26 MB" }, { "file_name": "FASTA: kome_est_5end_all.fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kome\/LATEST\/kome_est_5end_all.fasta.zip", "file_size": "27 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kome_est_5end_all#en", "data_acquisition": "", "analysis": "", "data_number": "241,854 entries", "details": [ { "name": "5'EST_NAME", "description": "5' EST name" }, { "name": "SEQUENCE", "description": "5' EST sequence" } ] }, { "path": "en\/leading-authors\/data-1.html", "name": "Body text collection", "database_name": "Leading Author's", "doi": "", "description": "It is the collection of this reviews' body text. It is provided in doc format, txt format and pdf format.\r\nIn simple search, you can view the body text and link doc\/txt\/pdf files and figures.", "files": [ { "file_name": "la_collection.zip (file list)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/la_collection.zip", "file_size": "965 KB" }, { "file_name": "format_doc.zip (doc format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/format_doc.zip", "file_size": "2.3 MB" }, { "file_name": "format_txt.zip (txt format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/format_txt.zip", "file_size": "1020 KB" }, { "file_name": "format_pdf.zip (pdf format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/format_pdf.zip", "file_size": "45 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/la_collection", "data_acquisition": "", "analysis": "", "data_number": "75", "details": [] }, { "path": "en\/leading-authors\/data-2.html", "name": "Figure collection", "database_name": "Leading Author's", "doi": "", "description": "It is the collection of figures in reviews.\r\nFigure itself is provided in jpeg format. Thumbnails are provided in png format.", "files": [ { "file_name": "format_jpg.zip (jpg format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/format_jpg.zip", "file_size": "79 MB" }, { "file_name": "format_png.zip (png format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/leading_authors\/LATEST\/format_png.zip", "file_size": "21 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/ligandbox\/data-1.html", "name": "Compounds of Namiki (Single Conformer)", "database_name": "LigandBox", "doi": "10.18908\/lsdba.nbdc00551-001", "description": "Extracted single conformer data from each compound provided by Namiki Shoji Co.,Ltd. (Oct. 2017). They are assembled on a file in Mol2 format. Comments in Mol2 format are extracted to another CSV file. They can be searched in simple search.", "files": [ { "file_name": "ligandbox_namiki_single.zip (CSV format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/ligandbox_namiki_single.zip", "file_size": "174MB" }, { "file_name": "Namiki_Single.mol2.gz (Mol2 format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/Namiki_Single.mol2.gz", "file_size": "6GB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ligandbox_namiki#en", "data_acquisition": "Provided by Namiki Shoji Co.,Ltd.", "analysis": "", "data_number": "5,434,894 entries", "details": [ { "name": "LIGANDBOX_ID", "description": "ID in LigandBox" }, { "name": "SINGLE", "description": "\"ture\" if the entry is extacted as single conformer, else \"false\"." }, { "name": "SOURCE", "description": "Source of this compound" }, { "name": "SOURCE_ID", "description": "ID in the source" }, { "name": "MOLECULAR_FORMULA", "description": "Molecular formula" }, { "name": "MOLECULAR_WEIGHT", "description": "Molecular weight" }, { "name": "MOLECULAR_CHARGE", "description": "Molecular charge" }, { "name": "NUM_OF_DONOR", "description": "Number of hydrogen bond donors" }, { "name": "NUM_OF_ACCEPTOR", "description": "Number of hydrogen bond acceptors" }, { "name": "NUM_OF_CHIRAL_ATOMS", "description": "Number of chiral atoms" }, { "name": "TPSA", "description": "Topological Polar Surface Area" }, { "name": "HOMO", "description": "Highest Occupied Molecular Orbital energy" }, { "name": "LUMO", "description": "Lowest Unoccupied Molecular Orbital energy" }, { "name": "LOGP", "description": "Partition coefficient" }, { "name": "LOGS", "description": "Solubility" }, { "name": "MOL2_FILE", "description": "URL of mol2 file for the entry" } ] }, { "path": "en\/ligandbox\/data-2.html", "name": "Compounds of Namiki", "database_name": "LigandBox", "doi": "10.18908\/lsdba.nbdc00551-002", "description": "Compounds provided by Namiki Shoji Co.,Ltd. (Oct. 2017). All conformers are included in it. They are assembled on a file in Mol2 format. Comments in Mol2 format are extracted to another CSV file. They can be searched in simple search.", "files": [ { "file_name": "ligandbox_namiki_multiple.zip (CSV format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/ligandbox_namiki_multiple.zip", "file_size": "199MB" }, { "file_name": "Namiki_Multiple.mol2.gz (Mol2 format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/Namiki_Multiple.mol2.gz", "file_size": "8.8GB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ligandbox_namiki#en", "data_acquisition": "Provided by Namiki Shoji Co.,Ltd.", "analysis": "", "data_number": "8,353,035 entries", "details": [ { "name": "LIGANDBOX_ID", "description": "ID in LigandBox" }, { "name": "SINGLE", "description": "\"TRUE\" if the entry is extacted as single conformer, else \"FALSE\"." }, { "name": "SOURCE", "description": "Source of this compound" }, { "name": "SOURCE_ID", "description": "ID in the source" }, { "name": "MOLECULAR_FORMULA", "description": "Molecular formula" }, { "name": "MOLECULAR_WEIGHT", "description": "Molecular weight" }, { "name": "MOLECULAR_CHARGE", "description": "Molecular charge" }, { "name": "NUM_OF_DONOR", "description": "Number of hydrogen bond donors" }, { "name": "NUM_OF_ACCEPTOR", "description": "Number of hydrogen bond acceptors" }, { "name": "NUM_OF_CHIRAL_ATOMS", "description": "Number of chiral atoms" }, { "name": "TPSA", "description": "Topological Polar Surface Area" }, { "name": "HOMO", "description": "Highest Occupied Molecular Orbital energy" }, { "name": "LUMO", "description": "Lowest Unoccupied Molecular Orbital energy" }, { "name": "LOGP", "description": "Partition coefficient" }, { "name": "LOGS", "description": "Solubility" }, { "name": "MOL2_FILE", "description": "URL of mol2 file for the entry" } ] }, { "path": "en\/ligandbox\/data-5.html", "name": "Compounds of PDB (Single Conformer)", "database_name": "LigandBox", "doi": "10.18908\/lsdba.nbdc00551-005", "description": "Extracted single conformer data from each compound in PDB. They are assembled on a file in Mol2 format. Comments in Mol2 format are extracted to another CSV file. They can be searched in simple search.", "files": [ { "file_name": "ligandbox_pdb_single.zip (CSV format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/ligandbox_pdb_single.zip", "file_size": "888KB" }, { "file_name": "PDB_Single.mol2.gz (Mol2 format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/PDB_Single.mol2.gz", "file_size": "31MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ligandbox_pdb#en", "data_acquisition": "PDB", "analysis": "", "data_number": "25,276 entries", "details": [ { "name": "LIGANDBOX_ID", "description": "ID in LigandBox" }, { "name": "SINGLE", "description": "\"true\" if the entry is extacted as single conformer, else \"false\"." }, { "name": "SOURCE", "description": "Source of this compound" }, { "name": "SOURCE_ID", "description": "ID in the source" }, { "name": "MOLECULAR_FORMULA", "description": "Molecular formula" }, { "name": "MOLECULAR_WEIGHT", "description": "Molecular weight" }, { "name": "MOLECULAR_CHARGE", "description": "Molecular charge" }, { "name": "NUM_OF_DONOR", "description": "Number of hydrogen bond donors" }, { "name": "NUM_OF_ACCEPTOR", "description": "Number of hydrogen bond acceptors" }, { "name": "NUM_OF_CHIRAL_ATOMS", "description": "Number of chiral atoms" }, { "name": "TPSA", "description": "Topological Polar Surface Area" }, { "name": "HOMO", "description": "Highest Occupied Molecular Orbital energy" }, { "name": "LUMO", "description": "Lowest Unoccupied Molecular Orbital energy" }, { "name": "LOGP", "description": "Partition coefficient" }, { "name": "LOGS", "description": "Solubility" }, { "name": "MOL2_FILE", "description": "URL of mol2 file for the entry" } ] }, { "path": "en\/ligandbox\/data-6.html", "name": "Compounds of PDB", "database_name": "LigandBox", "doi": "10.18908\/lsdba.nbdc00551-006", "description": "Compounds in PDB. All conformers are included in it. They are assembled on a file in Mol2 format. Comments in Mol2 format are extracted to another CSV file. They can be searched in simple search.", "files": [ { "file_name": "ligandbox_pdb_multiple.zip (CSV format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/ligandbox_pdb_multiple.zip", "file_size": "1.5MB" }, { "file_name": "PDB_Multiple.mol2.gz (Mol2 format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ligandbox\/LATEST\/PDB_Multiple.mol2.gz", "file_size": "102MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ligandbox_pdb#en", "data_acquisition": "PDB", "analysis": "", "data_number": "90,336 entries", "details": [ { "name": "LIGANDBOX_ID", "description": "ID in LigandBox" }, { "name": "SINGLE", "description": "\"TRUE\" if the entry is extacted as single conformer, else \"FALSE\"." }, { "name": "SOURCE", "description": "Source of this compound" }, { "name": "SOURCE_ID", "description": "ID in the source" }, { "name": "MOLECULAR_FORMULA", "description": "Molecular formula" }, { "name": "MOLECULAR_WEIGHT", "description": "Molecular weight" }, { "name": "MOLECULAR_CHARGE", "description": "Molecular charge" }, { "name": "NUM_OF_DONOR", "description": "Number of hydrogen bond donors" }, { "name": "NUM_OF_ACCEPTOR", "description": "Number of hydrogen bond acceptors" }, { "name": "NUM_OF_CHIRAL_ATOMS", "description": "Number of chiral atoms" }, { "name": "TPSA", "description": "Topological Polar Surface Area" }, { "name": "HOMO", "description": "Highest Occupied Molecular Orbital energy" }, { "name": "LUMO", "description": "Lowest Unoccupied Molecular Orbital energy" }, { "name": "LOGP", "description": "Partition coefficient" }, { "name": "LOGS", "description": "Solubility" }, { "name": "MOL2_FILE", "description": "URL of mol2 file for the entry" } ] }, { "path": "en\/mecab\/data-1.html", "name": "JST Thesaurus Headwords and Synonyms", "database_name": "MeCab user dictionary for science technology term", "doi": "10.18908\/lsdba.nbdc02358-001.V002", "description": "We have made a user dictionary of morphological analysis engine MeCab (http:\/\/taku910.github.io\/mecab\/) headwords and synonyms of JST Thesaurus (2015 edition) . As no reading was given to synonyms (Headword Flag: 'V') in the original thesaurus, NBDC had given natural reading to synonyms in life science (Category code: 'LSxx', where xx is a two-digit number) and computer science (Category code: 'EG01') and reading of base form to synonyms in other categories.\r\nThe dictionary items are based on IPA dictionary. Csv file is encoded in Shift-JIS and dic file is encoded in UTF-8. Entries with zenkaku alphabets, numerals and symbols converted into corresponding hankaku characters are also included.\r\nPlease note that this dictionary can not be used as a thesaurus because information on relations between words is not included in the dictionary.", "files": [ { "file_name": "Thesaurus2015.dic.zip (MeCab dic format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/Thesaurus2015.dic.zip", "file_size": "7.4 MB" }, { "file_name": "mecab_thesaurus.zip (csv format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/mecab_thesaurus.zip", "file_size": "3.8 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/mecab_thesaurus#en", "data_acquisition": "IPA dictionary (mecab-ipadic-2.7.0-20070801 downloaded from MeCab's site [see above]), JST Science and Technology Thesaurus (2015 edition)", "analysis": "", "data_number": "127,214 entries", "details": [ { "name": "Surface form", "description": "The word itself" }, { "name": "Left-context ID", "description": "MeCab internal ID for left context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Right-context ID", "description": "MeCab internal ID for right context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Cost", "description": "The cost for the likelihood of the word to appear in a sentence (smaller, more likely)" }, { "name": "POS", "description": "Part of speech" }, { "name": "POS subcategory 1", "description": "POS subcategory 1" }, { "name": "POS subcategory 2", "description": "POS subcategory 2" }, { "name": "POS subcategory 3", "description": "POS subcategory 3" }, { "name": "Conjugation type", "description": "Conjugation type" }, { "name": "Conjugation form", "description": "Conjugation form" }, { "name": "Base form", "description": "Corresponding headword in the JST thesaurus" }, { "name": "Reading('Furigana')", "description": "Reading of the headword.\r\nWhen Headword Flag is ’V’, it may be different from the reading of the surface form." }, { "name": "Pronunciation", "description": "Automatically generated from Reading" }, { "name": "Source dictionary", "description": "It is fixed as 'Thesaurus2015'." }, { "name": "ID in Source dictionary", "description": "ID in JST Thesaurus" }, { "name": "J-GLOBAL ID", "description": "ID in J-GLOBAL" }, { "name": "Headword Flag", "description": "・C: The word's surface form is the same as the headword in JST Thesaurus (or corresponding hankaku form)\r\n・V: Otherwise" }, { "name": "Category code", "description": "Category code of science fields in JST Thesaurus" }, { "name": "Common word flag 1", "description": "・1: There is an entry (or entries) for the surface form in IPA dictionary\r\n・0: There are no entries for the surface in IPA dictionary" }, { "name": "Common word flag 2", "description": "Based on \"IPA dictionary analysis results\":\r\n・When the value of Common word flag １ is 1, the value of this flag is the part of speech for the IPA dictionary analysis result.\r\n・When the value of Common word flag １ is 0:\r\n- UNKNOWN_1: if the result is one unknown word\r\n- UNKNOWN_2: if the result is multiple tokens including unknown word\r\n- MULTI_WORD: if the result is multiple tokens in IPA dictionary" }, { "name": "IPA dictionary analysis results", "description": "Results of the morphological analysis with the original IPA dictionary (and the dictionary with IPA dictionary entries where zenkaku alphanumeric characters and symbols are converted into corresponding hankaku characters). If the result is devided into multiple tokens, it is whitespace-separated. It is not manually corrected." } ] }, { "path": "en\/mecab\/data-2.html", "name": "J-GLOBAL MeSH Dictionary", "database_name": "MeCab user dictionary for science technology term", "doi": "10.18908\/lsdba.nbdc02358-002.V002", "description": "A user dictionary for morphological analysis engine MeCab(http:\/\/taku910.github.io\/mecab\/) from J-GLOBAL science and technology terms that have linked to MeSH (Medical Subect Headings: https:\/\/www.nlm.nih.gov\/mesh\/) terms by United States National Library of Medicine. The dictionary items are based on IPA dictionary. Csv file is encoded in Shift-JIS and dic file is encoded in UTF-8.", "files": [ { "file_name": "JSTMeSH.dic.zip (MeCab dic format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/JSTMeSH.dic.zip", "file_size": "1.2 MB" }, { "file_name": "mecab_jstmesh.zip (csv format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/mecab_jstmesh.zip", "file_size": "484 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/mecab_jstmesh#en", "data_acquisition": "IPA dictionary (mecab-ipadic-2.7.0-20070801 downloaded from MeCab's site [see above])、J-GLOBAL Knowledge", "analysis": "", "data_number": "15,425 entries", "details": [ { "name": "Surface form", "description": "The word itself" }, { "name": "Left-context ID", "description": "MeCab internal ID for left context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Right-context ID", "description": "MeCab internal ID for right context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Cost", "description": "The cost for the likelihood of the word to appear in a sentence (smaller, more likely)" }, { "name": "POS", "description": "Part of speech" }, { "name": "POS subcategory 1", "description": "POS subcategory 1" }, { "name": "POS subcategory 2", "description": "POS subcategory 2" }, { "name": "POS subcategory 3", "description": "POS subcategory 3" }, { "name": "Conjugation type", "description": "Conjugation type" }, { "name": "Conjugation form", "description": "Conjugation form" }, { "name": "Base form", "description": "Same as the surface form" }, { "name": "Reading('Furigana')", "description": "(empty)" }, { "name": "Pronunciation", "description": "(empty)" }, { "name": "Source dictionary", "description": "It is fixed as 'MeSH'." }, { "name": "ID in Source dictionary", "description": "MeSH UID" }, { "name": "J-GLOBAL ID", "description": "ID in J-GLOBAL" }, { "name": "Headword Flag", "description": "It is fixed as 'C'." }, { "name": "Category code", "description": "Category code of science fields in JST Thesaurus" }, { "name": "Common word flag 1", "description": "・1: There is an entry (or entries) for the surface form in IPA dictionary\r\n・0: There are no entries for the surface in IPA dictionary" }, { "name": "Common word flag 2", "description": "Based on \"IPA dictionary analysis results\":\r\n・When the value of Common word flag １ is 1, the value of this flag is the part of speech for the IPA dictionary analysis result.\r\n・When the value of Common word flag １ is 0:\r\n- UNKNOWN_1: if the result is one unknown word\r\n- UNKNOWN_2: if the result is multiple tokens including unknown word\r\n- MULTI_WORD: if the result is multiple tokens in IPA dictionary" }, { "name": "IPA dictionary analysis results", "description": "Results of the morphological analysis with the original IPA dictionary (and the dictionary with IPA dictionary entries where zenkaku alphanumeric characters and symbols are converted into corresponding hankaku characters). If the result is devided into multiple tokens, it is whitespace-separated. It is not manually corrected." } ] }, { "path": "en\/mecab\/data-3.html", "name": "Nikkaji Dictionary", "database_name": "MeCab user dictionary for science technology term", "doi": "10.18908\/lsdba.nbdc02358-003.V002", "description": "A user dictionary for morphological analysis engine MeCab(http:\/\/taku910.github.io\/mecab\/) from J-GLOBAL science and technology terms that have linked to Japan Chemical Substance Dictionary (Nikkaji), an organic compound dictionary database prepared by the Japan Science and Technology Agency. The dictionary items are based on IPA dictionary. Csv file is encoded in Shift-JIS and dic file is encoded in UTF-8.", "files": [ { "file_name": "Nikkaji.dic.zip (MeCab dic format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/Nikkaji.dic.zip", "file_size": "6.6 MB" }, { "file_name": "mecab_nikkaji.zip (csv format)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/mecab\/LATEST\/mecab_nikkaji.zip", "file_size": "2.4 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/mecab_nikkaji#en", "data_acquisition": "IPA dictionary (mecab-ipadic-2.7.0-20070801 downloaded from MeCab's site [see above])、J-GLOBAL Knowledge", "analysis": "", "data_number": "82,922 entries", "details": [ { "name": "Surface form", "description": "The word itself" }, { "name": "Left-context ID", "description": "MeCab internal ID for left context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Right-context ID", "description": "MeCab internal ID for right context (see http:\/\/taku910.github.io\/mecab\/dic.html)" }, { "name": "Cost", "description": "The cost for the likelihood of the word to appear in a sentence (smaller, more likely)" }, { "name": "POS", "description": "Part of speech" }, { "name": "POS subcategory 1", "description": "POS subcategory 1" }, { "name": "POS subcategory 2", "description": "POS subcategory 2" }, { "name": "POS subcategory 3", "description": "POS subcategory 3" }, { "name": "Conjugation type", "description": "Conjugation type" }, { "name": "Conjugation form", "description": "Conjugation form" }, { "name": "Base form", "description": "Same as the surface form" }, { "name": "Reading('Furigana')", "description": "(empty)" }, { "name": "Pronunciation", "description": "(empty)" }, { "name": "Source dictionary", "description": "It is fixed as 'Nikkaji'." }, { "name": "ID in Source dictionary", "description": "MeSH UID" }, { "name": "J-GLOBAL ID", "description": "ID in J-GLOBAL" }, { "name": "Headword Flag", "description": "It is fixed as 'C'." }, { "name": "Category code", "description": "Category code of science fields in JST Thesaurus" }, { "name": "Common word flag 1", "description": "・1: There is an entry (or entries) for the surface form in IPA dictionary\r\n・0: There are no entries for the surface in IPA dictionary" }, { "name": "Common word flag 2", "description": "Based on \"IPA dictionary analysis results\":\r\n・When the value of Common word flag １ is 1, the value of this flag is the part of speech for the IPA dictionary analysis result.\r\n・When the value of Common word flag １ is 0:\r\n- UNKNOWN_1: if the result is one unknown word\r\n- UNKNOWN_2: if the result is multiple tokens including unknown word\r\n- MULTI_WORD: if the result is multiple tokens in IPA dictionary" }, { "name": "IPA dictionary analysis results", "description": "Results of the morphological analysis with the original IPA dictionary (and the dictionary with IPA dictionary entries where zenkaku alphanumeric characters and symbols are converted into corresponding hankaku characters). If the result is devided into multiple tokens, it is whitespace-separated. It is not manually corrected." } ] }, { "path": "en\/metabolonote\/data-1.html", "name": "Sample Set (SE)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-001", "description": "Information about a set of experimental data corresponding to the study purpose, including information regarding data interpretation and handling, such as which sample should be compared with which control, etc.", "files": [ { "file_name": "metabolonote_sample_set.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_sample_set.zip", "file_size": "41 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_sample_set#en", "data_acquisition": "", "analysis": "", "data_number": "52 entries", "details": [ { "name": "Sample Set ID", "description": "Sample set ID" }, { "name": "Title", "description": "Sample set name" }, { "name": "Description", "description": "Describes important concepts for interpreting data, such as experiment purposes and relevancy between samples." }, { "name": "Authors", "description": "Author" }, { "name": "Reference", "description": "Related reference information" }, { "name": "Comment", "description": "Comment" }, { "name": "Experimental Conditions", "description": "Link to Experimental Conditions (only in Simple search)" } ] }, { "path": "en\/metabolonote\/data-2.html", "name": "Sample (S)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-002", "description": "Information about sample preparation methods.", "files": [ { "file_name": "metabolonote_sample.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_sample.zip", "file_size": "110 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_sample#en", "data_acquisition": "", "analysis": "", "data_number": "185 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Sample ID", "description": "Sample ID (\"Sample Set ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Sample name" }, { "name": "Organism - Scientific Name", "description": "Scientific name" }, { "name": "Organism - ID", "description": "Classification ID of the organism." }, { "name": "Compound - ID", "description": "Compound ID" }, { "name": "Compound - Source", "description": "Information about the availability of the reagent: the company name and catalog id." }, { "name": "Preparation", "description": "Growing methods, conditions, particular processing, sampling portions, sampling methods, and preparation methods for reagents" }, { "name": "Comment", "description": "Comment" }, { "name": "Analytical Method IDs", "description": "Link to Analytical Method (M) (only in Simple search)" } ] }, { "path": "en\/metabolonote\/data-3.html", "name": "Analytical Method (M)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-003", "description": "Information about methods of instrumental analysis.", "files": [ { "file_name": "metabolonote_analytical_method.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_analytical_method.zip", "file_size": "269 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_analytical_method#en", "data_acquisition": "", "analysis": "", "data_number": "527 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\", \"Analytical Method ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Analytical Method ID", "description": "Analysis method ID (\"Sample Set ID\", \"Analytical Method ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Analysis method name" }, { "name": "Analytical Method Details ID", "description": "Detailed analysis information ID (MS) applied. (\"Analytical Method Details ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Sample Amount", "description": "An amount of sample used.\r\nThis information is necessary for normalizing quantitative data to compare with other samples." }, { "name": "Comment", "description": "Comment" }, { "name": "Data Analysis IDs", "description": "Link to Data Analysis (D) (only in Simple search)" } ] }, { "path": "en\/metabolonote\/data-4.html", "name": "Data Analysis (D)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-004", "description": "Information about data analysis methods by using computational tools, etc.", "files": [ { "file_name": "metabolonote_data_analysis.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_data_analysis.zip", "file_size": "444 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_data_analysis#en", "data_acquisition": "", "analysis": "", "data_number": "915 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\", \"Data Analysis ID\", \"Sample ID\" and \"Analytical Method ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Data Analysis ID", "description": "Data analysis method ID (\"Sample Set ID\", \"Data Analysis ID\", \"Sample ID\" and \"Analytical Method ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Data analysis method name" }, { "name": "Data Analysis Details ID", "description": "Detailed data analysis method information ID (DS) applied. (\"Data Analysis Details ID\" and \"Sample ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Recommended decimal places of mass", "description": "Number of significant figures." }, { "name": "Comment", "description": "Comment" } ] }, { "path": "en\/metabolonote\/data-5.html", "name": "Analytical Method Details (MS)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-005", "description": "Detailed information regarding analysis methods commonly applied to several analysis experiments, including information about what kind of devices were used under what kind of settings, etc.\r\nReferred to by M (Method of Instrumental Analysis information).", "files": [ { "file_name": "metabolonote_analytical_method_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_analytical_method_details.zip", "file_size": "73 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_analytical_method_details#en", "data_acquisition": "", "analysis": "", "data_number": "65 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\" and \"Analytical Method Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Analytical Method Details ID", "description": "Detailed analysis information ID (\"Sample Set ID\" and \"Analytical Method Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Detailed analysis information name" }, { "name": "Instrument", "description": "Instrument name and vendor name" }, { "name": "Instrument Type", "description": "Instrument type" }, { "name": "Ionization Method", "description": "Ionization method" }, { "name": "Ion Mode", "description": "Distinction of positive analysis and negative analysis" }, { "name": "Description", "description": "Details about methods of instrumental analysis.\r\nDescribes all details regarding analytical instruments and analysis conditions." }, { "name": "Comment_of_details", "description": "Comment" } ] }, { "path": "en\/metabolonote\/data-6.html", "name": "Data Analysis Details (DS)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-006", "description": "Detailed information regarding data analysis methods commonly applied to several data analysis cases, including information about what kind of software programs were used with what kind of parameters, etc.\r\nReferred to by D (Data analysis information).", "files": [ { "file_name": "metabolonote_data_analysis_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_data_analysis_details.zip", "file_size": "67 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_data_analysis_details#en", "data_acquisition": "", "analysis": "", "data_number": "91 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\" and \"Data Analysis Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Data Analysis Details ID", "description": "Detailed analysis method information ID (\"Sample Set ID\" and \"Data Analysis Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Detailed analysis method information name" }, { "name": "Description", "description": "Describes all details regarding data analysis methods such as software programs used and the parameters adopted." }, { "name": "Comment_of_details", "description": "Comment" } ] }, { "path": "en\/metabolonote\/data-7.html", "name": "Annotation Method (AM)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-007", "description": "Information about method of metabolite peak annotation.", "files": [ { "file_name": "metabolonote_annotation_method_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_annotation_method_details.zip", "file_size": "26 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_annotation_method_details#en", "data_acquisition": "", "analysis": "", "data_number": "35 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\" and \"Annotation Method Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Annotation Method Details ID", "description": "Annotation method ID (\"Sample Set ID\" and \"Annotation Method Details ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Annotation method name" }, { "name": "Description", "description": "Describes details regarding annotation methods.\r\nDescribes standards by which annotation has been assigned." }, { "name": "Comment_of_details", "description": "Comment" } ] }, { "path": "en\/metabolonote\/data-8.html", "name": "Sample Preparation (SS)", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-008", "description": "Detailed information regarding sample preparations commonly applied to several samples, including information about growth conditions, drug treatments, etc.\r\nReferred to by S (Sample information).", "files": [ { "file_name": "metabolonote_sample_preparation_details.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_sample_preparation_details.zip", "file_size": "13 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_sample_preparation_details#en", "data_acquisition": "", "analysis": "", "data_number": "13 entries", "details": [ { "name": "Sample Set ID", "description": "Sample Set ID (\"Sample Set ID\" and \"Sample Preparation ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Sample Preparation ID", "description": "The sample preparation details ID (\"Sample Set ID\" and \"Sample Preparation ID\" are merged into \"ID\" in the Simple search.)" }, { "name": "Title", "description": "Sample preparation name" }, { "name": "Description", "description": "Details about sample preparation.\r\nIn the case of biological samples, for example, details of growth conditions and drug treatments are described. Descriptions that depend on analytical methods should not be included here, and they should be included in the details of analytical methods (MS)." }, { "name": "Comment_of_details", "description": "Comment" } ] }, { "path": "en\/metabolonote\/data-9.html", "name": "Experimental Conditions", "database_name": "Metabolonote", "doi": "10.18908\/lsdba.nbdc01324-009", "description": "It is the list of sample (S) with Analytical Method (M) and Data Analysis (D) etc.", "files": [ { "file_name": "metabolonote_experimental_conditions.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/metabolonote\/LATEST\/metabolonote_experimental_conditions.zip", "file_size": "15 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/metabolonote_experimental_conditions#en", "data_acquisition": "Some representative items such as \"Title\" are choosen and united from 8 data (Sample Set, Sample, Analytical Method, Analytical Method Details, Data Analysis, Data Analysis Details, Annotation Method, Sample Preparation).", "analysis": "", "data_number": "915 entries", "details": [ { "name": "Data Analysis ID", "description": "Data analysis method ID" }, { "name": "Sample Set ID", "description": "Sample Set ID (Not shown in the Simple search)" }, { "name": "Sample Set", "description": "Sample set name" }, { "name": "Sample ID", "description": "Sample ID (Not shown in the Simple search)" }, { "name": "Sample", "description": "Sample name" }, { "name": "Analytical Method ID", "description": "Analytical Method ID (Not shown in the Simple search)" }, { "name": "Sample Amount", "description": "An amount of sample used." }, { "name": "Sample Comment", "description": "Sample comment" }, { "name": "Analytical Method Details ID", "description": "Detailed analysis information ID (MS) applied. (Not shown in the Simple search)" }, { "name": "Analytical Method Details", "description": "Detailed analysis information name" }, { "name": "Data Analysis Details ID", "description": "Detailed analysis method information ID (Not shown in the Simple search)" }, { "name": "Data Analysis Details", "description": "Detailed analysis method information name" }, { "name": "Recommended decimal places of mass", "description": "Number of significant figures." }, { "name": "Annotation Method ID", "description": "Annotation method ID (Not shown in the Simple search)" }, { "name": "Annotation Method", "description": "Annotation method name" }, { "name": "Sample Preparation ID", "description": "The sample preparation details ID (Not shown in the Simple search)" }, { "name": "Sample Preparation", "description": "Sample preparation name" } ] }, { "path": "en\/microbedb\/data-1.html", "name": "BRC", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-001.V002", "description": "Metadata of strains in NBRC and JCM with the annotation results of ontologies (i.e., MCCV and MEO).\r\nData file (compressed in tar.gzip) consists of 2 directories (see the following table).", "files": [ { "file_name": "brc.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/brc.tar.gz", "file_size": "6.7 MB" } ], "togodb_url": "", "data_acquisition": "Metadata of strains were provided by NBRC and JCM in 2013 and 2016, respectively.", "analysis": "", "data_number": "1,183,864 triples", "details": [ { "name": "brc\/nbrc\/", "description": "Metadata of strains in NBRC." }, { "name": "brc\/jcm\/", "description": "Metadata of strains in JCM." } ] }, { "path": "en\/microbedb\/data-4.html", "name": "Ontology", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-004.V002", "description": "The ontology files that are used in MicrobeDB.jp version 2.\r\nData file (compressed in tar.gzip) consists of some directories (see the following table).", "files": [ { "file_name": "ontology.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/ontology.tar.gz", "file_size": "91 MB" } ], "togodb_url": "", "data_acquisition": "The MPO and MCCV files were obtained from a collaborator. The NCBI Taxonomy and INSDC ontology files were obtained from the DDBJ web site. Other ontologies were developed in this project.", "analysis": "", "data_number": "21,722,610 triples", "details": [ { "name": "ontology\/meo\/meo.ttl", "description": "An ontology for describing organismal habitats (especially focused on microbes)." }, { "name": "ontology\/meo\/meo_fma_mapping.ttl", "description": "An ontology mapping files that was mapped between MEO and FMA." }, { "name": "ontology\/msv\/msv.ttl", "description": "An ontology for describing several states of sampling environment for metagenome analyses." }, { "name": "ontology\/mdbv\/mdbv.rdf", "description": "A vocabulary for describing data schema in MicrobeDB.jp version 2." }, { "name": "ontology\/mgfo\/mgfo.ttl", "description": "An ontology for describing the gene function category that is used in MBGD." }, { "name": "ontology\/pdo\/pdo.owl", "description": "An ontology for describing both human infectious diseases caused by microbes and the diseases that is related to microbial infection." }, { "name": "ontology\/csso\/csso.owl", "description": "An ontology for describing clinical signs and symptoms." }, { "name": "ontology\/mpo\/mpo.ttl", "description": "An ontology for describing microbial phenotypes." }, { "name": "ontology\/mccv\/mccv.ttl", "description": "Structured controlled vocabulary for describing meta information of microbial culture collection maintained in biological resource centers." }, { "name": "ontology\/taxonomy\/taxonomy.ttl", "description": "Modified NCBI Taxonomy ontology for describing taxonomic relationships of organisms." }, { "name": "ontology\/insdc\/nucleotide.ttl", "description": "A vocabulary for describing metadata of INSDC entries." } ] }, { "path": "en\/microbedb\/data-5.html", "name": "Refsequence", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-005.V002", "description": "Microbial complete genome and high quality draft genome annotation RDF data. We used corresponding amino acid sequence data for MBGD ortholog clustering and functional assignments of metagenome data. Information on each replicon in the genomes are described in a RDF file using FALDO, SO, and other ontologies.\r\nData file (compressed in tar.gzip) consists of directories divided by genome. Each directory has a genome RDF file to indicate replicon.", "files": [ { "file_name": "refsequence.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/refseq.tar.gz", "file_size": "49 GB" } ], "togodb_url": "", "data_acquisition": "Microbial high quality draft (identified by using the MBGD criteria) and complete genome annotation data were obtained from NCBI RefSeq and GenBank.", "analysis": "", "data_number": "4,165,436,499 triples", "details": [] }, { "path": "en\/microbedb\/data-6.html", "name": "SRA", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-006.V002", "description": "Metadata and taxonomic\/functional compositions of 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples. Metadata were annotated by several ontologies (i.e., MEO, MSV, and NCBI Taxonomy).\r\nData file (compressed in tar.gzip) consists of some directories (see the following table).", "files": [ { "file_name": "sra.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/sra.tar.gz", "file_size": "8.4 GB" } ], "togodb_url": "", "data_acquisition": "Metadata and DNA sequence data of each 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing sample were obtained from INSDC DRA\/ERA\/SRA.", "analysis": "After quality filtering of reads, DNA sequence data of all 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples were phylogenetically analyzed by VITCOMIC2. Functional composition of metagenomic shotgun sequencing samples were analyzed by the combination of MetaGeneMark, GHOSTX, and Refsequences database.", "data_number": "1,926,303,942 triples", "details": [ { "name": "sra\/metadata\/meo_mapping\/", "description": "The MEO annotation results of 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/metadata\/msv_mapping\/", "description": "The MSV annotation results of 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/metadata\/host_taxonomy_mapping\/", "description": "The NCBI Taxonomy annotation results of host organisms of microbes for 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/metadata\/sra_description\/", "description": "The metadata descriptions of 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/sra\/function\/mbgd\/", "description": "The MBGD ortholog cluster composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/sra\/function\/mgfo\/", "description": "The MBGD ortholog functional composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/sra\/function\/ko\/", "description": "The KEGG ortholog composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/sra\/function\/pathway\/", "description": "The KEGG pathway composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/sra\/taxonomy\/", "description": "The taxonomic composition of 16S rRNA gene-based amplicon sequencing and metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA." }, { "name": "sra\/analysis\/env\/function\/mbgd\/", "description": "The MBGD ortholog cluster composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." }, { "name": "sra\/analysis\/env\/function\/mgfo\/", "description": "The MBGD ortholog function composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." }, { "name": "sra\/analysis\/env\/function\/ko\/", "description": "The KEGG ortholog composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." }, { "name": "sra\/analysis\/env\/function\/pathway\/", "description": "The KEGG pathway composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." }, { "name": "sra\/analysis\/env\/taxonomy\/meta16s\/", "description": "The taxonomic composition of 16S rRNA gene-based amplicon sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." }, { "name": "sra\/analysis\/env\/taxonomy\/metagenome\/", "description": "The taxonomic composition of metagenomic shotgun sequencing samples in INSDC DRA\/ERA\/SRA that were annotated to each MEO category." } ] }, { "path": "en\/microbedb\/data-7.html", "name": "Disease", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-007.V002", "description": "The PDO annotation results of microbes including pathogenic disease name, symptom, causal genes, and related taxa.", "files": [ { "file_name": "disease.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/disease.tar.gz", "file_size": "1.2 MB" } ], "togodb_url": "", "data_acquisition": "The information of pathogenic disease name, symptom, causal genes, and related taxa were obtained from literature.", "analysis": "", "data_number": "253,056 triples", "details": [] }, { "path": "en\/microbedb\/data-8.html", "name": "GOLD", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-008.V002", "description": "Annotation results of phenotypes of genome-sequenced microbes in JGI GOLD by using MPO.", "files": [ { "file_name": "gold.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/gold.tar.gz", "file_size": "882 KB" } ], "togodb_url": "", "data_acquisition": "Metadata of genome-sequenced microbes were obtained from JGI GOLD.", "analysis": "", "data_number": "138,948 triples", "details": [] }, { "path": "en\/microbedb\/data-9.html", "name": "NCBI", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-009.V002", "description": "The RDF data of several NCBI related data (i.e., BioProject, BioSample, PubMed, and Assembly) which are important to integrate data in MicrobeDB.jp version 2.\r\nData file (compressed in tar.gzip) consists of 4 directories (see the following table).", "files": [ { "file_name": "ncbi.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/ncbi.tar.gz", "file_size": "79 MB" } ], "togodb_url": "", "data_acquisition": "The data that are important to integrate data in MicrobeDB.jp version 2 were obtained by parsing XML and TSV format files in NCBI.", "analysis": "", "data_number": "14,905,682 triples", "details": [ { "name": "ncbi\/bioproject\/", "description": "The RDF files of metadata of NCBI BioProject." }, { "name": "ncbi\/biosample\/", "description": "The RDF files of metadata of NCBI BioSample with the annotations of MEO, MSV, and NCBI Taxonomy." }, { "name": "ncbi\/pubmed\/", "description": "The RDF files of metadata of PubMed." }, { "name": "ncbi\/assembly\/", "description": "The RDF files of metadata of Assembly Reports in NCBI Assembly." } ] }, { "path": "en\/microbedb\/data-10.html", "name": "Ortholog", "database_name": "MicrobeDB.jp", "doi": "10.18908\/lsdba.nbdc01181-010.V002", "description": "Microbial ortholog RDF data obtained from MBGD. Genome sequences of Refsequence data were used for ortholog clustering in MBGD. In those RDF files, the IDs and host phylogenetic information of genes belong to each ortholog cluster are described. Functional categories of the ortholog clusters are also described.", "files": [ { "file_name": "ortholog.tar.gz", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/microbedb\/LATEST\/ortholog.tar.gz", "file_size": "5.5 GB" } ], "togodb_url": "", "data_acquisition": "We obtained these ortholog RDF data from MBGD in January 2015.", "analysis": "", "data_number": "1,610,893,814 triples", "details": [] }, { "path": "en\/mouse-basement-membrane-bodymap\/data-1.html", "name": "Protein List", "database_name": "Mouse Basement Membrane Bodymap", "doi": "10.18908\/lsdba.nbdc00574-001", "description": "It is the list of basement membrane proteins shown in images.", "files": [ { "file_name": "matrixome_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/matrixome\/LATEST\/matrixome_protein.zip", "file_size": "2.1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/matrixome_protein", "data_acquisition": "", "analysis": "", "data_number": "42", "details": [ { "name": "Protein Category", "description": "Protein Category" }, { "name": "Protein Name", "description": "Protein Name" }, { "name": "Mouse Genomic Loci", "description": "Chromosome region of the mouse gene locus" }, { "name": "Human Genomic Loci", "description": "Chromosome region of the human gene locus" }, { "name": "Genbank Accession #", "description": "Genbank Accession Number of the coding region in the mRNA" }, { "name": "MGI", "description": "MGI ID of the gene" }, { "name": "Mouse Embryo", "description": "Age in days of mouse embryo (In simple search, it shows the link to mouse embryo image page)" }, { "name": "Antibody", "description": "Antibody to stain the target protein" }, { "name": "Validation", "description": "Validation result (medium or high)" } ] }, { "path": "en\/mouse-basement-membrane-bodymap\/data-2.html", "name": "AntiBody", "database_name": "Mouse Basement Membrane Bodymap", "doi": "10.18908\/lsdba.nbdc00574-002", "description": "It is the list of antibodies to stain the target proteins.", "files": [ { "file_name": "matrixome_antibody.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/matrixome\/LATEST\/matrixome_antibody.zip", "file_size": "1.3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/matrixome_antibody", "data_acquisition": "", "analysis": "", "data_number": "42", "details": [ { "name": "Protein Name", "description": "Protein Name" }, { "name": "Antibody Name", "description": "Antibody Name" }, { "name": "Producer \/ Vender", "description": "Producer \/ Vender" }, { "name": "Catalog #", "description": "Catalog #" }, { "name": "Immunization Species", "description": "Immunization Species" }, { "name": "Clonality", "description": "Clonality(monoclonal or polyclonal)" }, { "name": "Fixative", "description": "Fixative" }, { "name": "Hyaluronidase \/ Chondroitinase Treatment", "description": "Hyaluronidase \/ Chondroitinase Treatment" }, { "name": "Acid Treatment", "description": "Acid Treatment" }, { "name": "Validation Score", "description": "Validation result (medium or high)" }, { "name": "Validation", "description": "Detail of validation result" } ] }, { "path": "en\/mouse-basement-membrane-bodymap\/data-3.html", "name": "Bodymap", "database_name": "Mouse Basement Membrane Bodymap", "doi": "10.18908\/lsdba.nbdc00574-003", "description": "It is the collection of high resolution virtual slides created from gigapixel digital images of mouse embryo.\r\nSimple search has two interfaces, \"protein-based\" and \"tissue-based\".\r\nProtein-based search: http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/matrixome_bodymap_protein_based\r\nTissue-based search: http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/matrixome_bodymap_tissue_based\r\nTo view or download original images of virtual slides, see the following page.\r\nhttps:\/\/togodb.biosciencedbc.jp\/togodb\/view\/matrixome_bodymap_imagelist#en", "files": [ { "file_name": "images", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/matrixome\/images", "file_size": "278.6 GB" } ], "togodb_url": "", "data_acquisition": "Whole mouse sagittal and head frontal sections were immunohistochemically stained with the antibody against each target protein, and their adjacent sections were stained with hematoxylin\/eosin. And they are shown zoomed for each tissue.\r\nPlease see for detail:\r\nhttp:\/\/dbarchive.biosciencedbc.jp\/archive\/matrixome\/bm\/AboutBodymap\/Production\/production.html", "analysis": "", "data_number": "246", "details": [] }, { "path": "en\/rice-tos17-insertion\/data-1.html", "name": "plant", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-001.V001", "description": "Phenotype description of Tos17 insertion lines", "files": [ { "file_name": "tos17_plant.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_plant.csv.zip", "file_size": "1.4 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tos17_plant#en", "data_acquisition": "Individuals of line have been observed in the field.", "analysis": "Description of phenotype and photograph are listed.", "data_number": "181289", "details": [ { "name": "plant", "description": "Line name" }, { "name": "sub", "description": "Individual number" }, { "name": "date", "description": "observed date" }, { "name": "image", "description": "image file name" }, { "name": "comment_j", "description": "comment Japanese" }, { "name": "comment_e", "description": "comment English" }, { "name": "phenotype", "description": "keyword of phenotype" } ] }, { "path": "en\/rice-tos17-insertion\/data-2.html", "name": "def_phenotype", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-002.V001", "description": "Definition of phenotype.", "files": [ { "file_name": "tos17_def_phenotype.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_def_phenotype.csv.zip", "file_size": "1.4 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tos17_def_phenotype#en", "data_acquisition": "", "analysis": "", "data_number": "53", "details": [ { "name": "id", "description": "Phenotype ID" }, { "name": "category_j", "description": "Category in Japanese" }, { "name": "category_e", "description": "Category in English" }, { "name": "description_j", "description": "Phenotype name in Japanese" }, { "name": "description_e", "description": "Phenotype name in English" }, { "name": "comment", "description": "comment" } ] }, { "path": "en\/rice-tos17-insertion\/data-3.html", "name": "phenotype", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-003.V001", "description": "List of line name showing phenotype.", "files": [ { "file_name": "tos17_phenotype.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_phenotype.csv.zip", "file_size": "213 KB" } ], "togodb_url": "", "data_acquisition": "Categorized by phenotypic descriptions from plant table.", "analysis": "", "data_number": "85828", "details": [ { "name": "id", "description": "Phenotype ID" }, { "name": "name", "description": "Strain Name" } ] }, { "path": "en\/rice-tos17-insertion\/data-4.html", "name": "seq", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-004.V001", "description": "Table of sequence name, line name and accession number.", "files": [ { "file_name": "tos17_seq.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_seq.csv.zip", "file_size": "550 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tos17_seq#en", "data_acquisition": "", "analysis": "", "data_number": "93215", "details": [ { "name": "Sequence Name", "description": "Sequence name" }, { "name": "Line Name", "description": "Line name" }, { "name": "Accession", "description": "Accession number" } ] }, { "path": "en\/rice-tos17-insertion\/data-5.html", "name": "tos17_insertion", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-005.V001", "description": "Insertion position of Tos17 relative to the rice genome reference sequence (Nipponbare, IRGSP-1.0) in each mutant line", "files": [ { "file_name": "tos17_tos17_insertion.csv.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_tos17_insertion.csv.zip", "file_size": "751 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tos17_tos17_insertion#en", "data_acquisition": "A BLASTN search of Tos17 insertion adjacent sequence (flanking) was performed against IRGSP-1.0 to obtain Tos17 insertion position.", "analysis": "", "data_number": "82790", "details": [ { "name": "Chromosome", "description": "Chromosome number" }, { "name": "Position", "description": "Position of Tos17 insertion" }, { "name": "Direction", "description": "Direction of Tos17" }, { "name": "E-value", "description": "E-value" }, { "name": "Line name", "description": "Line name" }, { "name": "Sequence Name", "description": "Name of Tos17 flanking sequence" } ] }, { "path": "en\/rice-tos17-insertion\/data-6.html", "name": "flanking", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-006.V001", "description": "Fasta format file of Tos17 flanking sequence", "files": [ { "file_name": "tos17_flanking.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_flanking.zip", "file_size": "11 MB" } ], "togodb_url": "", "data_acquisition": "Experiment", "analysis": "Flanking DNA fragments of Tos17 were amplified by TAIL-PCR or Suppression PCR. Fragments were separated by agarose gel electrophoresis. And then nucleotide sequences were determined by Sanger method.", "data_number": "93262", "details": [] }, { "path": "en\/rice-tos17-insertion\/data-7.html", "name": "photograph", "database_name": "Mutant Panel", "doi": "10.18908\/lsdba.nbdc00229-007.V001", "description": "Photograph of mutant phenotype.", "files": [ { "file_name": "tos17_photograph.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/rice-tos17-insertion\/LATEST\/tos17_photograph.zip", "file_size": "17 GB" } ], "togodb_url": "", "data_acquisition": "Lines were observed in the field.", "analysis": "Photographs from 5 to 25 individuals of Tos17 insertion lines in the field and seeds have been taken.", "data_number": "59376", "details": [] }, { "path": "en\/nikkaji\/data-1.html", "name": "Basic Information", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-001.V011", "description": "This RDF data contains the basic information of 3.6 million or more chemical substances, such as Nikkaji Number, molecular formula, molecular weight, and English\/Japanese name.", "files": [ { "file_name": "NBDC_NikkajiRDF_main.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_main.tar.gz", "file_size": "1.0 GB" } ], "togodb_url": "", "data_acquisition": "This RDF is described by using widely used terms and ontologies, such as rdfs:label, rdf:type, owl:sameAs, dcterms:identifier, and foaf:depiction.", "analysis": "", "data_number": "3,671,776 compounds", "details": [] }, { "path": "en\/nikkaji\/data-2.html", "name": "InChI and InChIKey", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-002.V011", "description": "This RDF data contains InChI and InChIKey of chemical substances registered in Nikkaji by using CHEMINF, SIO and other ontologies. We recommend using this RDF together with the Core RDF.", "files": [ { "file_name": "NBDC_NikkajiRDF_InChI.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_InChI.tar.gz", "file_size": "510 MB" } ], "togodb_url": "", "data_acquisition": "InChI and InChIKey were obtained from J-GLOBAL Chemical Substance Database. Only available for substances with 'Substance Type: Decided Structure'.", "analysis": "", "data_number": "3,493,208 compounds", "details": [] }, { "path": "en\/nikkaji\/data-3.html", "name": "Canonical SMILES", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-003.V011", "description": "This RDF data contains canonical SMILES of chemical substances registered in Nikkaji by using CHEMINF, SIO and other ontologies. We recommend using this RDF together with the Core RDF.", "files": [ { "file_name": "NBDC_NikkajiRDF_SMILES.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_SMILES.tar.gz", "file_size": "149 MB" } ], "togodb_url": "", "data_acquisition": "Canonical SMILES were obtained from J-GLOBAL Chemical Substance Database. Only available for substances with 'Substance Type: Decided Structure'.", "analysis": "", "data_number": "3,493,208 compounds", "details": [] }, { "path": "en\/nikkaji\/data-4.html", "name": "Links to J-GLOBAL", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-004.V011", "description": "This RDF data includes information of links to other databases, such as J-GLOBAL which contains information of chemical substances, genes, researchers, literature, patents, and other scientific and technologies information (http:\/\/jglobal.jst.go.jp\/).", "files": [ { "file_name": "NBDC_NikkajiRDF_link2JGLOBAL.ttl.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_link2JGLOBAL.ttl.gz", "file_size": "1.8 MB" } ], "togodb_url": "", "data_acquisition": "This RDF data was constructed from the data collected by J-GLOBAL knowledge （https:\/\/stirdf.jglobal.jst.go.jp\/ :closed in 2018）.", "analysis": "", "data_number": "219,663 triples", "details": [] }, { "path": "en\/nikkaji\/data-5.html", "name": "Molecular Formula and Molecular Weight", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-005.V011", "description": "This RDF data contains molecular formula and molecular weight of chemical substances registered in Nikkaji by using CHEMINF, SIO and other ontologies.", "files": [ { "file_name": "NBDC_NikkajiRDF_MFMW.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_MFMW.tar.gz", "file_size": "507 MB" } ], "togodb_url": "", "data_acquisition": "The data was converted from data of molecular formulas and molecular weights in Basic Information (http:\/\/dbarchive.biosciencedbc.jp\/en\/nikkaji\/data-1.html).", "analysis": "", "data_number": "3,671,776 compounds", "details": [] }, { "path": "en\/nikkaji\/data-6.html", "name": "Links to Other DBs (based on UniChem)", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-006.V011", "description": "This RDF data includes information of links between Nikkaji substances and chemical substances registered in other databases* by using skos:closeMatch. This is based on a work at https:\/\/www.ebi.ac.uk\/unichem\/ .\r\n*: ChEMBL, DrugBank, PDB, Guide to Pharmacology, KEGG, ChEBI, ZINC, Gene Expression Atlas, PharmGKB, Human Metabolome Database (HMDB), PubChem, NMRShiftDB, Aggregated Computational Toxicology Resource (ACToR), BindingDB, and KNApSAcK.", "files": [ { "file_name": "NBDC_NikkajiRDF_link2OtherDBs_basedOnUniChem.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_link2OtherDBs_basedOnUniChem.tar.gz", "file_size": "69 MB" } ], "togodb_url": "", "data_acquisition": "The data was created from the mapping data between Nikkaji substances, and chemical substances in other databases which were acquired using UniChem FTP service (ftp:\/\/ftp.ebi.ac.uk\/pub\/databases\/chembl\/UniChem\/). The mapping data between Nikkaji and KNApSAcK substances was created using the InChIKey provided by KNApSAcK (http:\/\/kanaya.naist.jp\/KNApSAcK\/).", "analysis": "", "data_number": "18,910,927 triples", "details": [] }, { "path": "en\/nikkaji\/data-7.html", "name": "Links to Other DBs (based on PubChem)", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-007.V011", "description": "This RDF data includes information of links between Nikkaji substances and PubChem substances, compounds and GlyTouCan (https:\/\/glytoucan.org\/) by using skos:exactMatch and skos:closeMatch. This is a result of BioHackathon 2015 (http:\/\/2015.biohackathon.org\/hackathon).", "files": [ { "file_name": "NBDC_NikkajiRDF_link2OtherDBs_basedOnPubChem.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_link2OtherDBs_basedOnPubChem.tar.gz", "file_size": "49 MB" } ], "togodb_url": "", "data_acquisition": "The data was created from the mapping data between Nikkaji substances, and PubChem substances, and compounds which were acquired using UniChem FTP service (https:\/\/pubchem.ncbi.nlm.nih.gov\/upload\/).", "analysis": "", "data_number": "34,671,881 triples", "details": [] }, { "path": "en\/nikkaji\/data-8.html", "name": "Core", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-008.V011", "description": "This RDF data contains the core information of chemical substances such as NIkkaji Number, English\/Japanese label, Type, Chemical structure diagram, and same object which were extracted extracted from the Basic Information RDF. We recommend using this RDF together with the 'InChI and InChIKey' 'Canonical SMILES' or 'MOL\/SDF' RDF.", "files": [ { "file_name": "NBDC_NikkajiRDF_core.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_core.tar.gz", "file_size": "308 MB" } ], "togodb_url": "", "data_acquisition": "This RDF data were created from the Basic Information RDF.", "analysis": "", "data_number": "3,671,776 compounds", "details": [] }, { "path": "en\/nikkaji\/data-9.html", "name": "MOL\/SDF", "database_name": "NBDC Nikkaji RDF", "doi": "10.18908\/lsdba.nbdc01530-02-009.V011", "description": "This RDF data contains the URL-encoded content of MOL\/SDF files of chemical substances registered in Nikkaji by using CHEMINF, SIO and other ontologies. We recommend using this RDF together with the Core RDF.", "files": [ { "file_name": "NBDC_NikkajiRDF_SDF.tar.gz", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/nikkaji\/LATEST\/NBDC_NikkajiRDF_SDF.tar.gz", "file_size": "957MB" } ], "togodb_url": "", "data_acquisition": "MOL\/SDF informations were obtained from J-GLOBAL Chemical Substance Database. Only available for substances with 'Substance Type: Decided Structure'.", "analysis": "", "data_number": "3,493,208 compounds", "details": [] }, { "path": "en\/nikkaji-inchi-mapping\/data-1.html", "name": "Nikkaji Number-InChI", "database_name": "Nikkaji-InChI Mapping Table", "doi": "10.18908\/lsdba.nbdc01530-01-001.V004", "description": "Mapping data among Nikkaji Number, InChI, and InChIKey.", "files": [ { "file_name": "nikkaji_inchi_mapping.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/nikkaji-inchi-mapping\/LATEST\/nikkaji_inchi_mapping.zip", "file_size": "218 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/nikkaji_inchi_mapping#en", "data_acquisition": "InChI and InChIKey are generated from SDF by IUPAC InChI Software v.1.0.4 (http:\/\/www.inchi-trust.org\/downloads\/).", "analysis": "", "data_number": "3,485,917 entries", "details": [ { "name": "Nikkaji Number", "description": "Identifier of Chemical Substances in Nikkaji" }, { "name": "InChI", "description": "IUPAC International Chemical Identifier" }, { "name": "InChIKey", "description": "IUPAC International Chemical Identifier Key" } ] }, { "path": "en\/nucleic-acid-drug\/data-1.html", "name": "Original Data", "database_name": "Oligonucleic Acid Drug Database", "doi": "10.18908\/lsdba.nbdc02343-001.V003", "description": "The list of nucleic acid drugs (contains unapproved one) and its statistics information\r\n(Excel format)", "files": [ { "file_name": "NucleicAcidDrugList.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/nucleic-acid-drug\/LATEST\/NucleicAcidDrugList.zip", "file_size": "55 KB" } ], "togodb_url": "", "data_acquisition": "Acquired information on nucleic acid drugs from pharmaceutical company and clinical information site (https:\/\/clinicaltrials.gov\/, https: \/\/www.clinicaltrialsregister.eu\/).\r\nAlso acquired information on approved nucleic acid drugs from FDA, EMA, PMDA and KEGG.", "analysis": "The related proteins, diseases and pathway information are obtained from scientific papers and pathway related DBs.", "data_number": "43 entries", "details": [] }, { "path": "en\/nucleic-acid-drug\/data-2.html", "name": "Oligonucleic Acid Drug List", "database_name": "Oligonucleic Acid Drug Database", "doi": "10.18908\/lsdba.nbdc02343-002.V003", "description": "The list of oligonucleic acid drug (contains unapproved one)", "files": [ { "file_name": "nucleic_acid_drug_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/nucleic-acid-drug\/LATEST\/nucleic_acid_drug_list.zip", "file_size": "12 KB" }, { "file_name": "nucleic_acid_drug_list_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/nucleic-acid-drug\/LATEST\/nucleic_acid_drug_list_en.zip", "file_size": "11 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/nucleic_acid_drug_list_en", "data_acquisition": "The approved nucleic acid drug information is from FDA, EMA, PMDA, KEGG.", "analysis": "Acquisition of Phase (I-III) information from clinical information site (https:\/\/clinicaltrials.gov\/, http:\/\/www.clinicaltrialsregister.eu\/)", "data_number": "43 entries", "details": [ { "name": "Medals oligonucleic drug ID", "description": "Medals oligonucleic drug ID (issued by MEDALS)" }, { "name": "ATC Classification", "description": "ATC classification" }, { "name": "Product Name", "description": "Product name" }, { "name": "Synonims", "description": "Synonims" }, { "name": "Country", "description": "Country" }, { "name": "Company", "description": "Company" }, { "name": "Phase", "description": "AD: Approved\r\nI-III: PhaseI-III\r\nR: Rejected" }, { "name": "Type", "description": "Nucleotide type" }, { "name": "Adaptation Diseases", "description": "Adaptation diseases" }, { "name": "Target Molecule", "description": "Target molecule" }, { "name": "Remarks", "description": "Remarks" }, { "name": "Nucleic Acid Sequence", "description": "Nucleic acid sequence" }, { "name": "Source", "description": "Source" }, { "name": "DrugBank", "description": "DrugBank ID" }, { "name": "TargetProtein - UniProt", "description": "TargetProtein - UniProt ID" }, { "name": "TargetProtein - PDB", "description": "TargetProtein - PDB ID" } ] }, { "path": "en\/open-tggates\/data-1.html", "name": "Compound list", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-001", "description": "Compiled list of compounds and links to gene expression data and its attribute information of each compound in Open TG-GATEs.", "files": [ { "file_name": "open_tggates_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_main.zip", "file_size": "6.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_main#en", "data_acquisition": "", "analysis": "", "data_number": "170 entries", "details": [ { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "COMPOUND_ABBREVIATION", "description": "Abbreviated compound name" }, { "name": "COMPOUND_NO", "description": "Number assigned to each compound. Numbers are not in serial order." }, { "name": "Human - in vitro", "description": "Gene expression data of in vitro tests with human liver cells (Link to a zip file which contains multiple CEL files)" }, { "name": "Rat - in vitro", "description": "Gene expression data of in vitro tests with rat liver cells (Link to a zip file which contains multiple CEL files)" }, { "name": "Rat - in vivo - Liver - Single", "description": "Gene expression data of single-dose in vivo tests with rat liver (Link to a zip file which contains multiple CEL files)" }, { "name": "Rat - in vivo - Liver - Repeat", "description": "Gene expression data of repeat-dose in vivo tests with rat liver (Link to a zip file which contains multiple CEL files)" }, { "name": "Rat - in vivo - Kidney - Single", "description": "Gene expression data of single-dose in vivo tests with rat kidney (Link to a zip file which contains multiple CEL files)" }, { "name": "Rat - in vivo - Kidney - Repeat", "description": "Gene expression data of repeat-dose in vivo tests with rat kidney (Link to a zip file which contains multiple CEL files)" }, { "name": "Pathological items (Liver)", "description": "Pathological findings and slide images of in vivo tests with rat liver (Link to \"Pathological items\", \"Pathological images\" and \"CEL file attributes\")" }, { "name": "Pathological items (Kidney)", "description": "Pathological findings and slide images of in vivo tests with rat kidney (Link to \"Pathological items\", \"Pathological images\" and \"CEL file attributes\")" } ] }, { "path": "en\/open-tggates\/data-2.html", "name": "Gene expression data (CEL files)", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-002", "description": "CEL files available in Open TG-GATEs are grouped by the test, and then they are compressed separately into a zip file. In each zip file, a CEL file attribute file in Tab Separated Value (TSV) format is included.\r\nCEL is one of the file formats that expresses gene expression data (raw data) generated from Affymetrix GeneChip®.", "files": [ { "file_name": "Gene expression data from rat samples", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/Rat\/", "file_size": "12.0GB total" }, { "file_name": "Gene expression data from human samples", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/Human\/", "file_size": "53.6GB total" } ], "togodb_url": "", "data_acquisition": "Gene expression data were generated from Affymetrix GeneChip®. In vivo data were acquired from three rats with body weights close to the average of each group (five rats).", "analysis": "", "data_number": "ZIP files: 686 files\r\nCEL files: 24,023 files", "details": [] }, { "path": "en\/open-tggates\/data-3.html", "name": "CEL file attributes", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-003", "description": "List of attribute information explain about each CEL file.", "files": [ { "file_name": "open_tggates_cel_file_attribute.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_cel_file_attribute.zip", "file_size": "199 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_cel_file_attribute#en", "data_acquisition": "", "analysis": "", "data_number": "24,023 entries", "details": [ { "name": "BARCODE", "description": "Bar-code assigned to each GeneChip in order to indentify. Bar-code matches CEL file name without extension." }, { "name": "ARR_DESIGN", "description": "In the project, HG-U133_Plus_2 was used for human and Rat230_2 was used for rat." }, { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual\/sample within a group. IDs are in single digit." }, { "name": "ORGAN", "description": "Organ evaluated in tests. Liver or Kidney." }, { "name": "MATERIAL_ID", "description": "ID assigned to each tissue section which was used to acquire gene expression data. IDs are in a single letter." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "COMPOUND_ABBREVIATION", "description": "Abbreviated compound name" }, { "name": "COMPOUND_NO", "description": "Number assigned to each compound. Numbers are not in serial order." }, { "name": "SPECIES", "description": "Species" }, { "name": "EXP_TEST_TYPE", "description": "Type of test. In vivo test or in vitro test." }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "STRAIN_TYPE", "description": "Rat strain used with in vivo tests" }, { "name": "ADMINISTRATION_ROUTE_TYPE", "description": "Administration route" }, { "name": "ANIMAL_AGE(week)", "description": "Age of animal (weeks). Only rats at 6 weeks of age were used." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." } ] }, { "path": "en\/open-tggates\/data-4.html", "name": "Cell sample", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-004", "description": "The list of liver cell samples from which gene expression and toxicity (cell viability) data were acquired.", "files": [ { "file_name": "open_tggates_cell.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_cell.zip", "file_size": "54 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_cell#en", "data_acquisition": "", "analysis": "", "data_number": "5,990 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each sample within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SPECIES", "description": "Species" }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "SACRIFICE_PERIOD", "description": "Duration of exposure on in vitro test." }, { "name": "DOSE", "description": "Concentration" }, { "name": "DOSE_UNIT", "description": "Unit of concentration" }, { "name": "DOSE_LEVEL", "description": "Exposure level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "BARCODE", "description": "Link to \"CEL file attributes\"" }, { "name": "CELL_VIABILITY", "description": "Link to \"Cell viability\"" } ] }, { "path": "en\/open-tggates\/data-5.html", "name": "Cell viability", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-005", "description": "The list of liver cell viability data obtained from in vitro tests.", "files": [ { "file_name": "open_tggates_cell_viablity.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_cell_viability.zip", "file_size": "51 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_cell_viability#en", "data_acquisition": "", "analysis": "", "data_number": "5,986 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each sample within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SPECIES", "description": "Species" }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "SACRIFICE_PERIOD", "description": "Duration of exposure on in vitro test." }, { "name": "DOSE", "description": "Concentration" }, { "name": "DOSE_UNIT", "description": "Unit of concentration" }, { "name": "DOSE_LEVEL", "description": "Exposure level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "DNA(%)", "description": "Relative survival rate calculated from DNA content." }, { "name": "LDH(%)", "description": "Relative survival rate calculated from the activity value of lactate dehydrogenase which is leaked in the culture supernatant." } ] }, { "path": "en\/open-tggates\/data-6.html", "name": "Individual list", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-006", "description": "The list of rats from which gene expression and toxicity data were acquired.", "files": [ { "file_name": "open_tggates_individual.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_individual.zip", "file_size": "97 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_individual#en", "data_acquisition": "", "analysis": "", "data_number": "23,868 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "STRAIN_TYPE", "description": "Rat strain used with in vivo tests" }, { "name": "ADMINISTRATION_ROUTE_TYPE", "description": "Administration route" }, { "name": "ANIMAL_AGE(week)", "description": "Age of animal (weeks). Only rats at 6 weeks of age were used." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "BARCODE (Liver)", "description": "Link to \"CEL file attributes (Liver)\"" }, { "name": "BARCODE (Kidney)", "description": "Link to \"CEL file attributes (Kidney)\"" }, { "name": "HEMATOLOGY", "description": "Link to \"Hematology\"" }, { "name": "BIOCHEMISTRY", "description": "Link to \"Biochemistry\"" }, { "name": "ORGAN_WEIGHT", "description": "Link to \"Organ weight\"" }, { "name": "BODY_WEIGHT", "description": "Link to \"Body weight\"" }, { "name": "FOOD_CONSUMPTION", "description": "Link to \"Food consumption\"" }, { "name": "PATHOLOGY (Liver)", "description": "Link to \"Pathological items (Liver)\"" }, { "name": "PATHOLOGY (Kidney)", "description": "Link to \"Pathological items (Kidney)\"" }, { "name": "PATHOLOGICAL_IMAGE (Liver)", "description": "Link to \"Pathological images (Liver)\"" }, { "name": "PATHOLOGICAL_IMAGE (Kidney)", "description": "Link to \"Pathological images (Kidney)\"" } ] }, { "path": "en\/open-tggates\/data-7.html", "name": "Organ weight", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-007", "description": "The list of organ weights acquired from in vivo tests. Information of terminal body weights is also included.", "files": [ { "file_name": "open_tggates_organ_weight.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_organ_weight.zip", "file_size": "379 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_organ_weight#en", "data_acquisition": "", "analysis": "", "data_number": "23,669 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "STRAIN_TYPE", "description": "Rat strain used with in vivo tests" }, { "name": "ADMINISTRATION_ROUTE_TYPE", "description": "Administration route" }, { "name": "ANIMAL_AGE(week)", "description": "Age of animal (weeks). Only rats at 6 weeks of age were used." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "TERMINAL_BW(g)", "description": "Terminal body weight" }, { "name": "LIVER(g)", "description": "The weight of the liver" }, { "name": "KIDNEY_TOTAL(g)", "description": "The total weight of the kidneys" }, { "name": "KIDNEY_R(g)", "description": "The weight of the right kidney" }, { "name": "KIDNEY_L(g)", "description": "The weight of the left kidney" } ] }, { "path": "en\/open-tggates\/data-8.html", "name": "Hematology", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-008", "description": "The list of hematological assessment data acquired from rats used in the in vivo tests.", "files": [ { "file_name": "open_tggates_hematology.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_hematology.zip", "file_size": "636 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_hematology#en", "data_acquisition": "", "analysis": "", "data_number": "23,642 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "RBC(x10_4\/ul)", "description": "red blood cell count" }, { "name": "Hb(g\/dL)", "description": "hemoglobin" }, { "name": "Ht(%)", "description": "hematocrit value" }, { "name": "MCV(fL)", "description": "mean corpuscular volume" }, { "name": "MCH(pg)", "description": "mean corpuscular hemoglobin" }, { "name": "MCHC(%)", "description": "mean corpuscular hemoglobin concentration" }, { "name": "Ret(%)", "description": "reticulocyte" }, { "name": "Plat(x10_4\/uL)", "description": "platelet count" }, { "name": "WBC(x10_2\/uL)", "description": "white blood cell count" }, { "name": "Neu(%)", "description": "neutrophil" }, { "name": "Eos(%)", "description": "eosinophil" }, { "name": "Bas(%)", "description": "basophil" }, { "name": "Mono(%)", "description": "monocyte" }, { "name": "Lym(%)", "description": "lymphocyte" }, { "name": "PT(s)", "description": "prothrombin time" }, { "name": "APTT(s)", "description": "activated partial thromboplastin time" }, { "name": "Fbg(mg\/dL)", "description": "fibrinogen" } ] }, { "path": "en\/open-tggates\/data-9.html", "name": "Biochemistry", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-009", "description": "The list of biochemical test data acquired from rats used in the in vivo tests.", "files": [ { "file_name": "open_tggates_biochemistry.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_biochemistry.zip", "file_size": "666 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_biochemistry#en", "data_acquisition": "", "analysis": "", "data_number": "23,643 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "ALP(IU\/L)", "description": "alkaline phosphatase" }, { "name": "TC(mg\/dL)", "description": "total cholesterol" }, { "name": "TG(mg\/dL)", "description": "triglyceride" }, { "name": "PL(mg\/dL)", "description": "phospholipid" }, { "name": "TBIL(mg\/dL)", "description": "total bilirubin" }, { "name": "DBIL(mg\/dL)", "description": "direct bilirubin" }, { "name": "GLC(mg\/dL)", "description": "glucose" }, { "name": "BUN(mg\/dL)", "description": "blood urea nitrogen" }, { "name": "CRE(mg\/dL)", "description": "creatinine" }, { "name": "Na(meq\/L)", "description": "sodium" }, { "name": "K(meq\/L)", "description": "potassium" }, { "name": "Cl(meq\/L)", "description": "chlorine" }, { "name": "Ca(mg\/dL)", "description": "calcium" }, { "name": "IP(mg\/dL)", "description": "inorganic phosphorus" }, { "name": "TP(g\/dL)", "description": "total protein" }, { "name": "RALB(g\/dL)", "description": "albumin" }, { "name": "A\/G", "description": "albumin globulin ratio" }, { "name": "AST(IU\/L)", "description": "aspartate aminotransferase" }, { "name": "ALT(IU\/L)", "description": "alanine aminotransferase" }, { "name": "LDH(IU\/L)", "description": "lactate dehydrogenase" }, { "name": "GTP(IU\/L)", "description": "γ-glutamyltranspeptidase" } ] }, { "path": "en\/open-tggates\/data-10.html", "name": "Body weight", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-010", "description": "Serial measurement of body weights of rats used in the in vivo tests. Information of slaughter weight is included in \"Organ Weight\".", "files": [ { "file_name": "open_tggates_body_weight.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_body_weight.zip", "file_size": "339 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_body_weight#en", "data_acquisition": "", "analysis": "", "data_number": "66,376 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "PROGRESS_TIME", "description": "Measurement date of body weight. The unit is day. The day when the administration was started is counted as day 1." }, { "name": "BODY_WEIGHT", "description": "Body weight of the rat on the day of PROGRESS_TIME. The unit is gram." } ] }, { "path": "en\/open-tggates\/data-11.html", "name": "Food consumption", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-011", "description": "The list regarding results of food consumption measurement acquired from rats used in the in vivo tests.", "files": [ { "file_name": "open_tggates_food_consumption.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_food_consumption.zip", "file_size": "108 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_food_consumption#en", "data_acquisition": "The amount of daily food intake of the first day is calculated as the amount of food taken during one day before the administration start. After the first day, the amount of food intake is measured in every three or four days. The amount of daily food intake is the average from the last measurement date.", "analysis": "", "data_number": "25,248 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "PROGRESS_TIME", "description": "Measurement date of food consumption. The unit is day. The day when the administration was started is counted as day 1." }, { "name": "FC_AMOUNT", "description": "The amount of daily food intake. The unit is gram per day (g\/day)." } ] }, { "path": "en\/open-tggates\/data-12.html", "name": "Pathological items", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-012", "description": "The list of pathological findings obtained from in vivo tests.", "files": [ { "file_name": "open_tggates_pathology.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/open_tggates_pathology.zip", "file_size": "89 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_pathology#en", "data_acquisition": "We prepared hematoxylin-eosin-stained specimen slides and then performed histopathological examination by optical microscopy.", "analysis": "", "data_number": "12,861 entries", "details": [ { "name": "BARCODE", "description": "Bar-code assigned to each GeneChip in order to indentify. Bar-code matches CEL file name without extension. Data with the value \"No ChipData\" don't have a corresponding CEL file since the microarray gene expression analysis wasn't performed." }, { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "ORGAN", "description": "Organ evaluated in tests. Liver or Kidney." }, { "name": "FINDING_TYPE", "description": "Pathological findings." }, { "name": "TOPOGRAPHY_TYPE", "description": "Region of the organ where the pathological changes were found." }, { "name": "GRADE_TYPE", "description": "Magnitude of pathological changes. The ascending order of the magnitude is P(present), minimal, slight, moderate, severe." }, { "name": "SP_FLG", "description": "The flag shows whether the lesion occurred spontaneously. The flag value is \"1\" if the lesion occurred spontaneously." }, { "name": "PATHOLOGICAL_IMAGE", "description": "Link to \"Pathological images\"" } ] }, { "path": "en\/open-tggates\/data-13.html", "name": "CEL file attachments", "database_name": "Open TG-GATEs", "doi": "10.18908\/lsdba.nbdc00954-01-013", "description": "This dataset merged seven datasets (CEL file attributes, Cell sample, Cell viability, Individual list, Organ weight, Hematology, and Biochemistry) into one. Each zip file you can download from \"Gene expression data\", includes the related part of this dataset as a TSV file named \"Attributes.tsv\".", "files": [ { "file_name": "Open-tggates_AllAttribute.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates\/LATEST\/Open-tggates_AllAttribute.zip", "file_size": "1.8 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_attribute#en", "data_acquisition": "", "analysis": "", "data_number": "33,566 entries", "details": [ { "name": "BARCODE", "description": "Bar-code assigned to each GeneChip in order to indentify. Bar-code matches CEL file name without extension. Data with the value \"No ChipData\" don't have a corresponding CEL file since the microarray gene expression analysis wasn't performed." }, { "name": "ARR_DESIGN", "description": "In the project, HG-U133_Plus_2 was used for human and Rat230_2 was used for rat." }, { "name": "EXP_ID", "description": "ID assigned to each test which can be indentified by a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are assigned from #0040. IDs for in vitro tests are assigned from #5000." }, { "name": "GROUP_ID", "description": "ID assigned to each group which can be indentified by a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "ORGAN", "description": "Organ evaluated in tests. Liver or Kidney." }, { "name": "MATERIAL_ID", "description": "ID assigned to each tissue section which was used to acquire gene expression data. IDs are in a single letter." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "COMPOUND_ABBREVIATION", "description": "Abbreviated compound name" }, { "name": "COMPOUND_NO", "description": "Number assigned to each compound. Numbers are not in serial order." }, { "name": "SPECIES", "description": "Species" }, { "name": "EXP_TEST_TYPE", "description": "Type of test. In vivo test or in vitro test." }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "SEX_TYPE", "description": "Gender. Male or Female." }, { "name": "STRAIN_TYPE", "description": "Rat strain used with in vivo tests" }, { "name": "ADMINISTRATION_ROUTE_TYPE", "description": "Administration route" }, { "name": "ANIMAL_AGE(week)", "description": "Age of animal (weeks). Only rats at 6 weeks of age were used." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" }, { "name": "DOSE_LEVEL", "description": "Dose level. The ascending order of the levels is Control, Low, Middle, High." }, { "name": "Organ Weight", "description": "" }, { "name": "TERMINAL_BW(g)", "description": "terminal body weight" }, { "name": "LIVER(g)", "description": "the weight of the liver" }, { "name": "KIDNEY_TOTAL(g)", "description": "the total weight of the kidneys" }, { "name": "KIDNEY_R(g)", "description": "the weight of the right kidney" }, { "name": "KIDNEY_L(g)", "description": "the weight of the left kidney" }, { "name": "Hematology", "description": "" }, { "name": "RBC(x10_4\/ul)", "description": "red blood cell count" }, { "name": "Hb(g\/dL)", "description": "hemoglobin" }, { "name": "Ht(%)", "description": "hematocrit value" }, { "name": "MCV(fL)", "description": "mean corpuscular volume" }, { "name": "MCH(pg)", "description": "mean corpuscular hemoglobin" }, { "name": "MCHC(%)", "description": "mean corpuscular hemoglobin concentration" }, { "name": "Ret(%)", "description": "reticulocyte" }, { "name": "Plat(x10_4\/uL)", "description": "platelet count" }, { "name": "WBC(x10_2\/uL)", "description": "white blood cell count" }, { "name": "Neu(%)", "description": "neutrophil" }, { "name": "Eos(%)", "description": "eosinophil" }, { "name": "Bas(%)", "description": "basophil" }, { "name": "Mono(%)", "description": "monocyte" }, { "name": "Lym(%)", "description": "lymphocyte" }, { "name": "PT(s)", "description": "prothrombin time" }, { "name": "APTT(s)", "description": "activated partial thromboplastin time" }, { "name": "Fbg(mg\/dL)", "description": "fibrinogen" }, { "name": "Biochemistry", "description": "" }, { "name": "ALP(IU\/L)", "description": "alkaline phosphatase" }, { "name": "TC(mg\/dL)", "description": "total cholesterol" }, { "name": "TG(mg\/dL)", "description": "triglyceride" }, { "name": "PL(mg\/dL)", "description": "phospholipid" }, { "name": "TBIL(mg\/dL)", "description": "total bilirubin" }, { "name": "DBIL(mg\/dL)", "description": "direct bilirubin" }, { "name": "GLC(mg\/dL)", "description": "glucose" }, { "name": "BUN(mg\/dL)", "description": "blood urea nitrogen" }, { "name": "CRE(mg\/dL)", "description": "creatinine" }, { "name": "Na(meq\/L)", "description": "sodium" }, { "name": "K(meq\/L)", "description": "potassium" }, { "name": "Cl(meq\/L)", "description": "chlorine" }, { "name": "Ca(mg\/dL)", "description": "calcium" }, { "name": "IP(mg\/dL)", "description": "inorganic phosphorus" }, { "name": "TP(g\/dL)", "description": "total protein" }, { "name": "RALB(g\/dL)", "description": "albumin" }, { "name": "A\/G", "description": "albumin globulin ratio" }, { "name": "AST(IU\/L)", "description": "aspartate aminotransferase" }, { "name": "ALT(IU\/L)", "description": "alanine aminotransferase" }, { "name": "LDH(IU\/L)", "description": "lactate dehydrogenase" }, { "name": "GTP(IU\/L)", "description": "γ-glutamyltranspeptidase" }, { "name": "Cell viability", "description": "" }, { "name": "DNA(%)", "description": "Relative survival rate calculated from DNA content." }, { "name": "LDH(%)", "description": "Relative survival rate calculated from the activity value of lactate dehydrogenase which is leaked in the culture supernatant." } ] }, { "path": "en\/open-tggates-pathological-images\/data-1.html", "name": "Pathological Image Information", "database_name": "Open TG-GATEs Pathological Image Database", "doi": "10.18908\/lsdba.nbdc00954-02-001", "description": "Information regarding each high-resolution digital image in the \"Pathological Images (SVS format)\" section.", "files": [ { "file_name": "open_tggates_pathological_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates-pathological-images\/LATEST\/open_tggates_pathological_image.zip", "file_size": "370 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/open_tggates_pathological_image#en", "data_acquisition": "Information entered into the digital slide scanner while scanning the slides.", "analysis": "", "data_number": "52,879 entries", "details": [ { "name": "EXP_ID", "description": "ID assigned to each test which is defined mainly as a combination of COMPOUND_NAME, SPECIES, EXP_TEST_TYPE, and SINGLE_REPEAT_TYPE. IDs for in vivo tests are #0040 or larger." }, { "name": "GROUP_ID", "description": "ID assigned to each group which is defined mainly as a combination of DOSE_LEVEL and SACRIFICE_PERIOD. IDs are in double digits. (e.g. 01, 16)" }, { "name": "INDIVIDUAL_ID", "description": "ID assigned to each individual within a group. IDs are in single digit." }, { "name": "COMPOUND_NAME", "description": "Compound name" }, { "name": "ORGAN", "description": "Organs evaluated in tests. Liver or Kidney." }, { "name": "FILE_LOCATION", "description": "FTP server path to the pathological images." }, { "name": "CAPTURE_NO\/NO_OF_SAMPLE(n\/n)", "description": "The sequence number of scanned images with the total number. 1\/2 means that 2 glass slides were scanned for an organ and that the image is the first one." }, { "name": "SPECIES", "description": "Species" }, { "name": "SINGLE_REPEAT_TYPE", "description": "Type of in vivo test. Single-dose test or 28-day repeat-dose test." }, { "name": "ADMINISTRATION_ROUTE_TYPE", "description": "Administration route" }, { "name": "ANIMAL_AGE(week)", "description": "Age of animal (weeks)." }, { "name": "SACRIFICE_PERIOD", "description": "Sampling time or period on in vivo test." }, { "name": "DOSE", "description": "Dose" }, { "name": "DOSE_UNIT", "description": "Unit of dose" } ] }, { "path": "en\/open-tggates-pathological-images\/data-2.html", "name": "Pathological Images (SVS format)", "database_name": "Open TG-GATEs Pathological Image Database", "doi": "10.18908\/lsdba.nbdc00954-02-002", "description": "High-resolution whole slide digital images of liver and kidney pathological specimens stained with hematoxylin-eosin dyes. The specimens were obtained through animal tests.", "files": [ { "file_name": "Pathological Images in SVS format", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/open-tggates-pathological-images\/LATEST\/images\/", "file_size": "25 TB (Total amount of SVS files)" } ], "togodb_url": "", "data_acquisition": "Digital images of glass slides were scanned by using digital slide scanner (Aperio's ScanScope AT).", "analysis": "", "data_number": "52,879 entries", "details": [] }, { "path": "en\/pgdbj-ortholog-db\/data-1.html", "name": "Protein (Viridiplantae)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-001.V002", "description": "Amino acid sequences of Viridiplantae (green plants) obtained from the NCBI Reference Sequence Database with the NCBI GI numbers, the Reference Sequence IDs, and annotations. The IDs of clusters that the amino acid sequences belong to in each taxon are indicated.", "files": [ { "file_name": "pgdbj_ortholog_db_viridiplantae_protein.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_viridiplantae_protein.zip", "file_size": "200 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_viridiplantae_protein#en", "data_acquisition": "Amino acid sequences obtained from the NCBI Reference Sequence Database.", "analysis": "Organisms that have equal to or greater than 500 amino acid sequences in the NCBI Reference Sequence Database were included.", "data_number": "1,137,698 entries", "details": [ { "name": "GI number", "description": "NCBI GI number of Amino Acid sequence" }, { "name": "RefSeq ID", "description": "NCBI Reference Sequence ID" }, { "name": "Chr", "description": "Chromosome number or genomic ID" }, { "name": "Start Position", "description": "Start Position" }, { "name": "Stop Position", "description": "Stop Position" }, { "name": "Cluster (Kingdom)", "description": "Cluster ID (rank: Kingdom)" }, { "name": "Cluster (Phylum)", "description": "Cluster ID (rank: Phylum)" }, { "name": "Cluster (No rank 1)", "description": "Cluster ID (rank: No rank 1)" }, { "name": "Cluster (No rank 2)", "description": "Cluster ID (rank: No rank 2)" }, { "name": "Cluster (No rank 3)", "description": "Cluster ID (rank: No rank 3)" }, { "name": "Cluster (No rank 4)", "description": "Cluster ID (rank: No rank 4)" }, { "name": "Cluster (No rank 5)", "description": "Cluster ID (rank: No rank 5)" }, { "name": "Cluster (No rank 6)", "description": "Cluster ID (rank: No rank 6)" }, { "name": "Cluster (No rank 7)", "description": "Cluster ID (rank: No rank 7)" }, { "name": "Cluster (No rank 8)", "description": "Cluster ID (rank: No rank 8)" }, { "name": "Cluster (No rank 9)", "description": "Cluster ID (rank: No rank 9)" }, { "name": "Cluster (No rank 10)", "description": "Cluster ID (rank: No rank 10)" }, { "name": "Cluster (Class)", "description": "Cluster ID (rank: Class)" }, { "name": "Cluster (No rank 11)", "description": "Cluster ID (rank: No rank 11)" }, { "name": "Cluster (Subclass)", "description": "Cluster ID (rank: Subclass)" }, { "name": "Cluster (No rank 12)", "description": "Cluster ID (rank: No rank 12)" }, { "name": "Cluster (Order)", "description": "Cluster ID (rank: Order)" }, { "name": "Cluster (Family)", "description": "Cluster ID (rank: Family)" }, { "name": "Cluster (No rank 13)", "description": "Cluster ID (rank: No rank 13)" }, { "name": "Cluster (Subfamily)", "description": "Cluster ID (rank: Subfamily)" }, { "name": "Cluster (No rank 14)", "description": "Cluster ID (rank: No rank 14)" }, { "name": "Cluster (Tribe)", "description": "Cluster ID (rank: Tribe)" }, { "name": "Cluster (Subtribe)", "description": "Cluster ID (rank: Subtribe)" }, { "name": "Cluster (Genus)", "description": "Cluster ID (rank: Genus)" }, { "name": "Cluster (Subgenus)", "description": "Cluster ID (rank: Subgenus)" }, { "name": "Cluster (Species)", "description": "Cluster ID (rank: Species)" }, { "name": "Cluster (Subspecies)", "description": "Cluster ID (rank: Subspecies)" }, { "name": "Cluster (Forma)", "description": "Cluster ID (rank: Forma)" }, { "name": "Cluster (No rank 15)", "description": "Cluster ID (rank: No rank 15)" }, { "name": "Annotation", "description": "Annotation of protein" }, { "name": "Organism", "description": "Organism" }, { "name": "AA sequence", "description": "Amino acid sequence" } ] }, { "path": "en\/pgdbj-ortholog-db\/data-2.html", "name": "Cluster (Viridiplantae)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-002.V002", "description": "Clusters of amino acid sequences of Viridiplantae (green plants) obtained from the NCBI Reference Sequence Database. Along a phylogenetic tree, clusters were generated in Viridiplantae taxon and in each sub-taxon of Viridiplantae by using the results of all-against-all BLAST searches among the amino acid sequences. An amino acid sequence belongs to only one cluster in a taxon.", "files": [ { "file_name": "pgdbj_ortholog_db_viridiplantae_cluster.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_viridiplantae_cluster.zip", "file_size": "16.6 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_viridiplantae_cluster#en", "data_acquisition": "Data in \"Protein (Viridiplantae)\" was used.", "analysis": "Along a phylogenetic tree obtained from the NCBI Taxonomy Database, clusters in lower taxa (subclusters) were recursively aggregated to form clusters in a taxon (superclusters).", "data_number": "2,310,444 entries", "details": [ { "name": "Cluster ID", "description": "The cluster ID is composed of a Taxonomy ID and a serial number beginning with “0”. For instance, “cluster ID: 33090.0” means the protein belongs to the cluster ranked 0th among the clusters in the “taxon: 33090”. This cluster ID is uniquely-assigned by the PGDBj Ortholog Database." }, { "name": "Cluster size", "description": "Number of proteins affiliated with the Cluster" }, { "name": "Supercluster", "description": "Next supercluster" }, { "name": "Subcluster", "description": "Next subcluster" } ] }, { "path": "en\/pgdbj-ortholog-db\/data-3.html", "name": "Taxon (Viridiplantae)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-003.V002", "description": "Phylogenetic relationships among the recursively generated clusters in \"Cluster (Viridiplantae).\"", "files": [ { "file_name": "pgdbj_ortholog_db_viridiplantae_taxon.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_viridiplantae_taxon.zip", "file_size": "4.0 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_viridiplantae_taxon#en", "data_acquisition": "Phylogenetic relationships were obtained from the NCBI Taxonomy Database.", "analysis": "", "data_number": "175 entries", "details": [ { "name": "Taxonomy name", "description": "NCBI Taxonomy name" }, { "name": "Taxonomy ID", "description": "NCBI Taxonomy ID" }, { "name": "Taxonomy rank", "description": "NCBI Taxonomy rank" }, { "name": "Number of clusters", "description": "Number of clusters affiliated with the Taxon" }, { "name": "Number of proteins", "description": "Number of proteins affiliated with the Taxon" }, { "name": "Higher taxon", "description": "Next suprageneric taxon" }, { "name": "Lower taxon", "description": "Next infrageneric taxon" } ] }, { "path": "en\/pgdbj-ortholog-db\/data-4.html", "name": "Protein (Cyanobacteria)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-004.V002", "description": "Amino acid sequences of Cyanobacteria (blue-green algae) obtained from the NCBI Reference Sequence Database with the NCBI GI numbers, the Reference Sequence IDs, and annotations. The IDs of clusters that the amino acid sequences belong to in each taxon are indicated.", "files": [ { "file_name": "pgdbj_ortholog_db_cyanobacteria_protein.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_cyanobacteria_protein.zip", "file_size": "106 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_cyanobacteria_protein", "data_acquisition": "Amino acid sequences obtained from the NCBI Reference Sequence Database.", "analysis": "Organisms that have equal to or greater than 500 amino acid sequences in the NCBI Reference Sequence Database were included.", "data_number": "797,587 entries", "details": [ { "name": "GI number", "description": "NCBI GI number of Amino Acid sequence" }, { "name": "RefSeq ID", "description": "NCBI Reference Sequence ID" }, { "name": "Chr", "description": "Chromosome number or genomic ID" }, { "name": "Start Position", "description": "Start Position" }, { "name": "Stop Position", "description": "Stop Position" }, { "name": "Cluster (Phylum)", "description": "Cluster ID (rank: Phylum)" }, { "name": "Cluster (Class)", "description": "Cluster ID (rank: Class)" }, { "name": "Cluster (Order)", "description": "Cluster ID (rank: Order)" }, { "name": "Cluster (No rank 1)", "description": "Cluster ID (rank: No rank 1)" }, { "name": "Cluster (Family)", "description": "Cluster ID (rank: Family)" }, { "name": "Cluster (Genus)", "description": "Cluster ID (rank: Genus)" }, { "name": "Cluster (No rank 2)", "description": "Cluster ID (rank: No rank 2)" }, { "name": "Cluster (Species)", "description": "Cluster ID (rank: Species)" }, { "name": "Cluster (No rank 3)", "description": "Cluster ID (rank: No rank 3)" }, { "name": "Cluster (Subspecies)", "description": "Cluster ID (rank: Subspecies)" }, { "name": "Cluster (No rank 4)", "description": "Cluster ID (rank: No rank 4)" }, { "name": "Annotation", "description": "Annotation of protein" }, { "name": "Organism", "description": "Organism" }, { "name": "AA sequence", "description": "Amino acid sequence" } ] }, { "path": "en\/pgdbj-ortholog-db\/data-5.html", "name": "Cluster (Cyanobacteria)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-005.V002", "description": "Clusters of amino acid sequences of Cyanobacteria (blue-green algae) obtained from the NCBI Reference Sequence Database. Along a phylogenetic tree, clusters were generated in Cyanobacteria taxon and in each sub-taxon of Cyanobacteria by using the results of all-against-all BLAST searches among the amino acid sequences. An amino acid sequence belongs to only one cluster in a taxon.", "files": [ { "file_name": "pgdbj_ortholog_db_cyanobacteria_cluster.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_cyanobacteria_cluster.zip", "file_size": "8.2 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_cyanobacteria_cluster#en", "data_acquisition": "Data in \"Protein (Cyanobacteria)\" was used.", "analysis": "Along a phylogenetic tree obtained from the NCBI Taxonomy Database, clusters in lower taxa (subclusters) were recursively aggregated to form clusters in a taxon (superclusters).", "data_number": "1,095,715 entries", "details": [ { "name": "Cluster ID", "description": "The cluster ID is composed of a Taxonomy ID and a serial number beginning with “0”. For instance, “cluster ID: 33090.0” means the protein belongs to the cluster ranked 0th among the clusters in the “taxon: 33090”. This cluster ID is uniquely-assigned by the PGDBj Ortholog Database." }, { "name": "Cluster size", "description": "Number of proteins affiliated with the Cluster" }, { "name": "Supercluster", "description": "Next supercluster" }, { "name": "Subcluster", "description": "Next subcluster" } ] }, { "path": "en\/pgdbj-ortholog-db\/data-6.html", "name": "Taxon (Cyanobacteria)", "database_name": "PGDBj - Ortholog DB", "doi": "10.18908\/lsdba.nbdc01194-02-006.V002", "description": "Phylogenetic relationships among the recursively generated clusters in \"Cluster (Cyanobacteria).\"", "files": [ { "file_name": "pgdbj_ortholog_db_cyanobacteria_taxon.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/pgdbj-ortholog-db\/LATEST\/pgdbj_ortholog_db_cyanobacteria_taxon.zip", "file_size": "7.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pgdbj_ortholog_db_cyanobacteria_taxon#en", "data_acquisition": "Phylogenetic relationships were obtained from the NCBI Taxonomy Database.", "analysis": "", "data_number": "318 entries", "details": [ { "name": "Taxonomy name", "description": "NCBI Taxonomy name" }, { "name": "Taxonomy ID", "description": "NCBI Taxonomy ID" }, { "name": "Taxonomy rank", "description": "NCBI Taxonomy rank" }, { "name": "Number of clusters", "description": "Number of clusters affiliated with the Taxon" }, { "name": "Number of proteins", "description": "Number of proteins affiliated with the Taxon" }, { "name": "Higher taxon", "description": "Next suprageneric taxon" }, { "name": "Lower taxon", "description": "Next infrageneric taxon" } ] }, { "path": "en\/plabrain-db\/data-1.html", "name": "FACS-based single-cell PCR data", "database_name": "Plabrain DB", "doi": "10.18908\/lsdba.nbdc01108-001", "description": "Gene expression patterns at the single-neuron (cell) resolution using FACS-based single cell PCR. \"+\" indicates a cell co-expressing each gene and a neural-specific marker gene EF1. Although all genes in this table are known to be expressed in the nervous system, the patterns of \"+\" indicate that these genes have different expression pattern in single neurons. Image file names of plotting the gene expression on the FACS profile are also included. A set of the image files is downloadble from \"Image files of PCR data plotted on the FACS profiles\".", "files": [ { "file_name": "planaria_fbsc_pcr.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/plabrain-db\/LATEST\/planaria_fbsc_pcr.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/plabrain_single_cell_exp#en", "data_acquisition": "FBSC-PCR (semi-quantitative single-cell RT-PCR using FACS)", "analysis": "", "data_number": "12", "details": [ { "name": "Gene name (Link to Image list)", "description": "Gene name (Link to \"Image list\" in simple search.)" }, { "name": "Single-cell PCR data (+ describes cells expressing the gene.)", "description": "\"+\" indicates a cell co-expressing each gene and a neural-specific marker gene EF1." }, { "name": "Mapping on FACS profile", "description": "PCR data plotting onto the FACS profile, in which cells are sorted by DNA content (Hoechst33342) and cell size (CalceinAM). Blue dots indicate the \"+\"cells. The FACS profile image is displayed when you click \"FACS Profile\" in simple search. In the downloaded data, its file name is shown." } ] }, { "path": "en\/plabrain-db\/data-2.html", "name": "Image files of PCR data plotted on the FACS profiles", "database_name": "Plabrain DB", "doi": "10.18908\/lsdba.nbdc01108-002", "description": "FACS-based single-cell PCR data was plotted on the FACS profile, in which cells are sorted by DNA content (Hoechst33342) and cell size (CalceinAM). Blue dots indicate the \"+\"cells. Individual FACS profile images are displayed when you click \"FACS Profile\" in \"FACS-based single-cell PCR data\" simple search.", "files": [ { "file_name": "planaria_facs_profile.zip", "file_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/plabrain_single_cell_exp#en", "file_size": "107KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "8", "details": [] }, { "path": "en\/plabrain-db\/data-3.html", "name": "A list of image files of planarians analyzed by in situ hybridication and immunohistochemical staining", "database_name": "Plabrain DB", "doi": "10.18908\/lsdba.nbdc01108-003", "description": "This list includes file names of images of gene expression pattern by whole-mount in situ hybridication and also protein distribution by immunohistochemical staining in intact planarians or planarian head regions in the regeneration process. A set of the image files is downloadable from \"Image files of planarians analyzed by In situ hybridication and immunohistochemical staining\".", "files": [ { "file_name": "planaria_image_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/plabrain-db\/LATEST\/planaria_image_list.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/plabrain_image#en", "data_acquisition": "Whole-mount in situ hybridication, immunohistochemical staining", "analysis": "", "data_number": "12", "details": [ { "name": "Gene name (Link to Image list)", "description": "Gene name (Link to a image list in simple search.)" }, { "name": "Accession", "description": "GenBank accession number (Link to NCBI in simple search.)" }, { "name": "Adult (ISH)", "description": "Image of in situ hybridization of adult planarians. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" }, { "name": "Adult (Ab)", "description": "Image of whole-mount immunostaining of intact planarians. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" }, { "name": "Regeneration 1 day (Ab)", "description": "Image of immunostaining at 1 day after decapitation. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" }, { "name": "Regeneration 3 days (Ab)", "description": "Image of immunostaining at 3 days after decapitation. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" }, { "name": "Regeneration 5 days (Ab)", "description": "Image of immunostaining at 5 days after decapitation. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" }, { "name": "Regeneration 7 days (Ab)", "description": "Image of immunostaining at 7 days after decapitation. (The image is displayed in simple search. In the downloaded data, its file name is shown.)" } ] }, { "path": "en\/plabrain-db\/data-4.html", "name": "Image files of planarians analyzed by in situ hybridication and immunohistochemical staining", "database_name": "Plabrain DB", "doi": "10.18908\/lsdba.nbdc01108-004", "description": "Image files of gene expression patterns by whole-mount in situ hybridication and also protein distribution by immunohistochemical staining of intact planarians or planarian head regions in the regeneration process. Images are displayed in \"A list of image files of planarians analyzed by in situ hybridication and immunohistochemical staining\" simple search.\r\nThe file name is created by the following rule.\r\n\r\n[gene name]-insitu.jpg\r\n\r\nFor planarian adult, [gene name]-Ab.jpg\r\nFor planarian brain regeneration, [gene name]regeneration[days after decapitation ].jpg", "files": [ { "file_name": "planaria_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/plabrain-db\/LATEST\/planaria_image.zip", "file_size": "2.74MB" } ], "togodb_url": "", "data_acquisition": "Whole-mount in situ hybridication, immunohistochemical staining", "analysis": "", "data_number": "35", "details": [] }, { "path": "en\/place\/data-1.html", "name": "Main", "database_name": "PLACE", "doi": "10.18908\/lsdba.nbdc00168-001", "description": "Nucleotide sequence information. For each \"Main\" entry, there may be one or more \"Reference\" entries available.", "files": [ { "file_name": "place_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/place\/LATEST\/place_main.zip", "file_size": "48.9 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/place_main#en", "data_acquisition": "The CSV file (place_main.zip) was generated from nucleotide sequence information in place.seq of Raw Data (ASCII format).", "analysis": "", "data_number": "469 entries", "details": [ { "name": "Identifier", "description": "Identifier" }, { "name": "Accession number", "description": "Accession number" }, { "name": "Date (operation) author", "description": "Date (operation) author" }, { "name": "Description", "description": "Description (regulation, gene, transacting factor, etc.)" }, { "name": "Keywords", "description": "Keywords" }, { "name": "Species", "description": "Species" }, { "name": "Sequence", "description": "Sequence of the cis-acting regulatory DNA element.\r\nFor the cis-acting elements the following symbols were used as codes representing A, G, C or T.\r\nB: C, G or T\r\nD: A, G or T\r\nH: A, C or T\r\nK: G or T\r\nM: A or C\r\nN: A, C, G or T\r\nR: A or G\r\nS: C or G\r\nV: A, C or G\r\nW: A or T\r\nY: C or T\r\n(Mar. 31, 1997)" } ] }, { "path": "en\/place\/data-2.html", "name": "Reference", "database_name": "PLACE", "doi": "10.18908\/lsdba.nbdc00168-002", "description": "Literature information. For each \"Main\" entry, there may be one or more \"Reference\" entries available.", "files": [ { "file_name": "place_reference.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/place\/LATEST\/place_reference.zip", "file_size": "52.5 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/place_reference#en", "data_acquisition": "The CSV file (place_reference.zip) was generated from literature information in place.seq of Raw Data (ASCII format).", "analysis": "", "data_number": "900 entries", "details": [ { "name": "Identifier", "description": "Identifier" }, { "name": "Authors", "description": "Authors" }, { "name": "Title", "description": "Title" }, { "name": "Literature data", "description": "Literature data" }, { "name": "Criteria", "description": "Criteria (DNase I footprinting study \/ Chemical modifications \/ Gel retardation assay \/ homology \/ other)" }, { "name": "PubMed", "description": "PubMed ID" }, { "name": "GenBank", "description": "DDBJ\/EMBL\/GenBank accession number" } ] }, { "path": "en\/place\/data-3.html", "name": "Raw Data (ASCII format)", "database_name": "PLACE", "doi": "10.18908\/lsdba.nbdc00168-003", "description": "The document in EMBL-like format that contains brief descriptions of individual cis-elements.", "files": [ { "file_name": "place.seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/place\/LATEST\/place.seq.zip", "file_size": "110 KB" } ], "togodb_url": "", "data_acquisition": "The nucleotide sequence motifs for the regulatory region of gene expression were surveyed from published papers. In addition, supplementary descriptions, references, and the accession numbers in sequence databases are provided.", "analysis": "", "data_number": "469 entries", "details": [ { "name": "ID", "description": "Identifier" }, { "name": "AC", "description": "Accession number" }, { "name": "DT", "description": "Date (operation) author" }, { "name": "DE", "description": "Description (regulation, gene, transacting factor, etc.)" }, { "name": "KW", "description": "Keywords" }, { "name": "OS", "description": "Species" }, { "name": "RA", "description": "Authors" }, { "name": "RT", "description": "Title" }, { "name": "RL", "description": "Literature data" }, { "name": "RC", "description": "Criteria (DNase I footprinting study \/ Chemical modifications \/ Gel retardation assay \/ homology \/ other)" }, { "name": "RD", "description": "External Database (MEDLINE number or DDBJ\/EMBL\/GenBank accession number)" }, { "name": "SQ", "description": "Sequence of the cis-acting regulatory DNA element.\r\nFor the cis-acting elements the following symbols were used as codes representing A, G, C or T.\r\nB: C, G or T\r\nD: A, G or T\r\nH: A, C or T\r\nK: G or T\r\nM: A or C\r\nN: A, C, G or T\r\nR: A or G\r\nS: C or G\r\nV: A, C or G\r\nW: A or T\r\nY: C or T\r\n(Mar. 31, 1997)" }, { "name": "XX", "description": "Data item delimiter" } ] }, { "path": "en\/place\/data-4.html", "name": "Raw Data (Signal scan format)", "database_name": "PLACE", "doi": "10.18908\/lsdba.nbdc00168-004", "description": "The document in Signal scan format that contains brief descriptions of individual cis-elements.", "files": [ { "file_name": "place.dat.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/place\/LATEST\/place.dat.zip", "file_size": "7.4 KB" } ], "togodb_url": "", "data_acquisition": "The data were generated by extracting the necessary information from the place.seq of Raw Data (ASCII format).", "analysis": "", "data_number": "469 entries", "details": [ { "name": "Old data ID", "description": "Identifier in old data (r01.1 or earlier : Identifier, r02.0 or later : \"unknown\")" }, { "name": "ID", "description": "Identifier (r01.1 or earlier : Name, r02.0 or later : Identifier)" }, { "name": "Sequence", "description": "Sequence of the cis-acting regulatory DNA element.\r\nFor the cis-acting elements the following symbols were used as codes representing A, G, C or T.\r\nB: C, G or T\r\nD: A, G or T\r\nH: A, C or T\r\nK: G or T\r\nM: A or C\r\nN: A, C, G or T\r\nR: A or G\r\nS: C or G\r\nV: A, C or G\r\nW: A or T\r\nY: C or T\r\n(Mar. 31, 1997)" }, { "name": "Sequence length", "description": "Sequence length" }, { "name": "Accession number", "description": "Accession number" } ] }, { "path": "en\/place\/data-5.html", "name": "Raw Data (FASTA format)", "database_name": "PLACE", "doi": "10.18908\/lsdba.nbdc00168-005", "description": "The document in FASTA format that contains brief descriptions of individual cis-elements.", "files": [ { "file_name": "place.fasta.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/place\/LATEST\/place.fasta.zip", "file_size": "36.3 KB" } ], "togodb_url": "", "data_acquisition": "The data were generated by extracting the necessary information from the place.seq of Raw Data (ASCII format).", "analysis": "", "data_number": "469 entries", "details": [] }, { "path": "en\/possum\/data-1.html", "name": "Known binding sites", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-001", "description": "Known binding sites on protein", "files": [ { "file_name": "possum_ksite.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_ksite.zip", "file_size": "7.9 MB" } ], "togodb_url": "", "data_acquisition": "PDB", "analysis": "", "data_number": "325,890 entries", "details": [ { "name": "PocketIndex", "description": "Internal ID for this binding site" }, { "name": "PDB_ID", "description": "PDB ID for the protein" }, { "name": "HET_Code", "description": "HET code for the ligand" }, { "name": "ChainID", "description": "ID for the chain where the binding site is" }, { "name": "HET_Res.No.", "description": "Residue sequence number of the ligand" }, { "name": "ResLength", "description": "Length of residue sequence of the site" }, { "name": "Atoms", "description": "Num of atoms of the ligand" }, { "name": "MolName", "description": "Molecular name of the site" }, { "name": "EC", "description": "EC ID for the site" }, { "name": "CATH", "description": "CATH ID for the site" }, { "name": "SCOPe", "description": "SCOPe ID for the site" }, { "name": "UniProt", "description": "UniProt ID for the site" }, { "name": "UniRef50", "description": "UniRef50 cluster ID for the site (when it is analysed)" }, { "name": "GO1", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO2", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO3", "description": "Gene ontology to indicate molecular function of the site" } ] }, { "path": "en\/possum\/data-2.html", "name": "Potential binding sites", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-002", "description": "Not confirmed yet but putative binding sites on protein", "files": [ { "file_name": "possum_psite.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_psite.zip", "file_size": "27 MB" } ], "togodb_url": "", "data_acquisition": "PDB", "analysis": "", "data_number": "1,203,295 entries", "details": [ { "name": "PocketIndex", "description": "Internal ID for this binding site" }, { "name": "PDB_ID", "description": "PDB ID for the protein" }, { "name": "HET_Code", "description": "HET code for the ligand" }, { "name": "ChainID", "description": "ID for the chain where the binding site is" }, { "name": "ResLength", "description": "Length of residue sequence of the site" }, { "name": "Atoms", "description": "Num of atoms of the ligand" }, { "name": "MolName", "description": "Molecular name of the site" }, { "name": "EC", "description": "EC ID for the site" }, { "name": "CATH", "description": "CATH ID for the site" }, { "name": "SCOPe", "description": "SCOPe ID for the site" }, { "name": "UniProt", "description": "UniProt ID for the site" }, { "name": "UniRef50", "description": "UniRef50 cluster ID for the site (when it is analysed)" }, { "name": "GO1", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO2", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO3", "description": "Gene ontology to indicate molecular function of the site" } ] }, { "path": "en\/possum\/data-3.html", "name": "Known binding site similarities", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-003", "description": "Similarity data between known binding sites", "files": [ { "file_name": "possum_kpair.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_kpair.zip", "file_size": "3.9 GB" } ], "togodb_url": "", "data_acquisition": "PDB", "analysis": "", "data_number": "52,860,682 entries", "details": [ { "name": "Q:PocketIndex", "description": "Internal ID for query site" }, { "name": "Ｔ:PocketIndex", "description": "Internal ID for target site" }, { "name": "Q:PDB_ID", "description": "PDB ID for query site" }, { "name": "T:PDB_ID", "description": "PDB ID for target site" }, { "name": "Q:HET_Code", "description": "HED code for query site" }, { "name": "T:HET_Code", "description": "HED code for target site" }, { "name": "Q:ChainID", "description": "ID for the chain where the query site is" }, { "name": "T:ChainID", "description": "ID for the chain where the target site is" }, { "name": "Q:Res.No.", "description": "Residence number for the amino acid where the query site is" }, { "name": "T:Res.No.", "description": "Residence number for the amino acid where the target site is" }, { "name": "Cosine", "description": "Cosine similarity with physicochemical and geometric properties" }, { "name": "AlignedLength", "description": "Length of amino acid alignment" }, { "name": "RMSD", "description": "Root Mean Square Deviation" }, { "name": "TM-score", "description": "Template modeling score of protein structure" }, { "name": "Pval", "description": "P-Value of similarity" }, { "name": "AminoIdentity", "description": "Amino acid match rate" }, { "name": "MolName", "description": "Molecular name of the site" }, { "name": "EC", "description": "EC ID for the site" }, { "name": "CATH", "description": "CATH ID for the site" }, { "name": "SCOPe", "description": "SCOPe ID for the site" }, { "name": "UniProt", "description": "UniProt ID for the site" }, { "name": "UniRef50", "description": "UniRef50 cluster ID for the site (when it is analysed)" }, { "name": "GO1", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO2", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO3", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "AlignedResidues", "description": "Amino acid alignment result" } ] }, { "path": "en\/possum\/data-4.html", "name": "Binding site similarities", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-004", "description": "Similarity data between known\/potential binding sites", "files": [ { "file_name": "possum_ppair.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_ppair.zip", "file_size": "5.4 GB" } ], "togodb_url": "", "data_acquisition": "PDB", "analysis": "", "data_number": "81,069,340 entries", "details": [ { "name": "Q:PocketIndex", "description": "Internal ID for query site" }, { "name": "Ｔ:PocketIndex", "description": "Internal ID for target site" }, { "name": "Q:PDB_ID", "description": "PDB ID for query site" }, { "name": "T:PDB_ID", "description": "PDB ID for target site" }, { "name": "Q:HET_Code", "description": "HED code for query site" }, { "name": "T:HET_Code", "description": "HED code for target site" }, { "name": "Q:ChainID", "description": "ID for the chain where the query site is" }, { "name": "T:ChainID", "description": "ID for the chain where the target site is" }, { "name": "Q:Res.No.", "description": "Residence number for the amino acid where the query site is" }, { "name": "T:Res.No.", "description": "Residence number for the amino acid where the target site is" }, { "name": "Cosine", "description": "Cosine similarity with physicochemical and geometric properties" }, { "name": "AlignedLength", "description": "Length of amino acid alignment" }, { "name": "RMSD", "description": "Root Mean Square Deviation" }, { "name": "TM-score", "description": "Template modeling score of protein structure" }, { "name": "Pval", "description": "P-Value of similarity" }, { "name": "AminoIdentity", "description": "Amino acid match rate" }, { "name": "MolName", "description": "Molecular name of the site" }, { "name": "EC", "description": "EC ID for the site" }, { "name": "CATH", "description": "CATH ID for the site" }, { "name": "SCOPe", "description": "SCOPe ID for the site" }, { "name": "UniProt", "description": "UniProt ID for the site" }, { "name": "UniRef50", "description": "UniRef50 cluster ID for the site (when it is analysed)" }, { "name": "GO1", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO2", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "GO3", "description": "Gene ontology to indicate molecular function of the site" }, { "name": "AlignedResidues", "description": "Amino acid alignment result" } ] }, { "path": "en\/possum\/data-5.html", "name": "(Drug Search)Ligand list", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-005", "description": "Ligand list for Drug Search extracted from ChEMBL", "files": [ { "file_name": "possum_ligand_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_ligand_list.zip", "file_size": "11 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_ligand_list#en", "data_acquisition": "ChEMBL", "analysis": "", "data_number": "194 entries", "details": [ { "name": "ID", "description": "Internal ID for this ligand" }, { "name": "HET_Code", "description": "HET Code" }, { "name": "Link", "description": "Link to tables in Drug Search (only in simple search)" }, { "name": "ChEMBL_ID", "description": "ChEMBL ID" }, { "name": "PrefName", "description": "Preferred name" }, { "name": "HeavyAtoms", "description": "Number of heavy atoms" }, { "name": "FullMWT", "description": "Full molocular weight" }, { "name": "Alogp", "description": "Value of ALogP" }, { "name": "HBA", "description": "Number of H-bond acceptors" }, { "name": "HBD", "description": "Number of H-bond donors" }, { "name": "RotatableBonds", "description": "Number of ratatable bonds" }, { "name": "PSA", "description": "Polar surface area" }, { "name": "ATC_Level1", "description": "Classification in ATC level1" }, { "name": "ATC_Level2", "description": "Classification in ATC level2" }, { "name": "ATC_Level3", "description": "Classification in ATC level3" }, { "name": "ATC_Level4", "description": "Classification in ATC level4" } ] }, { "path": "en\/possum\/data-6.html", "name": "(Drug Search)Query site list", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-006", "description": "The list of binding sites (query) for ligands in (Drug Search) Ligand list", "files": [ { "file_name": "possum_query_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_query_protein.zip", "file_size": "40 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_query_protein#en", "data_acquisition": "PDB", "analysis": "", "data_number": "2,595 entries", "details": [ { "name": "PocketIndex", "description": "Internal ID for this binding site" }, { "name": "PDB_ID", "description": "PDB ID for the protein" }, { "name": "HET_Code", "description": "HET code for the ligand" }, { "name": "ChainID", "description": "ID for the chain where the binding site is" }, { "name": "Res.No.", "description": "Residence number for the amino acid where the binding site is" }, { "name": "MolName", "description": "Molecular name of the protein" }, { "name": "UniProt", "description": "UniProt ID for the protein" }, { "name": "UniRef50", "description": "UniRef50 claster ID for the protein (when it is analysed)" }, { "name": "EC", "description": "EC ID for the protein" }, { "name": "CATH", "description": "CATH ID for the protein" }, { "name": "SCOPe", "description": "SCOPe scope for the ligand" } ] }, { "path": "en\/possum\/data-7.html", "name": "(Drug Search)Target site list", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-007", "description": "The list of binding sites (target) similar with query sites", "files": [ { "file_name": "possum_target_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_target_protein.zip", "file_size": "844 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_target_protein#en", "data_acquisition": "PDB", "analysis": "", "data_number": "55,404 entries", "details": [ { "name": "PocketIndex", "description": "Internal ID for this binding site" }, { "name": "PDB_ID", "description": "PDB ID for the protein" }, { "name": "HET_Code", "description": "HET code for the ligand" }, { "name": "ChainID", "description": "ID for the chain where the binding site is" }, { "name": "Res.No.", "description": "Residence number for the amino acid where the binding site is" }, { "name": "MolName", "description": "Molecular name of the protein" }, { "name": "UniProt", "description": "UniProt ID for the protein" }, { "name": "UniRef50", "description": "UniRef50 cluster ID for the protein (when it is analysed)" }, { "name": "EC", "description": "EC ID for the protein" }, { "name": "CATH", "description": "CATH ID for the protein" }, { "name": "SCOPe", "description": "SCOPe scope for the ligand" } ] }, { "path": "en\/possum\/data-8.html", "name": "(Drug Search)Target ligand list", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-008", "description": "The list of target sites and binding ligands", "files": [ { "file_name": "possum_target_ligand.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_target_ligand.zip", "file_size": "792 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_target_ligand#en", "data_acquisition": "ChEMBL", "analysis": "", "data_number": "27,326 entries", "details": [ { "name": "HET_Code", "description": "HET Code for the ligand" }, { "name": "SimilarPockets", "description": "Internal id of site binding the ligand" }, { "name": "JaccardIndex(MACCS)", "description": "Jaccard Index between ligand and target site (with MACCS)" }, { "name": "JaccardIndex(FP2)", "description": "Jaccard Index between ligand and target site (with FP2)" }, { "name": "InChi_Key", "description": "InChIKey of binding molocular" }, { "name": "CanonicalSmiles", "description": "Canonical SMILES of binding molocular" } ] }, { "path": "en\/possum\/data-9.html", "name": "(Drug Search)Known binding site similarity", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-009", "description": "Similarity data between known binding sites in (Drug Search) query and target sites", "files": [ { "file_name": "possum_binding_sites_known_similarity.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_binding_sites_known_similarity.zip", "file_size": "2.4 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_binding_sites_known_similarity#en", "data_acquisition": "PDB", "analysis": "", "data_number": "50,626 entries", "details": [ { "name": "Q:PocketIndex", "description": "Internal ID for query site" }, { "name": "Ｔ:PocketIndex", "description": "Internal ID for target site" }, { "name": "Q:PDB_ID", "description": "PDB ID for query site" }, { "name": "T:PDB_ID", "description": "PDB ID for target site" }, { "name": "Q:HET_Code", "description": "HED code for query site" }, { "name": "T:HET_Code", "description": "HED code for target site" }, { "name": "Q:ChainID", "description": "ID for the chain where the query site is" }, { "name": "T:ChainID", "description": "ID for the chain where the target site is" }, { "name": "Q:Res.No.", "description": "Residence number for the amino acid where the query site is" }, { "name": "T:Res.No.", "description": "Residence number for the amino acid where the target site is" }, { "name": "AlignedLength", "description": "Length of amino acid alignment" }, { "name": "RMSD", "description": "Root Mean Square Deviation" }, { "name": "AminoIdentity", "description": "Amino acid match rate" }, { "name": "Q:MolName", "description": "Molecular name of the query site" }, { "name": "T:MolName", "description": "Molecular name of the target site" }, { "name": "Q:EC", "description": "EC ID for the query site" }, { "name": "T:EC", "description": "EC ID for the target site" }, { "name": "Q:CATH", "description": "CATH ID for the query site" }, { "name": "T:CATH", "description": "CATH ID for the target site" }, { "name": "Q:SCOPe", "description": "SCOPe ID for the query site" }, { "name": "T:SCOPe", "description": "SCOPe ID for the target site" }, { "name": "Q:UniProt", "description": "UniProt ID for the query site" }, { "name": "T:UniProt", "description": "UniProt ID for the target site" }, { "name": "Q:UniRef50", "description": "UniRef50 cluster ID for the query site (when it is analysed)" }, { "name": "T:UniRef50", "description": "UniRef50 cluster ID for the target site (when it is analysed)" }, { "name": "EC_Df", "description": "Different or not between query and target site in EC ID" }, { "name": "CATH_Df", "description": "Different or not between query and target site in CATH ID" }, { "name": "SCOPe_Df", "description": "Different or not between query and target site in SCOPe ID" }, { "name": "ChEMBL_Assay", "description": "Assay data in ChEMBL or none" }, { "name": "AlignedResidues", "description": "Amino acid alignment result" } ] }, { "path": "en\/possum\/data-10.html", "name": "(Drug Search)Known binding site similarity", "database_name": "PoSSuM", "doi": "10.18908\/lsdba.nbdc01144-010", "description": "Similarity data between known\/potential binding sites in (Drug Search) query and target sites", "files": [ { "file_name": "possum_binding_sites_putative_similarity.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/possum\/LATEST\/possum_binding_sites_putative_similarity.zip", "file_size": "5 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/possum_binding_sites_putative_similarity#en", "data_acquisition": "PDB", "analysis": "", "data_number": "113,495 entries", "details": [ { "name": "Q:PocketIndex", "description": "Internal ID for query site" }, { "name": "Ｔ:PocketIndex", "description": "Internal ID for target site" }, { "name": "Q:PDB_ID", "description": "PDB ID for query site" }, { "name": "T:PDB_ID", "description": "PDB ID for target site" }, { "name": "Q:HET_Code", "description": "HED code for query site" }, { "name": "T:HET_Code", "description": "HED code for target site" }, { "name": "Q:ChainID", "description": "ID for the chain where the query site is" }, { "name": "T:ChainID", "description": "ID for the chain where the target site is" }, { "name": "Q:Res.No.", "description": "Residence number for the amino acid where the query site is" }, { "name": "T:Res.No.", "description": "Residence number for the amino acid where the target site is" }, { "name": "AlignedLength", "description": "Length of amino acid alignment" }, { "name": "RMSD", "description": "Root Mean Square Deviation" }, { "name": "AminoIdentity", "description": "Amino acid match rate" }, { "name": "Q:MolName", "description": "Molecular name of the query site" }, { "name": "T:MolName", "description": "Molecular name of the target site" }, { "name": "Q:EC", "description": "EC ID for the query site" }, { "name": "T:EC", "description": "EC ID for the target site" }, { "name": "Q:CATH", "description": "CATH ID for the query site" }, { "name": "T:CATH", "description": "CATH ID for the target site" }, { "name": "Q:SCOPe", "description": "SCOPe ID for the query site" }, { "name": "T:SCOPe", "description": "SCOPe ID for the target site" }, { "name": "Q:UniProt", "description": "UniProt ID for the query site" }, { "name": "T:UniProt", "description": "UniProt ID for the target site" }, { "name": "Q:UniRef50", "description": "UniRef50 cluster ID for the query site (when it is analysed)" }, { "name": "T:UniRef50", "description": "UniRef50 cluster ID for the target site (when it is analysed)" }, { "name": "EC_Df", "description": "Different or not between query and target site in EC ID" }, { "name": "CATH_Df", "description": "Different or not between query and target site in CATH ID" }, { "name": "SCOPe_Df", "description": "Different or not between query and target site in SCOPe ID" }, { "name": "ChEMBL_Assay", "description": "Assay data in ChEMBL or none" }, { "name": "AlignedResidues", "description": "Amino acid alignment result" } ] }, { "path": "en\/pscdb\/data-1.html", "name": "PSCID List", "database_name": "PSCDB", "doi": "10.18908\/lsdba.nbdc01636-001", "description": "The list of PSCID and common elements of each entry", "files": [ { "file_name": "pscdb_pscid_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/pscdb\/LATEST\/pscdb_pscid_list.zip", "file_size": "24.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pscdb_pscid_list#en", "data_acquisition": "PDB", "analysis": "", "data_number": "839 entries", "details": [ { "name": "PSCID", "description": "ID of this data" }, { "name": "Classification", "description": "The six digit numbers (from left to right) are, respectively,\r\n1st: the number of components of motion for the coupled domain motion\r\n2nd: the number for the independent domain motion\r\n3rd: the number for the coupled local motion\r\n4th: the number for the independent local motion\r\n5th: the number of domains exhibiting the burying ligand motion\r\n6th: the number of domains with ligand molecules situated on the protein surface." }, { "name": "Protein name", "description": "Protein name" }, { "name": "FreeID", "description": "PDB ID of ligand-free form" }, { "name": "BoundID", "description": "PDB ID of ligand-bound form" }, { "name": "Ligands", "description": "Ligand name(PDB)" }, { "name": "EC", "description": "Enzyme commission number" }, { "name": "Distance", "description": "The distance between the active site annotated in Catalytic Site Atlas (CSA) and the ligand-binding sites" } ] }, { "path": "en\/pscdb\/data-2.html", "name": "Protein Structural Change Data", "database_name": "PSCDB", "doi": "10.18908\/lsdba.nbdc01636-002", "description": "This data represent the relationship between protein structural change and ligand binding.", "files": [ { "file_name": "pscdb.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/pscdb\/LATEST\/pscdb.zip", "file_size": "45.6 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/pscdb#en", "data_acquisition": "", "analysis": "", "data_number": "1,084 entries", "details": [ { "name": "PSCID", "description": "ID of this data" }, { "name": "Classification", "description": "The six digit numbers (from left to right) are, respectively,\r\n1st: the number of components of motion for the coupled domain motion\r\n2nd: the number for the independent domain motion\r\n3rd: the number for the coupled local motion\r\n4th: the number for the independent local motion\r\n5th: the number of domains exhibiting the burying ligand motion\r\n6th: the number of domains with ligand molecules situated on the protein surface." }, { "name": "Protein name", "description": "Protein name" }, { "name": "FreeID", "description": "PDB ID of ligand-free form" }, { "name": "BoundID", "description": "PDB ID of ligand-bound form" }, { "name": "Ligands", "description": "Ligand name(PDB)" }, { "name": "EC", "description": "Enzyme commission number" }, { "name": "Distance", "description": "The distance between the active site annotated in Catalytic Site Atlas (CSA) and the ligand-binding sites" }, { "name": "Component No", "description": "Component Number" }, { "name": "Type of motion", "description": "Type of motion" }, { "name": "Ligand binding", "description": "Type of ligand binding" }, { "name": "Type of coupled motion", "description": "Type of coupled motion" }, { "name": "Order-disorder transition", "description": "Whether the open form contains the disordered structure. (\"Yes\" or space)" }, { "name": "RMSD", "description": "The root-mean-square displacement of a component of motion calculated for the domain motions" }, { "name": "Mean displacement", "description": "The mean displacement of a component of motion calculated for the local motions" }, { "name": "C.C.", "description": "The correlation coefficient between the displacement vector predicted by the linear response theory and the one observed in the crystal structures" }, { "name": "Crystal packing", "description": "Whether the change in the crystal environment is coupled with the structural change. (\"Coupled\" or space)" }, { "name": "Fixed segment", "description": "Fixed segment" }, { "name": "Moving segment", "description": "Moving segment" }, { "name": "Disorder", "description": "The number of disordered residues" }, { "name": "Helix\/coil", "description": "The number of residues exhibiting the alpha-helix to coil transition" }, { "name": "Open state", "description": "Distinction between the open state and the closed state required for examining the influence of the crystal environment" }, { "name": "H-bonds\/ligand", "description": "The number of hydrogen-bonds with ligands (observed in the proteins classified in \"Buried Ligand\")" }, { "name": "H-bonds\/water", "description": "The number of hydrogen-bonds with water (observed in the proteins classified in \"Buried Ligand\")" }, { "name": "H-bonds\/protein", "description": "The number of hydrogen-bonds with proteins (observed in the proteins classified in \"Buried Ligand\")" } ] }, { "path": "en\/pscdb\/data-3.html", "name": "Protein 3D Structure Image", "database_name": "PSCDB", "doi": "10.18908\/lsdba.nbdc01636-003", "description": "Protein 3D structure images created with PyMOL", "files": [ { "file_name": "pscdb_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/pscdb\/LATEST\/pscdb_image.zip", "file_size": "96.4 MB" } ], "togodb_url": "", "data_acquisition": "PDB", "analysis": "", "data_number": "839 entries", "details": [] }, { "path": "en\/qtaro\/data-1.html", "name": "QTL Information Table", "database_name": "Q-TARO", "doi": "10.18908\/lsdba.nbdc01234-001", "description": "1051 QTLs extracted from 463 reports are recorded as representative QTLs (As of March 31, 2008).", "files": [ { "file_name": "qtaro_sjis.zip (Shift JIS)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/qtaro\/LATEST\/qtaro_sjis.zip", "file_size": "89 KB" }, { "file_name": "qtaro_utf8.zip (UTF-8)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/qtaro\/LATEST\/qtaro_utf8.zip", "file_size": "89 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/qtaro#en", "data_acquisition": "5096 QTLs were extracted from 1214 reports previously published.\r\nReference sources:\r\n- PubMed (http:\/\/www.ncbi.nlm.nih.gov\/sites\/entrez)\r\n- HighWire (http:\/\/highwire.stanford.edu\/)\r\n- Jstage (http:\/\/www.jstage.jst.go.jp\/browse\/-char\/ja)\r\n- the Rice Genetics Newsletter (http:\/\/www.gramene.org\/newsletters\/rice_genetics\/).", "analysis": "The positions of these QTLs were estimated from the physical positions of either two flanking markers (the genomic positions of the distal ends of the two markers) or a co-segregated single marker (between the start and end positions on the genome). By screening for redundancy of traits at the same physical positions, representative QTLs were selected.", "data_number": "1,051 entries", "details": [ { "name": "id", "description": "ID number of QTL" }, { "name": "QTL\/Gene", "description": "Name of QTL" }, { "name": "Major category", "description": "Major category of quantitative character" }, { "name": "Category of object character", "description": "Category of object character" }, { "name": "Character", "description": "Character" }, { "name": "Marker", "description": "Type of marker" }, { "name": "No. of marker for position determination", "description": "Number of the markers used for position determination" }, { "name": "Chr", "description": "Chromosome number" }, { "name": "Genome start", "description": "QTL start position on the genome" }, { "name": "Genome end", "description": "QTL end position on the genome" }, { "name": "Mapping method", "description": "Mapping method" }, { "name": "Population", "description": "Population of plants" }, { "name": "No. of plants", "description": "Number of plants" }, { "name": "LOD", "description": "LOD score" }, { "name": "Parent A", "description": "Parent A" }, { "name": "Parent B", "description": "Parent B" }, { "name": "Direction (Parent)", "description": "Direction (Parent)" }, { "name": "a) Physical", "description": "Marker of physical mapping" }, { "name": "b) Fine1; interval", "description": "Flanking marker of fine mapping A" }, { "name": "b) Fine2; interval", "description": "Flanking marker of fine mapping B" }, { "name": "b) Fine3; co-segregated", "description": "Co-segregated marker of fine mapping" }, { "name": "c) Interval1; interval", "description": "Flanking marker of interval mapping A" }, { "name": "c) Interval2; interval", "description": "Flanking marker of interval mapping B" }, { "name": "c) Interval3; co-segregated", "description": "Co-segregated marker of interval mapping" }, { "name": "d) Co-segregated", "description": "Co-segregated marker" }, { "name": "Explained variance", "description": "Explained variance" }, { "name": "Additive effect", "description": "Additive effect" }, { "name": "Year", "description": "Year the reference was published" }, { "name": "Reference source", "description": "Search method of the reference.\r\nJournals were searched within the following websites.\r\n- Jsa (Jstage)\r\n- Pha (PubMed, HighWire)\r\n- RGN (Rice Genetics Newsletter)" }, { "name": "Reference no.", "description": "Number assigned to the reference serially within each reference source" }, { "name": "Reference", "description": "Reference" }, { "name": "Reference location", "description": "URL of the reference" } ] }, { "path": "en\/redii-inaho\/data-1.html", "name": "Probe data", "database_name": "RED II INAHO", "doi": "10.18908\/lsdba.nbdc01557-001", "description": "Probe information", "files": [ { "file_name": "redii_inaho_probe.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/redii-inaho\/LATEST\/redii_inaho_probe.zip", "file_size": "3.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/redii_inaho_probe#en", "data_acquisition": "", "analysis": "", "data_number": "31,791 entries", "details": [ { "name": "Probe no", "description": "Probe number" }, { "name": "Probe ID", "description": "Probe ID" }, { "name": "TU ID", "description": "ID of the TU (Transcriptional Unit)" }, { "name": "Microarray", "description": "Microarray name\r\nRED : Rice 9k Array used in the RMOS database\r\nARRAY22K : Rice 22k Array used in the KOME database" }, { "name": "Accession", "description": "Gene Accession number of probe" }, { "name": "5'end Accession", "description": "Gene Accession number of probe 5'end" }, { "name": "3'end Accession", "description": "Gene Accession number of probe 3'end" }, { "name": "Gene name", "description": "Gene name" }, { "name": "Probe name", "description": "Probe name" }, { "name": "Annotation", "description": "Probe Annotation" }, { "name": "5'probe sequence", "description": "Sequence of probe 5'end" }, { "name": "3'probe sequence", "description": "Sequence of probe 3'end" } ] }, { "path": "en\/redii-inaho\/data-2.html", "name": "Experimental information", "database_name": "RED II INAHO", "doi": "10.18908\/lsdba.nbdc01557-002", "description": "Outline of the experiment including sample combinations of each round.", "files": [ { "file_name": "redii_inaho_experiment.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/redii-inaho\/LATEST\/redii_inaho_experiment.zip", "file_size": "22.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/redii_inaho_experiment#en", "data_acquisition": "", "analysis": "", "data_number": "1,158 entries", "details": [ { "name": "Experiment no", "description": "Experiment number" }, { "name": "Experiment ID", "description": "String connected by a '_' between \"Research ID\", \"Round\", \"Group no\" of \"Control ID\" data and \"Group no\" of \"Target ID\" data." }, { "name": "Microarray", "description": "Microarray name\r\nRED : Rice 9k Array used in the RMOS database\r\nARRAY22K : Rice 22k Array used in the KOME database" }, { "name": "Control ID", "description": "Control Data, correspondence to column of \"Sample ID\" on the redii_inaho_sample table." }, { "name": "Target ID", "description": "Target Data, correspondence to column of \"Sample ID\" on the redii_inaho_sample table." }, { "name": "Control dye", "description": "Control dye" }, { "name": "Target dye", "description": "Target dye" }, { "name": "Experimenter", "description": "User name" }, { "name": "Institute", "description": "Organization" }, { "name": "Experimental category1", "description": "Experimental category 1" }, { "name": "Experimental category2", "description": "Experimental category 2" }, { "name": "Experimental category3", "description": "Experimental category 3" }, { "name": "Experimental category4", "description": "Experimental category 4" }, { "name": "Keyword", "description": "Experimental keyword" }, { "name": "Method", "description": "Method" }, { "name": "Experiment Date 1", "description": "Experiment date 1" }, { "name": "Glass ID 1", "description": "Array glass ID 1" }, { "name": "Glass Production Date 1", "description": "Array glass production date 1" }, { "name": "Spotter No 1", "description": "Spot number 1" }, { "name": "Pen Set ID 1", "description": "Pen set ID 1" }, { "name": "Glass Batch ID 1", "description": "Array glass batch 1" }, { "name": "Experiment Date 2", "description": "Experiment date 2" }, { "name": "Glass ID 2", "description": "Array glass ID 2" }, { "name": "Glass Production Date 2", "description": "Array glass production date 2" }, { "name": "Spotter No 2", "description": "Spot number 2" }, { "name": "Pen Set ID 2", "description": "Pen set ID 2" }, { "name": "Glass Batch ID 2", "description": "Array glass batch 2" } ] }, { "path": "en\/redii-inaho\/data-3.html", "name": "Sample information", "database_name": "RED II INAHO", "doi": "10.18908\/lsdba.nbdc01557-003", "description": "Sample information used as control sample or target sample.", "files": [ { "file_name": "redii_inaho_sample.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/redii-inaho\/LATEST\/redii_inaho_sample.zip", "file_size": "11.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/redii_inaho_sample#en", "data_acquisition": "The sample was used in the experiment as control sample or target sample.", "analysis": "", "data_number": "1,232 entries", "details": [ { "name": "Sample ID", "description": "Sample ID" }, { "name": "Microarray", "description": "Microarray name\r\nRED : Rice 9k Array used in the RMOS database\r\nARRAY22K : Rice 22k Array used in the KOME database" }, { "name": "Experiment ID", "description": "Original experimental ID. String connected by a '_' between \"Research ID\", \"Round\" and \"Group no\"." }, { "name": "Organism", "description": "Organism" }, { "name": "Subspecies", "description": "Subspecies" }, { "name": "Cultivar", "description": "Cultivar, Line" }, { "name": "Developmental Stage", "description": "Developmental stage" }, { "name": "Tissue", "description": "Tissue" }, { "name": "Mutant", "description": "Mutant" }, { "name": "Transgenic", "description": "Transgenic" } ] }, { "path": "en\/redii-inaho\/data-4.html", "name": "Expression data", "database_name": "RED II INAHO", "doi": "10.18908\/lsdba.nbdc01557-004", "description": "Normalized expression data derived from experiments.", "files": [ { "file_name": "redii_inaho_expression.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/redii-inaho\/LATEST\/redii_inaho_expression.zip", "file_size": "101 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/redii_inaho_expression#en", "data_acquisition": "This table contains normalized expression data derived from various experiments hybridized to RED (Rice 9K Array) and ARRAY22K (Rice 22k Array).", "analysis": "The data were normalized by data processing, including PRIM (processing implementation for microarray) filtering, and ‘sector median’ normalization, performed at each spotting sector on the glass slide to remove uneven sectors. All the expression data are shown as values of the expression ratio.", "data_number": "7,354,240 entries", "details": [ { "name": "Microarray", "description": "Microarray name\r\nRED : Rice 9k Array used in the RMOS database\r\nARRAY22K : Rice 22k Array used in the KOME database" }, { "name": "Experiment no", "description": "Experiment number" }, { "name": "Spot ID", "description": "Spot ID" }, { "name": "Probe no", "description": "Probe number" }, { "name": "Probe name", "description": "Probe name" }, { "name": "Expression value", "description": "Expression value (log ratio)" } ] }, { "path": "en\/refex\/data-1.html", "name": "Data Relationship Matrix", "database_name": "RefEx", "doi": "", "description": "A table of the relationship among different type of data.", "files": [ { "file_name": "refex_data_relationship_matrix.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_data_relationship_matrix.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "", "analysis": "", "data_number": "12", "details": [ { "name": "Species", "description": "Species of object" }, { "name": "Experimental Method", "description": "Experimantal method of collecting expression data." }, { "name": "Kind of ID", "description": "Kind of ID" }, { "name": "Gene Expression (classificated in 10 organs)", "description": "Gene expression data classified in 10 organs." }, { "name": "Gene Expression (classificated in 10 organs) DOI", "description": "DOI of gene expression data classificated in 10 organs." }, { "name": "Gene Expression (classificated in 40 organs)", "description": "Gene expression data classified in 40 organs." }, { "name": "Gene Expression (classificated in 40 organs) DOI", "description": "DOI of gene expression data classificated in 40 organs." }, { "name": "Gene Expression (by FANTOM5 CAGE)", "description": "CAGE data collected by FANTOM5." }, { "name": "Gene Expression (by FANTOM5 CAGE) DOI", "description": "DOI of CAGE data collected by FANTOM5." }, { "name": "Sample Classification Table", "description": "Classification table of each tissue." }, { "name": "Sample Classification Table DOI", "description": "DOI of classification table of each tissue." }, { "name": "Sample Annotation", "description": "Information of sample annotation" }, { "name": "Sample Annotation DOI", "description": "DOI of information of sample annotation." }, { "name": "Tissue Specificity (calculated by ROKU)", "description": "Tissue specificity calculated by ROKU method." }, { "name": "Tissue Specificity (calculated by ROKU) DOI", "description": "DOI of tissue specificity calculated by ROKU method." } ] }, { "path": "en\/refex\/data-2.html", "name": "Gene Expression Data", "database_name": "RefEx", "doi": "", "description": "Gene expression data collected by EST, GeneChip, CAGE, or RNA-seq Each data is named \"RefEx_expression_[experimental method][the number of tissue classes]_[species]\" in general.\r\ne.g. RefEx_expression_EST10_human\r\n\r\nNevertheless, some data collected by CAGE are named \"RefEx_expression_CAGE_all_[species]\".\r\ne.g. RefEx_expression_CAGE_all_human", "files": [ { "file_name": "refex_expression01_cage10_human_prjdb1099.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression01_cage10_human_prjdb1099.zip", "file_size": "908 KB" }, { "file_name": "refex_expression02_cage40_human_prjdb1099.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression02_cage40_human_prjdb1099.zip", "file_size": "2.5 MB" }, { "file_name": "refex_expression03_cage_all_human_prjdb1099.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression03_cage_all_human_prjdb1099.zip", "file_size": "40.5 MB" }, { "file_name": "refex_expression04_cage_all_mouse_prjdb1100.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression04_cage_all_mouse_prjdb1100.zip", "file_size": "21.2 MB" }, { "file_name": "refex_expression05_est10_human.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression05_est10_human.zip", "file_size": "597 KB" }, { "file_name": "refex_expression06_est10_mouse.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression06_est10_mouse.zip", "file_size": "592 KB" }, { "file_name": "refex_expression07_est10_rat.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression07_est10_rat.zip", "file_size": "421 KB" }, { "file_name": "refex_expression08_est40_human.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression08_est40_human.zip", "file_size": "1.2 MB" }, { "file_name": "refex_expression09_est40_mouse.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression09_est40_mouse.zip", "file_size": "1.1 MB" }, { "file_name": "refex_expression10_est40_rat.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression10_est40_rat.zip", "file_size": "550 KB" }, { "file_name": "refex_expression11_genechip10_human_gse7307.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression11_genechip10_human_gse7307.zip", "file_size": "1.1 MB" }, { "file_name": "refex_expression12_genechip10_mouse_gse10246.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression12_genechip10_mouse_gse10246.zip", "file_size": "898 KB" }, { "file_name": "refex_expression13_genechip10_rat_gse952.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression13_genechip10_rat_gse952.zip", "file_size": "143 KB" }, { "file_name": "refex_expression14_genechip40_human_gse7307.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression14_genechip40_human_gse7307.zip", "file_size": "10.6 MB" }, { "file_name": "refex_expression15_genechip40_mouse_gse10246.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression15_genechip40_mouse_gse10246.zip", "file_size": "2.8 MB" }, { "file_name": "refex_expression16_genechip40_rat_gse952.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression16_genechip40_rat_gse952.zip", "file_size": "326 KB" }, { "file_name": "refex_expression17_rnaseq10_human_prjeb2445.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression17_rnaseq10_human_prjeb2445.zip", "file_size": "1.9 MB" }, { "file_name": "refex_expression18_rnaseq10_mouse_prjna30467.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression18_rnaseq10_mouse_prjna30467.zip", "file_size": "307 KB" }, { "file_name": "refex_expression19_rnaseq40_human_prjeb2445.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression19_rnaseq40_human_prjeb2445.zip", "file_size": "3.2 MB" }, { "file_name": "refex_expression20_rnaseq40_mouse_prjna30467.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_expression20_rnaseq40_mouse_prjna30467.zip", "file_size": "344 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "EST\r\nhuman,mouse,rat: INSD\r\nGeneChip\r\nhuman: GSE7307（Human body index - transcriptional profiling）\r\nmouse: GSE10246（GNF Mouse GeneAtlas V3）\r\nrat: GSE952（Transcriptome analysis in rat）\r\nCAGE\r\nhuman: PRJDB3010 (A promoter level mammalian expression atlas (human, ChIP-Seq))\r\nmouse: PRJDB1100 (FANTOM5 Mouse CAGE)\r\nRNA-seq\r\nhuman: PRJEB2445 (RNA-Seq of human individual tissues and mixture of 16 tissues (Illumina Body Map))\r\nmouse: PRJNA30467（Mapping and quantifying mammalian transcriptomes by RNA-Seq; brain, liver, muscle）", "analysis": "https:\/\/github.com\/dbcls\/RefEx\/tree\/master\/Rawdata_Processing", "data_number": "", "details": [] }, { "path": "en\/refex\/data-3.html", "name": "Tissue Specific Gene Expression Data", "database_name": "RefEx", "doi": "", "description": "Data of tissue specific gene expression calculated by ROKU method.", "files": [ { "file_name": "refex_tissue_specific01_genechip_human_gse7307.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_tissue_specific01_genechip_human_gse7307.zip", "file_size": "560 KB" }, { "file_name": "refex_tissue_specific02_genechip_mouse_gse10246.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_tissue_specific02_genechip_mouse_gse10246.zip", "file_size": "485 KB" }, { "file_name": "refex_tissue_specific03_genechip_rat_gse952.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_tissue_specific03_genechip_rat_gse952.zip", "file_size": "97 KB" }, { "file_name": "refex_tissue_specific04_rnaseq_human_prjeb2445.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_tissue_specific04_rnaseq_human_prjeb2445.zip", "file_size": "462 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "Tissue specificity is calculated based on gene expression data collected by EST, GeneChip, CAGE, or RNA-Seq.", "analysis": "Tissue specificity is calculated for all tissues using the ROKU method of TCC library of Bioconductor. For details of the ROKU method, see http:\/\/bioconductor.org\/packages\/release\/bioc\/manuals\/TCC\/man\/TCC.pdf (pp.22-24)", "data_number": "", "details": [ { "name": "ID", "description": "In GeneChip data and RNA-Seq data, Probe set ID by Affymetrix and NCBI RefSeq ID respectively." }, { "name": "score", "description": "Entropy score. When this score is smaller, specificity of the gene is higher." }, { "name": "v[tissue ID in RefEx]_[name of tissue]", "description": "For each tissue, 1: specific high expression, -1: specific low expression, 0: others" } ] }, { "path": "en\/refex\/data-4.html", "name": "ID Relation Table", "database_name": "RefEx", "doi": "", "description": "Relation table of Gene IDs.", "files": [ { "file_name": "refex_id_relation_human.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_id_relation_human.zip", "file_size": "388 KB" }, { "file_name": "refex_id_relation_mouse.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_id_relation_mouse.zip", "file_size": "406 KB" }, { "file_name": "refex_id_relation_rat.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_id_relation_rat.zip", "file_size": "167 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "NCBI_GeneID", "description": "NCBI Entrez Gene ID" }, { "name": "NCBI_UnigeneID", "description": "NCBI Unigene ID" }, { "name": "NCBI_RefSeqID", "description": "NCBI RefSeq ID" }, { "name": "Affymetrix_probesetID", "description": "Affymetrix probeset ID" }, { "name": "organism", "description": "Organism" } ] }, { "path": "en\/refex\/data-5.html", "name": "Tissue 10\/40 Table", "database_name": "RefEx", "doi": "", "description": "Tissue classification in RefEx.\r\nAs column names of sample ID, \"GSM_#\" are used in GeneChip data, while \"SINGLE\" and \"PAIRED\" in RNA-Seq data.", "files": [ { "file_name": "refex_10_40_classifications01_genechip_human_gse7307.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_10_40_classifications01_genechip_human_gse7307.zip", "file_size": "3 KB" }, { "file_name": "refex_10_40_classifications02_genechip_mouse_gse10246.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_10_40_classifications02_genechip_mouse_gse10246.zip", "file_size": "1 KB" }, { "file_name": "refex_10_40_classifications03_genechip_rat_gse952.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_10_40_classifications03_genechip_rat_gse952.zip", "file_size": "1 KB" }, { "file_name": "refex_10_40_classifications04_rnaseq_human_prjeb2445.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_10_40_classifications04_rnaseq_human_prjeb2445.zip", "file_size": "1 KB" }, { "file_name": "refex_10_40_classifications05_rnaseq_mouse_prjna30467.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_10_40_classifications05_rnaseq_mouse_prjna30467.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Description (RefEx refined)", "description": "Tissue name" }, { "name": "10 groups", "description": "ID of each tissue classified in 10 organs." }, { "name": "40 groups", "description": "ID of each tissue classified in 40 organs." }, { "name": "GSM_#", "description": "IDs of all samples used in experiments of each tissue." }, { "name": "SINGLE", "description": "Data on Single-End RNA-Seq" }, { "name": "PAIRED", "description": "Data on Pair-End RNA-Seq" } ] }, { "path": "en\/refex\/data-6.html", "name": "Sample Annotations", "database_name": "RefEx", "doi": "", "description": "Sample annotations provided by each project.\r\nColumns are different in CAGE data and GeneChip data.", "files": [ { "file_name": "refex_sample_ann01_cage_human_prjdb1099", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_sample_ann01_cage_human_prjdb1099.zip", "file_size": "27 KB" }, { "file_name": "refex_sample_ann02_cage_mouse_prjdb1100", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_sample_ann02_cage_mouse_prjdb1100.zip", "file_size": "11 KB" }, { "file_name": "refex_sample_ann03_genechip_mouse_gse10246", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_sample_ann03_genechip_mouse_gse10246.zip", "file_size": "3 KB" }, { "file_name": "refex_sample_ann04_genechip_rat_gse952", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/refex\/LATEST\/refex_sample_ann04_genechip_rat_gse952.zip", "file_size": "2 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/refex_data_relationship_matrix#en", "data_acquisition": "Provided by each project", "analysis": "", "data_number": "", "details": [ { "name": "CAGE", "description": "" }, { "name": "FANTOM5 Original Order", "description": "Order defined in FANTOM5" }, { "name": "Alphabetical Uniq Order by developmental, primary cells", "description": "Alphabetical order" }, { "name": "RefEx Tissue Class10", "description": "ID of each tissue classified in 10 organs." }, { "name": "RefEx Tissue Class40", "description": "ID of each tissue classified in 40 organs." }, { "name": "Cell Class", "description": "Class of cell based on its property." }, { "name": "Tissue Class", "description": "Class of tissue based on its property." }, { "name": "Description (RefEx refined)", "description": "Additional information on samples provided by RefEx." }, { "name": "FANTOM5 URL", "description": "URL for information on samples provided by FANTOM5." }, { "name": "Description (FANTOM5)", "description": "Additional information on samples provided by FANTOM5." }, { "name": "GeneChip", "description": "" }, { "name": "Accession", "description": "GEO accession of sample" }, { "name": "Title", "description": "Sample name" }, { "name": "Sample Type", "description": "Type of sample" }, { "name": "Taxonomy", "description": "Organism" }, { "name": "Channels", "description": "The number of kind of fluorescent pigments in Microarray." }, { "name": "Platform", "description": "GEO accession of experimental platform" }, { "name": "Series", "description": "GEO accession of series the sample belongs in." }, { "name": "Supplementary Types", "description": "Formats of available raw data file" }, { "name": "Supplementary Links", "description": "URL for raw data file" }, { "name": "SRA Accession", "description": "SRA accession" }, { "name": "Contact", "description": "Contact about data" }, { "name": "Release Date", "description": "Release date of data" } ] }, { "path": "en\/rgp-caps\/data-1.html", "name": "Information of the markers in each chromosome", "database_name": "RGP caps", "doi": "10.18908\/lsdba.nbdc00318-05-001", "description": "Information of the STS and CAPS markers in each chromosome.", "files": [ { "file_name": "rgp_caps_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-caps\/LATEST\/rgp_caps_main.zip", "file_size": "18.5 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_caps_main#en", "data_acquisition": "STS markers : The 161 STS markers have been developed using clone-specific sequences (3'end) designed from the EST sequence derived from several cDNA libraries (Yamamoto et al. 1997 Plant Mol Biol 35: 135-144).\r\n \r\nCAPS markers : We have developed 171 CAPS markers including 6 derived CAPS (dCAPS) markers (Konieczny and Ausbel 1993 Plant J. 4: 403-410, Neff et al. 1998 Plant J. 14: 387-392) using the information derived from a high-density RFLP linkage map (A HIGH-DENSITY RICE GENETIC MAP, Harushima et al. 1998, The Latest High-Density Rice Genetic Map, Including 3267 Markers, Rice Genome Research Program 2000).", "analysis": "STS markers : The chromosomal location of each marker has been identified by EST mapping (Wu et al. 2002 Plant Cell 14: 525--535) using a YAC-based physical map of rice. For all polymorphic markers, we have confirmed the chromosomal location by linkage analysis using 46 randomly selected BILs (Lin et al. 1998 Theor Appl Genet 96: 997-1003). Amplification was performed in GeneAmp PCR System 9600 (Perkin-Elmer).\r\n \r\nCAPS markers : Using 5' and 3' sequence data for the clones used for RFLP linkage analysis, we designed unique primer pairs for the specific amplification of genome. Then, restriction digestion was carried out to detect polymorphism. In order to confirm the chromosomal location of CAPS markers, linkage analysis was performed using 14 randomly selected F2 plants (Harushima et al. 1998 Genetices 148: 479-494). Amplification was performed in GeneAmp PCR System 9600 (Perkin-Elmer).", "data_number": "527 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Position in a YAC physical map (cM)", "description": "Position in a YAC physical map (genetic distance, cM)" }, { "name": "Marker name", "description": "Marker name" }, { "name": "Type of marker", "description": "Type of marker.\r\nPolymorphism between Nipponbare and Kasalath were revealed by STS, CAPS, or dCAPS.\r\nNP indicates that no polymorphism was detected between Nipponbare and Kasalath." }, { "name": "Enzyme", "description": "Restriction enzymes used for CAPS and dCAPS to detect polymorphism between Nipponbare and Kasalath. No digestion is needed for STS markers." }, { "name": "Amplified band size (bp)", "description": "Amplified band size in Nipponbare (bp)" }, { "name": "5' primer sequence", "description": "5' primer sequence" }, { "name": "3' primer sequence", "description": "3' primer sequence" }, { "name": "Mapping population", "description": "Mapping population" }, { "name": "Position", "description": "Chromosomal location of each marker is shown by either the RFLP marker co-segregated or the interval of flanking RFLP markers on the previously reported linkage map (Harushima et al. 1998 Genetices 148: 479-494, Lin et al.1998 Theor Appl Genet 96: 997-1003)." }, { "name": "Comment", "description": "Comment" }, { "name": "Image file name 1", "description": "Image file name 1 of gel electrophoresis" }, { "name": "Image file name 2", "description": "Image file name 2 of gel electrophoresis" }, { "name": "Image file name 3", "description": "Image file name 3 of gel electrophoresis" }, { "name": "Image file name 4", "description": "Image file name 4 of gel electrophoresis" } ] }, { "path": "en\/rgp-caps\/data-2.html", "name": "Images of gel electrophoresis", "database_name": "RGP caps", "doi": "10.18908\/lsdba.nbdc00318-05-002", "description": "Detailed information and images of gel electrophoresis of each marker.", "files": [ { "file_name": "rgp_caps_electrophoresis_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-caps\/LATEST\/rgp_caps_electrophoresis_image.zip", "file_size": "28.7 MB" } ], "togodb_url": "", "data_acquisition": "Gel electrophoresis", "analysis": "STS markers :\r\nThe reaction mixture for PCR amplification consisted of 25 ng total DNA, 200 mM of each dNTP (Boehringer Mannheim), 20 pmol primers (5' and 3' primers), 2 units of Taq DNA polymerase (Perkin-Elmer), PCR buffer (10 mM Tris pH 8.3 at 25°C, 50 mM KCl, and 0.001% (w\/v) gelatin), and 40 mM MgCl2 in 20.0 μL volume. Amplification was performed in GeneAmp PCR System 9600 (Perkin-Elmer) with 35 cycles of 94°C (1 min), 60°C (1 min), and 72°C (2 min), and a final cycle of 72°C for 7 min. The amplified DNA products were electrophoresed on 3.0% agarose gels in 0.5 x TBE buffer at 120 V for 2 h, and stained with ethidium bromide. The size standard marker for electrophoretic analysis was mixture of HindIII digests of λDNA and HaeIII digests of φX174DNA.\r\n \r\nCAPS markers :\r\nPCR amplification was performed using the GeneAmp PCR System 9600 and the following amplification condition: 30 cycles of 94°C (1 min), 60°C (2 min), and 72°C (3 min), and a final cycle of 72°C for 7 min. The amplified products of each primer pair were digested with 28 restriction enzymes (PstI, HindIII, BamHI, EcoRI, ApaI, XhoI, KpnI, HaeIII, DraI, XbaI, SalI, EcoT14I, MspI, HinfI, EcoRV, BglII, SacI, HhaI, EcoT22I, HapII, ScaI, AfaI, MluI, PshBI, MboI, MvaI, SacII, and HincII). For some markers, the amplified products were further digested with 14 more restriction enzymes (AccII, AluI, AvaII, BcnI, Cfr13I, AccI, AvaI, BanII, Cfr10I, EaeI, HaeII, MflI, Bsp1286I, and TthHB8I). The digested products were electrophoresed on 2.0% agarose gels in 0.5 x TBE buffer at 120 V for 2 h, and stained with ethidium bromide. For dCAPS marker development, we performed the genomic DNA sequencing to identify nucleotide polymorphisms between Nipponbare and Kasalath, and created a unique restriction site into the PCR product in one of varieties by combination of the nucleotide polymorphism with mismatch primer sequences. PCR amplifications with dCAPS primers were carried out at the same condition as that with CAPS primers and the resultant products were digested with the enzyme. The digested products was electrophoresed on 4.0% agarose gels in 0.5 x TBE buffer at 120 V for 2 h, and stained with ethidium bromide.", "data_number": "673 files", "details": [] }, { "path": "en\/rgp-estmap2001\/data-1.html", "name": "Statistics information of rice EST mapping results", "database_name": "RGP estmap2001", "doi": "10.18908\/lsdba.nbdc00318-04-001", "description": "Summary of Rice EST Mapping Results per each chromosome.\r\nThe map is composed of 2782 YAC clones, containing 364 YAC contigs with 6591 assigned EST sites from 6421 unique sequences, and covers 80.8% of the rice genome.", "files": [ { "file_name": "rgp_estmap2001_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-estmap2001\/LATEST\/rgp_estmap2001_main.zip", "file_size": "597 B" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_estmap2001_main#en", "data_acquisition": "Numeric data calculated during construction of a YAC-Based Rice Transcript Map.", "analysis": "Number of YAC clones and contigs that was used to make rice EST mapping of each type of Chromosome were counted. Also, the coverage and average EST density was calculated.", "data_number": "14 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number\r\n(UN: Chromosome unknown)" }, { "name": "YAC Clones", "description": "Number of YAC clones" }, { "name": "YAC Contigs", "description": "Number of YAC contigs" }, { "name": "Total Length of YAC Contigs (Mb)", "description": "Total length of YAC contigs (Mb)" }, { "name": "Coverage (%)", "description": "Coverage (%)\r\n= Total length (Mb) of YAC contigs \/ ( genetic length of chromosome (cM) x 430 (Mb) \/ 1530.4 (cM) ) x 100" }, { "name": "EST Sites", "description": "Number of EST sites" }, { "name": "Ave EST Density (EST\/100 kb)", "description": "Average EST density (EST\/100 kb)\r\n= Number of ESTs \/ total length of YAC contigs" }, { "name": "Contig Image File", "description": "Image file name of chromosomal distribution" } ] }, { "path": "en\/rgp-estmap2001\/data-2.html", "name": "Details of rice EST mapping results", "database_name": "RGP estmap2001", "doi": "10.18908\/lsdba.nbdc00318-04-002", "description": "The data contains the detailed results of PCR-based YAC screening with the clone-specific EST primers.", "files": [ { "file_name": "rgp_estmap2001_detail.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-estmap2001\/LATEST\/rgp_estmap2001_detail.zip", "file_size": "242 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_estmap2001_detail#en", "data_acquisition": "We used clone-specific primer pairs designed from 6713 unique EST sequences (3' end) derived from 19 cDNA libraries.", "analysis": "SEGMAP (version 3.48) was used for the analysis of YAC screening data and the establishment of the EST map.\r\nDNA gel blot hybridization of YAC or rice genomic DNA with genetic markers or EST clones was conducted using the enhanced chemiluminescence system (Amersham, Buckinghamshire, UK).\r\n \r\nNotes\r\n#; floating markers on the genetic map\r\nc; chimeric YAC clones\r\n*; PCR band size longer than predicted\r\nAnn T; 60 ℃ unless otherwise indicated\r\nNI; YACs with unknown insert", "data_number": "6,760 entries", "details": [ { "name": "Anchor", "description": "Genetic markers used for YAC landing" }, { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Position (cM)", "description": "Genetic distance (cM)" }, { "name": "EST Clone", "description": "EST Clone (sites) name" }, { "name": "DDBJ Acc FW", "description": "DDBJ accession of the EST clone (Forward sequence)" }, { "name": "DDBJ Acc RV", "description": "DDBJ accession of the EST clone (Reverse sequence)" }, { "name": "Positive YACs", "description": "Positive YAC names" }, { "name": "PCR Primer", "description": "PCR primer name" }, { "name": "Amplified Band Size", "description": "Amplified PCR band size (kb)" }, { "name": "Ann T", "description": "Annealing temperature (℃)" }, { "name": "5'-Primer Sequence", "description": "Primer sequence (5' primer, each 20 bases)" }, { "name": "3'-Primer Sequence", "description": "Primer sequence (3' primer, each 20 bases)" }, { "name": "Map Image File", "description": "Image file name of the rice transcript map" } ] }, { "path": "en\/rgp-estmap2001\/data-3.html", "name": "The rice transcript map", "database_name": "RGP estmap2001", "doi": "10.18908\/lsdba.nbdc00318-04-003", "description": "Images of a YAC-Based rice transcript map containing 6591 EST Sites.", "files": [ { "file_name": "rgp_estmap2001_map_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-estmap2001\/LATEST\/rgp_estmap2001_map_image.zip", "file_size": "4.9 MB" } ], "togodb_url": "", "data_acquisition": "YAC screening, DNA gel blot hybridization", "analysis": "Figures contain the rice genetic and YAC physical maps with the assigned EST sites. From left to right in each YAC contig: anchor (genetic markers used for YAC landing), genetic distance (cM), estimated physical distance (kb) of YAC contigs, YAC contig and EST sites (multiple sites of an EST are indicated by alphabets after the name) are shown. Vertical bars on the left of EST names indicate the estimated distribution range of sites where the relative order of each site could be changeable. Relative order as well as direction of YAC contigs anchored by the genetic markers with the same genetic distance (often observed in the regions around the centromeres) also could be changeable.", "data_number": "352 entries", "details": [] }, { "path": "en\/rgp-gmap\/data-1.html", "name": "Statistics of DNA Markers", "database_name": "RGP gmap", "doi": "10.18908\/lsdba.nbdc00318-01-001", "description": "Statistics of DNA markers that were used to create the rice genetic map.", "files": [ { "file_name": "rgp_gmap_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap\/LATEST\/rgp_gmap_main.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap_main#en", "data_acquisition": "Numeric data calculated during construction of a genetic linkage map.", "analysis": "Number of clones of each type of marker were counted.\r\nSegregation patterns in 186 F2 plants were detected by DNA hybridization signals on X-ray film for RFLP or by electrophoresis for RAPD markers and analyzed with MAPMAKER\/EXP 3.0.\r\nThe error detection was performed with MAPMAKER\/EXP 3.0 using the errot detection-on mode. All the candidate errors were reinspected in genotype segregation with further Southern hybridization analysis. Most of the residual candidate errors came from the array of genotypes of hetero-homo-hetero, with false counting of errors (w-cross overs). Therefore, the map distance was calculated by error detection-off mode.", "data_number": "13 entries", "details": [ { "name": "Chrom. No.", "description": "Number of chromosome (In Simple search site, the chromosome number link to the site of \"Detailed information of DNA markers\", and the image file name link to the map image.)" }, { "name": "No. of callus cDNA clones", "description": "Number of callus cDNA clones" }, { "name": "No. of root cDNA clones", "description": "Number of root cDNA clones" }, { "name": "No. of random genomic clones", "description": "Number of random genomic clones" }, { "name": "No. of NotI-linking clones", "description": "Number of NotI-linking clones" }, { "name": "No. of YAC end clones", "description": "Number of YAC end clones" }, { "name": "No. of telomere-associated clones", "description": "Number of telomere-associated clones" }, { "name": "No. of RAPD markers", "description": "Number of RAPD markers" }, { "name": "No. of STS markers", "description": "Number of STS markers" }, { "name": "No. of wheat clones", "description": "Number of wheat clones" }, { "name": "No. of other clones", "description": "Number of other clones" }, { "name": "Total marker number", "description": "Total marker number" }, { "name": "Total length in error detection off mode", "description": "Total length in Kosambi map function by error detection off mode of MAPMAKER\/EXP" }, { "name": "Total length in error detection on mode", "description": "Total length in Kosambi map function by error detection on mode of MAPMAKER\/EXP" }, { "name": "Difference between error detection on and off mode (cM)", "description": "Difference between error detection on and off mode (cM)" }, { "name": "Difference between error detection on and off mode (%)", "description": "Difference between error detection on and off mode (%)" }, { "name": "No. of candidate errors by MAPMAKER\/EXP", "description": "Number of the candidate errors shown by MAPMAKER\/EXP 3.0" }, { "name": "Total number of observed genotypes", "description": "The total number of the observed genotypes to calculate the map" }, { "name": "Average number of observed genotypes per marker", "description": "An avarege of the number of the observed genotypes per marker" } ] }, { "path": "en\/rgp-gmap\/data-2.html", "name": "Detailed information of DNA markers", "database_name": "RGP gmap", "doi": "10.18908\/lsdba.nbdc00318-01-002", "description": "Detailed information of DNA markers that were used to create the rice genetic map.", "files": [ { "file_name": "rgp_gmap_marker.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap\/LATEST\/rgp_gmap_marker.zip", "file_size": "28.3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap_marker#en", "data_acquisition": "As the source of polymorphic DNA markers for map construction, we used two types of cDNA clones (callus and roots), three types of genomic clones (randomly selected clone, NotI-linking clone, YAC end-clone) and RAPD (Randomly amplified polymorphic DNA) markers, all of which were derived from the japonica rice cultivar, Niponbare. About 90 other DNA clones derived from wheat and other rice varieties were also utilized.", "analysis": "A NotI-linking clone is a Sau3AI digested Nipponbare genomic DNA fragment having NotI site in it. For the selection from the other fragments, NotI-linking clones were cloned with a hygromycin resistance gene at the NotI site. Therefore, genomic inserts of NotI-linking clones were divided by inserting the hygromycin resistance gene in the middle of the cloned fragment. When we map NotI-linking clone, we prepare a PCR product by special primers, named T3, T7, Nos, and 35S, or use a digested fragment of a pair of restriction enzymes.\r\nThe sequences are as follows:\r\nT3 5'-ATTAACCCTCACTAAAG-3'\r\nT7 5'-AATACGACTCACTATAG-3'\r\n35S 5'-TGTGGGTTAGCATTCTTTCTG-3'\r\nNos 5'-TTACTAGATCGGGAATTGCCA-3'\r\n \r\nMost of the probe sizes are the PCR product sizes by M4 and RV primers.\r\nM4 5'-GTTTTCCCAGTCACGAC-3'\r\nRV 5'-CAGGAAACAGCTATGAC-3'\r\n\r\nThe probe sizes of the W-markers are the original insert sizes communicated by Dr. Michael Gale, John Innes Centre, Norwich, UK.\r\nFurther analysis was performed with MAPMAKER\/EXP 3.0.", "data_number": "1,381 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Two-point distance (cM)", "description": "The two-point distances to the previous markers (cM)" }, { "name": "Position (cM)", "description": "Marker position in the chromosome (cM)" }, { "name": "Locus name", "description": "Locus name" }, { "name": "DDBJ accession No.", "description": "DDBJ accession number(s) of the marker sequence" }, { "name": "Restriction enzyme", "description": "Names of restriction enzymes to detect the polymorphism between Nipponbare and Kasalath" }, { "name": "Nipponbare band size (kb)", "description": "Southern band size of Nipponbare (kb)" }, { "name": "Kasalath band size (kb)", "description": "Southern band size of Kasalath (kb)" }, { "name": "Probe size (kb)", "description": "Probe size" }, { "name": "Vector", "description": "Cloning vector" }, { "name": "Cloning site", "description": "Cloning site" }, { "name": "Special primers or restriction enzymes for NotI-linking clone", "description": "Special primer set or restriction enzyme set for the preparation of NotI-linking marker" }, { "name": "RAPD primer sequence 1", "description": "RAPD marker primer sequence 1" }, { "name": "RAPD primer sequence 2", "description": "RAPD marker primer sequence 2" }, { "name": "PCR protocol for RAPD and STS markers", "description": "PCR protocol of RAPD and STS markers" }, { "name": "Image file name", "description": "Southern image file name" } ] }, { "path": "en\/rgp-gmap\/data-3.html", "name": "Southern images", "database_name": "RGP gmap", "doi": "10.18908\/lsdba.nbdc00318-01-003", "description": "Parents Southern hybridization image files.", "files": [ { "file_name": "rgp_gmap_southern_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap\/LATEST\/rgp_gmap_southern_image.zip", "file_size": "37.3 MB" } ], "togodb_url": "", "data_acquisition": "Southern hybridization", "analysis": "For genotype segregation in F2 plants, Southern hybridization was performed with DNAs digested with the restriction enzymes; BamHI, BglII, EcoRV, HindIII, ApaI, DraI, EcoRI, KpnI.", "data_number": "1,181 files", "details": [] }, { "path": "en\/rgp-gmap2000\/data-1.html", "name": "High-density linkage map information", "database_name": "RGP gmap2000", "doi": "10.18908\/lsdba.nbdc00318-03-001", "description": "Information of High-density linkage maps of rice RFLP (Restriction Fragment Length Polymorphism).", "files": [ { "file_name": "rgp_gmap2000_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap2000\/LATEST\/rgp_gmap2000_main.zip", "file_size": "30.0 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap2000_main#en", "data_acquisition": "The rice RFLP linkage map was composed of a combination of nearly 1000 new RFLP marker and markers described in \"A High-Density Rice Genetic Map 1998\", which contains total 3267 DNA markers.\r\nFor the RFLP analysis of additional markers, we often used the 3' untranslated region (UTR) of a cDNA fragment as a probe rather than the whole insert. In such a case, the marker name ends with the letter S. To amplify the 3'UTR as well as the desired portion of the insert, use the universal primer M13RV and the appropriate specific primer that can be designed using sequence data of the 3' ends.\r\nThe marker designation and other miscellaneous details follow the data at \"A High-Density Rice Genetic Map 1998\".", "analysis": "This table includes the map position of each marker from the telomeric end of the short arm of each chromosome (genetic distance in cM), the chromosome number, the marker name, and (where available) DDBJ accession numbers of the sequences of both the 5' and 3' ends of insert fragments of the probes used in the RFLP analysis.\r\nFurther analysis was performed with MAPMAKER\/EXP 3.0.", "data_number": "3,267 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Floating marker", "description": "Floating marker.\r\n\"F\" in this column indicates that the segregation data of the locus did not show any recombination to the loci with the different positions.\r\nIf \"F\" is indicated in the column, the minimum position is shown in column \"position\" and the maximum position is shown in column \"max\"." }, { "name": "Position", "description": "The genetic distance of the locus from the short arm end.\r\nIf \"F\" is indicated in \"Floating marker\" column, the minimum position is shown in this column." }, { "name": "Max", "description": "If \"F\" is indicated in \"Floating marker\" column, the maximum position is shown in this column." }, { "name": "Marker name", "description": "Marker name: The \"Marker name\" corresponds to the \"Real name\" in \"Detailed information of DNA markers\"." }, { "name": "Accession 5'_1", "description": "The DDBJ sequence accession number for 5' end of insert fragment that was used as a probe." }, { "name": "Accession 5'_2", "description": "If there are two accession numbers for 5' end, another number is shown in this column." }, { "name": "Accession 3'", "description": "The DDBJ sequence accession number for 3' end" } ] }, { "path": "en\/rgp-gmap2000\/data-2.html", "name": "Detailed information of DNA markers", "database_name": "RGP gmap2000", "doi": "10.18908\/lsdba.nbdc00318-03-002", "description": "Detailed information of DNA markers that were used to create the rice genetic map.", "files": [ { "file_name": "rgp_gmap2000_marker.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap2000\/LATEST\/rgp_gmap2000_marker.zip", "file_size": "46.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap2000_marker#en", "data_acquisition": "As the source of polymorphic DNA markers for map construction, we used two types of cDNA clones (callus and roots), three types of genomic clones (randomly selected clone, NotI-linking clone, YAC end-clone) and RAPD (Randomly amplified polymorphic DNA) markers, all of which were derived from the japonica rice cultivar, Niponbare. Other DNA clones derived from wheat and other rice varieties were also utilized.", "analysis": "The probe sizes of the W-markers are the original insert sizes communicated by Dr. Michael Gale, John Innes Centre, Norwich, UK.\r\nFurther analysis was performed with MAPMAKER\/EXP 3.0.", "data_number": "3,267 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Locus name", "description": "Locus name" }, { "name": "Real name", "description": "If the polymorphism is detected at multiple locations, the locus name of marker that match the original sequence information is referred to as \"Real name\". The \"Real name\" corresponds to the \"Marker name\" in \"\"High-density linkage map information\"." }, { "name": "Restriction enzyme", "description": "Names of restriction enzymes to detect the polymorphism between Nipponbare and Kasalath" }, { "name": "Nipponbare band size (kb)", "description": "Southern band size of Nipponbare (kb)" }, { "name": "Kasalath band size (kb)", "description": "Southern band size of Kasalath (kb)" }, { "name": "Probe size (kb)", "description": "Probe size" }, { "name": "Vector", "description": "Cloning vector" }, { "name": "Cloning site", "description": "Cloning site" }, { "name": "Special primers or restriction enzymes for NotI-linking clone", "description": "Special primer set or restriction enzyme set for the preparation of NotI-linking marker" }, { "name": "Primer sequence 1", "description": "Primer sequence 1 of marker" }, { "name": "Primer sequence 2", "description": "Primer sequence 2 of marker" }, { "name": "PCR protocol", "description": "PCR protocol for markers" }, { "name": "Image file name", "description": "Parental Southern image file name" } ] }, { "path": "en\/rgp-gmap98\/data-1.html", "name": "The linked list of data", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-001", "description": "List of link information to related data on each chromosome of rice high-density linkage maps.", "files": [ { "file_name": "rgp_gmap98_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_main.zip", "file_size": "355 B" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap98_main#en", "data_acquisition": "", "analysis": "", "data_number": "12 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Genotype data", "description": "The link to genotypical data for all segregants (186 individuals) on a simple search site" }, { "name": "Linkage order", "description": "The link to marker information in order of the linkage map on a simple search site" }, { "name": "Map image file", "description": "The link to rice high-density linkage maps on a simple search site" } ] }, { "path": "en\/rgp-gmap98\/data-2.html", "name": "High-density linkage map information", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-002", "description": "Information of High-density RFLP (Restriction Fragment Length Polymorphism) linkage map of rice.", "files": [ { "file_name": "rgp_gmap98_detail.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_detail.zip", "file_size": "37.2 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap98_detail#en", "data_acquisition": "We used a marker derived from a cDNA clone of Nipponbare. The position of the locus has been identified by examining a recombination value between Nipponbare and Kasalath experimentally. An annotation for the sequence of the marker was estimated using a protein database. 1174 points are discrete positions on the map; each chromosome, 159, 129, 148, 95, 107, 104, 88, 83, 54, 68, 79, 60.", "analysis": "The 186 F2 plant mapping population used was derived from rice cultivars Nipponbare and Kasalath.\r\nThe main sources of the markers in this map derives from various cDNA libraries of Nipponbare, and markers are indicated by clone names denoted with C, R, G, Y, L, P, T, W, B, M, V or TEL numbers.\r\n \r\nThe first letter of the marker name indicates the category of mapped clones as follows:\r\nC, cDNA clones derived from callus library;\r\nR, cDNAs from root library;\r\nG, random genomic clones;\r\nY, YAC-end clones;\r\nL, NotI-linking clones;\r\nP, randomly amplified polymorphic DNAs;\r\nT, STS markers;\r\nW, wheat clones;\r\nB, barley clones;\r\nM, maize clones;\r\nTEL, telomere-associated sequences;\r\nS, cDNAs from etiolated shoot (S with numbers 10,000);\r\nF, cDNAs from shoot of a near-isogenic line;\r\nand V and other symbols (Ky4, Kyu08, Kyy03, SINE1_r6), clones derived from other rice varieties.\r\n \r\nW numbers correspond to the PSR numbers of clones developed by M. D. Gale (John Innes Centre, UK). Markers denoted with a V contain both genomic and cDNA clones including SINE1r6 isolated in other works. Letters A, B, C and D following the clone number indicate that those loci were assigned by mapping with one of the polymorphic DNA fragments of the multiple copy sequences. L and R following the Y number marker indicate left and right end clones, respectively, of YAC clones.\r\nName etc of protein coded by determination of location of RFLP markers were estimated by a similarity search in both the PIR (Rel.48.0) and SWISS-PROT (Rel.33) protein databases.", "data_number": "2,275 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Floating marker", "description": "Floating marker\r\n\"F\" in this column indicates that the segregation data of the locus did not show any recombinations to those of the loci with the different positions.\r\nIf \"F\" is indicated in this column, the minimum position is shown in \"Position\" column, and the maximum position is shown in \"Max\" column." }, { "name": "Position", "description": "The position of the locus from the short arm end.\r\nIf \"F\" is indicated in \"Floating marker\" column, this column is shown the minimum position." }, { "name": "Max", "description": "If \"F\" is indicated in \"Floating marker\" column, this column is shown the maximum position" }, { "name": "Arm", "description": "Chromosome arm was confirmed in strains of telo-torisomy, by markers used to determine the position of the centromere on linkage map" }, { "name": "Locus name", "description": "Locus name" }, { "name": "Image file name", "description": "Parental Southern image file name" }, { "name": "Accession", "description": "DDBJ accession number of the marker" }, { "name": "Accession 2", "description": "If marker has two accession numbers, another number is shown in this column" }, { "name": "Orignal clone name", "description": "The original name of the clone" }, { "name": "Protein", "description": "Name of the most similar protein appearing in PIR database R48.0 and SWISS-PROT R33" }, { "name": "Organism", "description": "Organism of the most similar protein appearing in PIR database R48.0 and SWISS-PROT R33" }, { "name": "Score", "description": "Bits score of the most similar protein appering in PIR database R48.0 and SWISS-PROT R33" } ] }, { "path": "en\/rgp-gmap98\/data-3.html", "name": "List of isozyme loci", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-003", "description": "List of information about a cDNA clone that were mapped in the present high-density linkage map, and that were putatively identified as isozyme genes.", "files": [ { "file_name": "rgp_gmap98_isozyme_loci.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_isozyme_loci.zip", "file_size": "611 B" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap98_isozyme_loci#en", "data_acquisition": "The data were acquired by similarity search of the cDNA using the protein database.", "analysis": "The cDNA inserts were sequenced from the 5' end for 300-400 bp, and were searched for sequence similarities in both the PIR (Rel. 48.0) and SWISS-PROT (Rel. 33) protein databases. The BLOSUM50 matrix was used for scoring similarity. After a similarity search, clones showing the best score with the expected value", "data_number": "15 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Isozyme locus", "description": "Isozyme locus" }, { "name": "Enzyme name", "description": "Enzyme name" }, { "name": "cDNA locus 1", "description": "cDNA locus 1" }, { "name": "Position 1", "description": "Position 1" }, { "name": "cDNA locus 2", "description": "cDNA locus 2" }, { "name": "Position 2", "description": "Position 2" }, { "name": "cDNA locus 3", "description": "cDNA locus 3" }, { "name": "Position 3", "description": "Position 3" }, { "name": "cDNA locus 4", "description": "cDNA locus 4" }, { "name": "Position 4", "description": "Position 4" } ] }, { "path": "en\/rgp-gmap98\/data-4.html", "name": "Genotype data", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-004", "description": "Genotype data for all segregants (186 individuals) of each chromosome.", "files": [ { "file_name": "rgp_gmap98_genotype_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_genotype_data.zip", "file_size": "48.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap98_genotype_data#en", "data_acquisition": "These data are the results of linkage analysis that used 186 F2 plants from a single cross between Nipponbare and Kasalath.", "analysis": "Linkage analysis was performed using MAPMAKER\/EXP 3.0.", "data_number": "2,277 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Locus", "description": "Locus name" }, { "name": "Genetic code", "description": "Genetic code by MAPMAKER" } ] }, { "path": "en\/rgp-gmap98\/data-5.html", "name": "Linkage order information", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-005", "description": "About the 1174 frame markers of the linkage map, following informations were listed by each chromosome; marker names, genetic distance to the next marker, number of genotyped plants, and genetic types of marker.", "files": [ { "file_name": "rgp_gmap98_linkage_order.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_linkage_order.zip", "file_size": "8.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_gmap98_linkage_order#en", "data_acquisition": "", "analysis": "Preferred orders of markers with different positions on entire chromosomes were checked by the \"ripple\" command with window size 5 and an LOD threshold of 2.0.", "data_number": "1,174 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Order", "description": "Linkage order" }, { "name": "Markers", "description": "Marker name" }, { "name": "Distance", "description": "The genetic distance to the next marker (cM)" }, { "name": "Genotypes", "description": "The genotypical number that was observed per each marker in mapping population.\r\ncodom : Codominant marker\r\n+\/- : Dominant marker" } ] }, { "path": "en\/rgp-gmap98\/data-6.html", "name": "Southern images", "database_name": "RGP gmap98", "doi": "10.18908\/lsdba.nbdc00318-02-006", "description": "Parental Southern hybridization image files.", "files": [ { "file_name": "rgp_gmap98_southern_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-gmap98\/LATEST\/rgp_gmap98_southern_image.zip", "file_size": "69.2 MB" } ], "togodb_url": "", "data_acquisition": "Southern hybridization", "analysis": "For genotype segregation in F2 plants, Southern hybridization was performed with DNAs digested with the restriction enzymes; BamHI, BglII, EcoRV, HindIII, ApaI, DraI, EcoRI, KpnI.", "data_number": "3,157 files", "details": [] }, { "path": "en\/rgp-physicalmap\/data-1.html", "name": "YAC contig information", "database_name": "RGP physicalmap", "doi": "10.18908\/lsdba.nbdc00318-06-001", "description": "YAC contigs on the rice chromosomes", "files": [ { "file_name": "rgp_physicalmap_yac_contigs.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-physicalmap\/LATEST\/rgp_physicalmap_yac_contigs.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_physicalmap_yac_contigs#en", "data_acquisition": "The range including YAC contig is shown for each the divided region within the chromosome. DNA marker names are different to those in \"YAC clone information\". For example, P61 and P0061 represents the same marker.\r\n \r\nPlease refer to the following literature for the acquisition method of YAC clone data.\r\n \r\nChromosome 1 : Wang et.al (1996), DNA Research, 3(5): 291-296.\r\nChromosome 2 : Umehara et.al (1997), DNA Research, 4(2): 127-131.\r\nChromosomes 3 and 11 : Tanoue et.al (1997), DNA Research, 4(2): 133-140.\r\nChromosomes 4 and 7 : Koike et.al (1997), DNA Research, 4(1): 27-33.\r\nChromosome 5 : Saji et.al (1996), DNA Research, 3(5): 297-302.\r\nChromosome 6 : Umehara et.al (1996), Genome Research, 6(10): 935-942.\r\nChromosomes 8 and 9 : Antonio et.al (1996), DNA Research, 3(6): 393-400.\r\nChromosomes 10 and 12 : Shimokawa et.al (1996), DNA Research, 3(6): 401-406.", "analysis": "", "data_number": "38 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Region", "description": "Region number" }, { "name": "Physical map image", "description": "The file name of rice physical map" }, { "name": "First marker", "description": "First DNA marker" }, { "name": "Distance of first marker (cM)", "description": "Distance of the first marker from the top of each chromosome (cM)" }, { "name": "Last marker", "description": "Last DNA marker" }, { "name": "Distance of last marker (cM)", "description": "Distance of the last marker from the top of each chromosome (cM)" } ] }, { "path": "en\/rgp-physicalmap\/data-2.html", "name": "YAC clone information", "database_name": "RGP physicalmap", "doi": "10.18908\/lsdba.nbdc00318-06-002", "description": "YAC clones selected with DNA markers", "files": [ { "file_name": "rgp_physicalmap_yac_clones.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-physicalmap\/LATEST\/rgp_physicalmap_yac_clones.zip", "file_size": "18.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_physicalmap_yac_clones#en", "data_acquisition": "YAC clones selected with RGP DNA markers in each chromosome are listed. DNA marker names are different to those in \"YAC contig information\". For example, P0061 and P61 represents the same marker.\r\n \r\nPlease refer to the following literature for the acquisition method of YAC clone data.\r\n \r\nChromosome 1 : Wang et.al (1996), DNA Research, 3(5): 291-296.\r\nChromosome 2 : Umehara et.al (1997), DNA Research, 4(2): 127-131.\r\nChromosomes 3 and 11 : Tanoue et.al (1997), DNA Research, 4(2): 133-140.\r\nChromosomes 4 and 7 : Koike et.al (1997), DNA Research, 4(1): 27-33.\r\nChromosome 5 : Saji et.al (1996), DNA Research, 3(5): 297-302.\r\nChromosome 6 : Umehara et.al (1996), Genome Research, 6(10): 935-942.\r\nChromosomes 8 and 9 : Antonio et.al (1996), DNA Research, 3(6): 393-400.\r\nChromosomes 10 and 12 : Shimokawa et.al (1996), DNA Research, 3(6): 401-406.", "analysis": "", "data_number": "1,136 entries", "details": [ { "name": "Chrom. No.", "description": "Chromosome number" }, { "name": "Region", "description": "Region number" }, { "name": "Physical map image", "description": "The file name of rice physical map" }, { "name": "Order", "description": "Linkage order" }, { "name": "Marker", "description": "Marker name" }, { "name": "Distance (cM)", "description": "The genetic distance from the previous marker (cM)" }, { "name": "YAC clone1", "description": "YAC clone 1\r\nThe YAC name followed by \"c\" shows that the YAC is a chimera." }, { "name": "YAC clone2", "description": "YAC clone 2" }, { "name": "YAC clone3", "description": "YAC clone 3" }, { "name": "YAC clone4", "description": "YAC clone 4" }, { "name": "YAC clone5", "description": "YAC clone 5" }, { "name": "YAC clone6", "description": "YAC clone 6" }, { "name": "YAC clone7", "description": "YAC clone 7" }, { "name": "YAC clone8", "description": "YAC clone 8" }, { "name": "YAC clone9", "description": "YAC clone 9" }, { "name": "YAC clone10", "description": "YAC clone 10" }, { "name": "YAC clone11", "description": "YAC clone 11" }, { "name": "YAC clone12", "description": "YAC clone 12" }, { "name": "YAC clone13", "description": "YAC clone 13" }, { "name": "YAC clone14", "description": "YAC clone 14" }, { "name": "YAC clone15", "description": "YAC clone 15" }, { "name": "YAC clone16", "description": "YAC clone 16" }, { "name": "YAC clone17", "description": "YAC clone 17" }, { "name": "YAC clone18", "description": "YAC clone 18" }, { "name": "YAC clone19", "description": "YAC clone 19" }, { "name": "YAC clone20", "description": "YAC clone 20" }, { "name": "YAC clone21", "description": "YAC clone 21" }, { "name": "YAC clone22", "description": "YAC clone 22" }, { "name": "YAC clone23", "description": "YAC clone 23" }, { "name": "YAC clone24", "description": "YAC clone 24" }, { "name": "YAC clone25", "description": "YAC clone 25" }, { "name": "YAC clone26", "description": "YAC clone 26" }, { "name": "YAC clone27", "description": "YAC clone 27" }, { "name": "YAC clone28", "description": "YAC clone 28" }, { "name": "YAC clone29", "description": "YAC clone 29" }, { "name": "YAC clone30", "description": "YAC clone 30" } ] }, { "path": "en\/rgp-physicalmap\/data-3.html", "name": "Insert size of YAC clones", "database_name": "RGP physicalmap", "doi": "10.18908\/lsdba.nbdc00318-06-003", "description": "Insert size of YAC clones in the physical map", "files": [ { "file_name": "rgp_physicalmap_insert_size.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rgp-physicalmap\/LATEST\/rgp_physicalmap_insert_size.zip", "file_size": "3.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rgp_physicalmap_insert_size#en", "data_acquisition": "YAC size was scaled by Southern hybridization with YAC vector as a probe after gel fractionation using PFGE. YACs are arranged in numerical order.", "analysis": "", "data_number": "962 entries", "details": [ { "name": "YAC No.", "description": "YAC clone number" }, { "name": "YAC insert size (kb)", "description": "Insert size of each YAC clone (kb)" } ] }, { "path": "en\/rmg\/data-1.html", "name": "Main data", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-001", "description": "List of data items that are open to the public.", "files": [ { "file_name": "rmg_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_main.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_main#en", "data_acquisition": "", "analysis": "", "data_number": "7 entries", "details": [ { "name": "Title", "description": "Title of the data" }, { "name": "Sequence data file", "description": "File name of the sequence data" }, { "name": "Data file (CSV)", "description": "File name of CSV formatted data" }, { "name": "Data file (TogoDB)", "description": "Name of the dataset on Simple search website (TogoDB)" }, { "name": "Image file", "description": "File name of the image" } ] }, { "path": "en\/rmg\/data-2.html", "name": "Entire Sequence", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-002", "description": "The data for entire sequence of rice mitochondrial genome with a total length of 490,520bp. This sequence was registered in the International Nucleotide Sequence Database with accession numbers AB076665 and AB076666, and was later combined into a single accession number BA000029. It was also registered in the previous RAP-DB genome browser.", "files": [ { "file_name": "rmg_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_seq.zip", "file_size": "142 KB" } ], "togodb_url": "", "data_acquisition": "Mitochondrial DNA was prepared as described by Kadowaki et al. (1996), and sequencing of plasmid clones from SauAI or TspEI shotgun libraries was performed using the dideoxy method.", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/rmg\/data-3.html", "name": "Genes (including RNA editing information)", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-003", "description": "List of genes in the rice mitochondrial genome including information on ORF (open reading frames), transcription and RNA editing.", "files": [ { "file_name": "rmg_gene.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_gene.zip", "file_size": "3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_gene#en", "data_acquisition": "\"Entire Sequence\" data in this database", "analysis": "Gene prediction using the tRNAscan-SE, and BLASTN, BLASTX homology search were performed against publicly available DNA databases. The REPuter program was used in the analysis of repetitive sequences.", "data_number": "81 entries", "details": [ { "name": "Gene", "description": "Gene.\r\nGene names ccmC, ccmFn, ccmFc and ccmB were proposed by Faivre-Nitschke et al. (2001)." }, { "name": "Comment", "description": "Comment" }, { "name": "Transcription", "description": "Transcription\r\nnt: not tested\r\nT: transcribed\r\nN: not transcribed" }, { "name": "Editing site", "description": "Editing site\r\nN: not transcribed" }, { "name": "Previous reports on editing sites", "description": "Previous reports on editing sites" }, { "name": "Strand", "description": "Strand\r\nS: sense\r\nA: antisense" }, { "name": "exon1 start", "description": "Start position of exon1" }, { "name": "exon1 end", "description": "End position of exon1" }, { "name": "exon2 start", "description": "Start position of exon2" }, { "name": "exon2 end", "description": "End position of exon2" }, { "name": "exon3 start", "description": "Start position of exon3" }, { "name": "exon3 end", "description": "End position of exon3" }, { "name": "exon4 start", "description": "Start position of exon4" }, { "name": "exon4 end", "description": "End position of exon4" }, { "name": "exon5 start", "description": "Start position of exon5" }, { "name": "exon5 end", "description": "End position of exon5" } ] }, { "path": "en\/rmg\/data-4.html", "name": "Plastid-like Seq in mt Genome", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-004", "description": "List of characteristic features of DNA fragments that were migrated from the plastid genome to the mitochondrial genome. Information on sizes, positions, gene names, homologies and differences for individual fragments is available.", "files": [ { "file_name": "rmg_plastid_like_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_plastid_like_seq.zip", "file_size": "2 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_plastid_like_seq#en", "data_acquisition": "\"Entire Sequence\" data in this database", "analysis": "", "data_number": "18 entries", "details": [ { "name": "Fragment no.", "description": "Fragment number" }, { "name": "Position in mtDNA", "description": "Position in the mitochondrial DNA sequence" }, { "name": "Fragment size(nt)", "description": "Size of the fragment" }, { "name": "Position in ptDNA", "description": "Position in the plastid DNA sequence\r\n(The position is based on Hiratsuka et al. (1989))" }, { "name": "Genes", "description": "Genes" }, { "name": "Substitution", "description": "Number of substitutions in the plastid DNA sequence" }, { "name": "Deletion", "description": "Number of nucleotide deletions in the plastid DNA sequence\r\n(Number of deletion sites is shown in parentheses)" }, { "name": "Insertion", "description": "Number of nucleotide insertions in the plastid DNA sequence\r\n(Number of insertion sites is shown in parentheses)" }, { "name": "Homology(%)", "description": "Percentage homology to the rice plastid DNA sequence" } ] }, { "path": "en\/rmg\/data-5.html", "name": "Nuclear-like Seq in mt Genome", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-005", "description": "List of sequence fragments in rice mitochondrial genome that showed similarity to nuclear retrotransposon and transposon sequences.", "files": [ { "file_name": "rmg_nuclear_like_seq.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_nuclear_like_seq.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_nuclear_like_seq#en", "data_acquisition": "\"Entire Sequence\" data in this database", "analysis": "Homology searches using BLASTX", "data_number": "19 entries", "details": [ { "name": "nuc. position", "description": "Position of the sequence fragment in the rice mitochondrial genome" }, { "name": "length", "description": "Length of the sequence fragment" }, { "name": "sense or antisense", "description": "Sense or antisense strand\r\n+: sense\r\n-: antisense" }, { "name": "organism", "description": "Source of the most closely related transposon\/retrotransposon sequence" }, { "name": "kind of element", "description": "Transposon or retrotransposon\r\nR: retrotransposon\r\nT: transposon" }, { "name": "accession", "description": "GenBank Accession number of the most closely related transposon\/retrotransposon sequence" }, { "name": "%", "description": "Percentage homology to the most closely related transposon\/retrotransposon sequence" }, { "name": "definition", "description": "Characteristics of the most closely related transposon\/retrotransposon sequence" } ] }, { "path": "en\/rmg\/data-6.html", "name": "tRNA", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-006", "description": "Data contents are as follows:\r\n\r\nAmino acid sequences of 23 tRNA from 17 species identified in the rice mitochondrial genome.\r\nList of genes in rice, Arabidopsis and sugar beet mitochondrial genomes and their existence in mitochondrial genomes of other plants.", "files": [ { "file_name": "rmg_trna.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_trna.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_trna#en", "data_acquisition": "\"Entire Sequence\" data in this database", "analysis": "", "data_number": "21 entries", "details": [ { "name": "Amino acids", "description": "Amino acid binding to tRNA" }, { "name": "tRNA", "description": "tRNA gene indicated by the cognate amino acid in one-letter code" }, { "name": "rice", "description": "Rice\r\n+: tRNA present\r\n-: tRNA absent\r\ny: pseudogene\r\na: mitochondrial tRNA\r\nb: plastid-like tRNA\r\nMiyata et al. (1998) was used as reference for rice trnP and trnR pseudogenes." }, { "name": "Arabidopsis", "description": "Arabidopsis\r\n+: tRNA present\r\n-: tRNA absent\r\ny: pseudogene\r\na: mitochondrial tRNA\r\nb: plastid-like tRNA\r\nReference: Unseld et al. (1997)" }, { "name": "sugarbeet", "description": "Sugar beet\r\n+: tRNA present\r\n-: tRNA absent\r\ny: pseudogene\r\na: mitochondrial tRNA\r\nb: plastid-like tRNA\r\nc: novel tRNA\r\nReference: Kubo et al. (2000b)" } ] }, { "path": "en\/rmg\/data-7.html", "name": "Genomic Dynamism", "database_name": "RMG", "doi": "10.18908\/lsdba.nbdc00193-007", "description": "List of sequences commonly found in mitochondria, plastid and nucleus of rice.\r\nThe list represents mitochondrial and nuclear sequences with homology and mutations to the plastid sequences.\r\nFrom these results, the movement of plastid sequence fragments into the mitochondria and nucleus can be clarified.", "files": [ { "file_name": "rmg_genomic_dynamism.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmg\/LATEST\/rmg_genomic_dynamism.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmg_genomic_dynamism#en", "data_acquisition": "", "analysis": "", "data_number": "6 entries", "details": [ { "name": "plastid sequence No.", "description": "Plastid sequence number" }, { "name": "Genes", "description": "Genes on the plastid sequence" }, { "name": "Length", "description": "Length of the plastid sequence" }, { "name": "Mutations of comparison with nuclear sequence", "description": "Comparison with the most closely related nuclear sequence\r\nsub: substitutions\r\ndel: deletions\r\nins: insertions\r\nThe total number of nucleotide alterations in the fragment is shown in parentheses" }, { "name": "Homology", "description": "Percentage homology to the most closely related nuclear sequence" }, { "name": "Mutations of comparison with mt sequence", "description": "Comparison with the most closely related mitochondrial sequence\r\nsub: substitutions\r\ndel: deletions\r\nins: insertions\r\nThe total number of nucleotide alterations in the fragment is shown in parentheses" }, { "name": "Homology", "description": "Percentage homology to the most closely related mitochondrial sequence" } ] }, { "path": "en\/rmos\/data-1.html", "name": "RMOS Contents", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-001", "description": "Static files of all RMOS site.\r\n - General Information\r\n - Application Guide Microarray System\r\n - Microarray Center Protocol\r\n - Microarray \/ Clone List\r\n - Search\r\n - Data Results\r\n - Publications", "files": [ { "file_name": "rmos_contents.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_contents.zip", "file_size": "22.2 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "1 entry", "details": [] }, { "path": "en\/rmos\/data-2.html", "name": "Array patterns and clones", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-002", "description": "Static files of array patterns and cDNA clones.", "files": [ { "file_name": "rmos_array1265_clone_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_array1265_clone_list.zip", "file_size": "27.3 KB" }, { "file_name": "rmos_f_array8987_clone_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_f_array8987_clone_list.zip", "file_size": "321 KB" }, { "file_name": "rmos_g_array8987_clone_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_g_array8987_clone_list.zip", "file_size": "827 KB" } ], "togodb_url": "", "data_acquisition": "- Rice1265\r\nIndependent rice cDNA clones of 1265 ESTs were collected randomly. All of clones were generated by large scale cDNA analysis in RGP (rice genome research program).\r\n \r\n- Rice8987 f_array\r\nOur microarray with rice cDNA comprises a pair of glass slides. The microarray patterns are shown in the figure. On the pair of rice microarrays, there are independent 8979 cDNA clones that were selected from about 40,000 cDNA clones isolated in the first research stage of the rice genome research project. Field 12 is for pig ESTs as positive controls that do not.\r\n \r\n- Rice8987 g_array\r\nFor all microarray experiments on and after July 1, 2002, second version of our rice microarray (called “g_array”) is used. The “g_array” carries the same 8987 cDNAs (with the full inserts) that the Rice8987 Array carries. However the location of each cDNA clone on “g_array” is different from that on the Rice8987 Array.", "analysis": "We fabricated a full insert cDNA microarray and a 3’UTR cDNA microarray. cDNA were applied as duplicate spots on the same glass slide. Blanks in the table (no name) mean that the clones with blank are not registered in DDBJ yet.", "data_number": "3 entries", "details": [] }, { "path": "en\/rmos\/data-4.html", "name": "Rice1265 Array: PCR check", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-004", "description": "List of the PCR check results about clones used in Rice1265 Microarray (Full insert version) \/ (3'UTR version)", "files": [ { "file_name": "rmos_1265pcrcheck.csv.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_1265pcrcheck.csv.zip", "file_size": "11.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmos_1265pcrcheck#en", "data_acquisition": "Independent rice cDNA clones of 1265 ESTs were collected randomly from clones generated by large scale cDNA analysis in RGP (rice genome research program). To check the clone uniqueness, PCR and gel-electrophoresis were applied.", "analysis": "Upper and Lower primer (refer to the Rice8987 Corresponding Table(f_g_primer)) were used for the 3' UTR check, and M13 RV primer and M4 primer (TAKARA) were used for the full-insert check.", "data_number": "1,269 entries", "details": [ { "name": "Element No. (Glass)", "description": "Element No. (Spotted Position on the Glass: refer to the 'Array patterns and clones')" }, { "name": "Clone id", "description": "Clone ID" }, { "name": "96 Plate", "description": "Identification number of the 96 Plate used for PCR check of the clone" }, { "name": "Position", "description": "Position in the 96 plate used for PCR check of the clone" }, { "name": "PCR products check (3'UTR)", "description": "PCR products check (3'UTR): \"blank\"; result match to the prediction, \"no\"; no band, \"m\"; multiband." }, { "name": "PCR products check (Full inserts)", "description": "PCR products check (Full inserts): \"blank\"; result match to the prediction, \"no\"; no band, \"m\"; multiband." }, { "name": "Accession id 1", "description": "DDBJ accession number 1" }, { "name": "Accession id 2", "description": "DDBJ accession number 2" } ] }, { "path": "en\/rmos\/data-5.html", "name": "Rice8987 Array: PCR check", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-005", "description": "List of the PCR check results about clones used in Rice8987 Microarray (f_array\/Full insert version)", "files": [ { "file_name": "rmos_8987pcrcheck.csv.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_8987pcrcheck.csv.zip", "file_size": "96.3 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmos_8987pcrcheck#en", "data_acquisition": "There are independent 8979 cDNA clones that were selected from about 40,000 cDNA clones isolated in the first research stage of the rice genome research project. Those 8979 cDNA clones were used for PCR, and checked the unqueness by gel electrophoresis.", "analysis": "Upper and Lower primer (refer to the Rice8987 Corresponding Table(f_g_primer)) were used for the 3' UTR check, and M13 RV primer and M4 primer (TAKARA) were used for the full-insert check .", "data_number": "9,216 entries", "details": [ { "name": "Element No. (Glass)", "description": "Element No. (Spotted Position on the Glass: refer to the 'Array patterns and clones')" }, { "name": "Clone name", "description": "Clone name" }, { "name": "Dplate", "description": "Destination Plate name, which used for PCR check of the clone" }, { "name": "Dplate Pos.", "description": "Position on the Destination Plate used for PCR check of the clone" }, { "name": "PCR products check (Full inserts)", "description": "PCR products check (Full inserts): \"blank\"; result match to the prediction, \"no\"; no band, \"m\"; multiband." }, { "name": "Accession (5')", "description": "DDBJ accession number (5')" }, { "name": "Accession (3')", "description": "DDBJ accession number (3')" } ] }, { "path": "en\/rmos\/data-6.html", "name": "Rice8987 Array: Gel images", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-006", "description": "Images of Gel Electrophoresis of 8979 cDNA clones used in Rice8987 Array (f_array\/Full insert version).", "files": [ { "file_name": "rmos_eidou_pict.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_eidou_pict.zip", "file_size": "1.25 MB" } ], "togodb_url": "", "data_acquisition": "The independent 8979 cDNA clones were selected from about 40,000 cDNA clones isolated in the first research stage of the rice genome research project.", "analysis": "To check the results of PCR reaction, gel electrophoresis was used. In the PCR reaction, M13 RV primer and M4 primer (TAKARA) were used.\r\nAgalose gel electrophoresis was carried out using 1.0% Agalose ME. Electrophoresis was run at 100V of constant voltage for 2 h. Molecular Rulers, EZ Load 100bp PCR (made by BioRad), was used to Dplate 33,34,41,42,43. Molecular Rulers, Maker2 (made by Wako), was used to other Dplate.\r\nGel images were scanned by scanner (Molecular Dynamics Co.).", "data_number": "94 entries", "details": [] }, { "path": "en\/rmos\/data-7.html", "name": "Rice8987 g_array: cDNA information", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-007", "description": "cDNA information of Rice8987 Array (Rice9000 g_array\/Full insert version).\r\n* For all microarray experiments on and after July 1, 2002, second version of our rice microarray (called “g_array”) is used. The “g_array” carries the same 8987 cDNAs (with the full inserts) that the Rice8987 Array carries. However the location of each cDNA clone on “g_array” is different from that on the Rice8987 Array.", "files": [ { "file_name": "rmos_rice9000array_g.csv.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_rice9000array_g.csv.zip", "file_size": "453 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmos_rice9000array_g#en", "data_acquisition": "The cDNA information, which used for Rice8987 Array (g_array), was marshalled.", "analysis": "This cDNA information is used for software “Array Gauge” (Fujifilm) to quantitatively analyze the image data.", "data_number": "9,216 entries", "details": [ { "name": "Element No. (Glass)", "description": "Element No. (Spotted Position on the Glass: refer to the 'Array patterns and clones')" }, { "name": "Spot No.", "description": "Spot No." }, { "name": "Clone name", "description": "Clone name" }, { "name": "Putative Gene Identification", "description": "Putative Gene Identification" }, { "name": "Destination Plate (96)", "description": "Destination Plate number, which used for PCR check of the clone" }, { "name": "Dplate Pos.", "description": "Position on the Destination Plate used for PCR check of the clone" }, { "name": "Source Plate Name", "description": "Source Plate Name\r\n*No available data" }, { "name": "Clone Pos. in STAFFDWP", "description": "Clone Pos. in STAFFDWP (STAFF Deep Well Plate)\r\n*No available data" }, { "name": "Accession No. (A)", "description": "DDBJ accession number, which clone neme include A" }, { "name": "Accession No. (Z)", "description": "DDBJ accession number, which clone neme include Z" }, { "name": "Primer No.", "description": "Primer number\r\n*No available data" }, { "name": "to Full Spot No.", "description": "to Full Spot number\r\n*No available data" }, { "name": "384Plate", "description": "Identification number of 384Plate used for spotting cDNA on the Glass" }, { "name": "384Plate Pos.", "description": "Position on the 384Plate" } ] }, { "path": "en\/rmos\/data-8.html", "name": "8987Array-Chromosome", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-008", "description": "Position information of the clone of Rice8987 Array (f_array) on chromosomes", "files": [ { "file_name": "rmos_8987array_chromosome.csv.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_8987array_chromosome.csv.zip", "file_size": "96.5 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmos_8987array_chromosome#en", "data_acquisition": "", "analysis": "", "data_number": "9,105 entries", "details": [ { "name": "f_array_element", "description": "f_array element number (spotted position on the glass: refer to the 'Array patterns and clones')" }, { "name": "Accession1", "description": "DDBJ accession number 1" }, { "name": "Accession2", "description": "DDBJ accession number 2" }, { "name": "Clone name", "description": "Clone name" }, { "name": "DDBJ name", "description": "Name in the definition of DDBJ" }, { "name": "Multi", "description": "Similarity between sequences of cDNA clones and those of rice genome.\r\n(high to low ; A, B, C….)" }, { "name": "Mapping", "description": "D : Sequence of the clone was directly used for mapping.\r\nG : Sequence of the representative clone in the group consisting of clones with similar sequences was used for mapping." }, { "name": "Chr.", "description": "Chromosome number" }, { "name": "Clone name (group)", "description": "Representative clone name in the group" }, { "name": "Multi (group)", "description": "Similarity between sequences of the representative clone and rice genome in the group.\r\n(high to low ; A, B, C….)" }, { "name": "Chr. (group)", "description": "Chromosome number of the genome sequence similar to that of the representative clone in the group" } ] }, { "path": "en\/rmos\/data-9.html", "name": "Rice8987Corresponding Table(f_g_primer)", "database_name": "RMOS", "doi": "10.18908\/lsdba.nbdc00194-009", "description": "List of primer information of Rice8987Array (f_g_primer).", "files": [ { "file_name": "rmos_f_g_primer_table.csv.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rmos\/LATEST\/rmos_f_g_primer_table.csv.zip", "file_size": "636 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rmos_f_g_primer_table#en", "data_acquisition": "", "analysis": "", "data_number": "8,987 entries", "details": [ { "name": "g_Element No.", "description": "g_Element number on the Rice8987 g_array, which indicates the spotting position on the glass" }, { "name": "f_Element No.", "description": "f_Element number on the Rice8987 f_array, which indicates the spotting position on the glass" }, { "name": "3UTR Element No.", "description": "3UTR Element number on the Rice8987 Array (3'UTR version), which indicates the spotting position on the glass" }, { "name": "Clone name", "description": "Clone name" }, { "name": "Accession 01", "description": "DDBJ accession number 01" }, { "name": "Accession 02", "description": "DDBJ accession number 02" }, { "name": "Putative Identification", "description": "Putative Gene Identification" }, { "name": "Destination Plate (96)", "description": "Destination Plate number, which used for PCR check of the clone" }, { "name": "Dplate Pos.", "description": "Position on the Destination Plate used for PCR check of the clone" }, { "name": "Full insert M \/no check", "description": "PCR products check (Full inserts) using the M13 RV primer and the M4 primer (TAKARA) : \"blank\"; result match to the prediction, \"no\"; no band, \"m\"; multiband." }, { "name": "Mapped 3'UTR Primer seq (Upper)", "description": "Mapped 3'UTR Primer sequence (Upper)" }, { "name": "Mapped 3'UTR Primer seq (Lower)", "description": "Mapped 3'UTR Primer sequence (Lower)" }, { "name": "Unmapped 3'UTR Primer seq (Upper)", "description": "Unmapped 3'UTR Primer sequence (Upper)" }, { "name": "Unmapped 3'UTR Primer seq (Lower)", "description": "Unmapped 3'UTR Primer sequence (Lower)" } ] }, { "path": "en\/rpd\/data-1.html", "name": "Gel table", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-001", "description": "List of gel image of 2D-PAGE for various organ or organelle in rice.", "files": [ { "file_name": "rpd_main.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_main.zip", "file_size": "1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rpd_main#en", "data_acquisition": "experiment", "analysis": "Proteins were extracted from organs or organelle of rice at various growing stages. The proteins were subjected to 2D-PAGE.", "data_number": "30 entries", "details": [ { "name": "Tissue ID", "description": "ID of the 2D-PAGE image." }, { "name": "Tissue type", "description": "Type of organ column.\r\n\"tissue\": growing stage or kind of organ.\r\n\"organelle\": kind of organelle." }, { "name": "Tissue", "description": "Kind of organ or organelle." }, { "name": "Gel image", "description": "File name of gel image." }, { "name": "Spot No gel image", "description": "File name of gel image with spot No." } ] }, { "path": "en\/rpd\/data-2.html", "name": "Spot table", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-002", "description": "List of the spots obtained by 2D-PAGE. The information for each spot such as Mw, pI, expression level, the amino acid sequence, and the result of homology search is provided.", "files": [ { "file_name": "rpd_spot.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_spot.zip", "file_size": "326 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rpd_spot#en", "data_acquisition": "experiment", "analysis": "Based on 23 reference maps of 2D-PAGE, each of the proteins was purified and sequenced by gas-phase protein sequencer or mass spectrometry. For amino acid sequence by gas-phase protein sequencer, the result of homology search was obtained by BLAST. For sequence by MS, it was obtained by Mascot analysis.", "data_number": "14,724 entries", "details": [ { "name": "Spot ID", "description": "ID of the spot." }, { "name": "Spot No.", "description": "Serial number of this spot on the gel." }, { "name": "tissue ID", "description": "ID of the 2D-PAGE image." }, { "name": "pI", "description": "pI (isoelectric point) of protein on this spot." }, { "name": "MW", "description": "MW (molecular weight) of protein on this spot." }, { "name": "organism", "description": "Plant material that user for protein extraction." }, { "name": "tissue", "description": "Tissue or organella for extracting tissue material." }, { "name": "expression", "description": "Expression of protein analysed by 2D ELITE (image analysis software of two-dimensional polyacrylamide gel electrophoresis, Amersham)." }, { "name": "spot gel image", "description": "Extended gel image of the spot." }, { "name": "Mass Spectrometry Accession No.", "description": "Accession No. of homologous protein by Mascot Analysis." }, { "name": "Mass Spectrometry Homologous Protein", "description": "Definition of homologous protein by Mascot Analysis." }, { "name": "Mass Spectrometry Score (%)", "description": "Mascot score." }, { "name": "Protein Sequencer Accession No.", "description": "Accession No. of homologous protein by protein sequencer. (multiple entries)" }, { "name": "Protein Sequencer Homologous Protein", "description": "Definition of homologous protein by Mascot Analysis. (multiple entries)" }, { "name": "cDNA Accession No.", "description": "Accession No. of homologous cDNA. (multiple entries)" } ] }, { "path": "en\/rpd\/data-3.html", "name": "Sequencer table", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-003", "description": "List of result of BLAST search for the amino acid sequence determined by gas-phase protein sequencer.", "files": [ { "file_name": "rpd_sequencer.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_sequencer.zip", "file_size": "23 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rpd_sequencer#en", "data_acquisition": "", "analysis": "Using the amino acid sequence determined by gas-phase protein sequencer as query, BLAST search was performed to NR database restricted to Oryza sativa. This result was obtained by using NR database at Oct. 2013.", "data_number": "3,376 entries", "details": [ { "name": "Spot ID", "description": "ID of the spot." }, { "name": "Amino sequence", "description": "Amino acid sequence of this spot analysed by protein sequencer." }, { "name": "Homologous Protein Accession No.", "description": "Accession No. of homologous protein." }, { "name": "Homologous Protein definition", "description": "Definition of homologous protein." }, { "name": "Homologous search identities (%)", "description": "Identifies percentage of homologous search." } ] }, { "path": "en\/rpd\/data-4.html", "name": "cDNA table", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-004", "description": "Results of homology search to cDNA clones in the KOME.", "files": [ { "file_name": "rpd_cdna.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_cdna.zip", "file_size": "15 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rpd_cdna#en", "data_acquisition": "", "analysis": "", "data_number": "1,258 entries", "details": [ { "name": "Spot ID", "description": "ID of the spot." }, { "name": "Accession NO", "description": "Accession No. of homologous cDNA." }, { "name": "Clone name", "description": "Clone name of homologous cDNA." }, { "name": "Score", "description": "Score" }, { "name": "Coverage", "description": "Coverage" } ] }, { "path": "en\/rpd\/data-5.html", "name": "Image files", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-005", "description": "Gel images and associated image files.", "files": [ { "file_name": "rpd_gel_image.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_gel_image.zip", "file_size": "38.5 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "Gel image: 23 entries\r\nGel image with spot No.: 23 entries\r\nImage of vertical and horizontal axes: 2 entries\r\nExtended gel image of each spot : 12,807 entries\r\n\"no_image.jpeg\": 1 entry", "details": [] }, { "path": "en\/rpd\/data-6.html", "name": "Protocol", "database_name": "RPD", "doi": "10.18908\/lsdba.nbdc00191-006", "description": "Protocols for various methods of proteomics.", "files": [ { "file_name": "rpd_protocol_jp.zip (Japanese version)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_protocol_jp.zip", "file_size": "535 KB" }, { "file_name": "rpd_protocol_en.zip (English version)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpd\/LATEST\/rpd_protocol_en.zip", "file_size": "329 KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "We cut out protocols for methods of proteomics from the web description page, added index.html, and we compressed into a zip file.", "data_number": "", "details": [] }, { "path": "en\/rpsd\/data-1.html", "name": "Main", "database_name": "RPSD", "doi": "10.18908\/lsdba.nbdc00749-001", "description": "List of information about the three-dimensional structures of the proteins of plant seven kinds, such as rice.", "files": [ { "file_name": "rpsd_main_sjis.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpsd\/LATEST\/rpsd_main_sjis.zip", "file_size": "120 KB" }, { "file_name": "rpsd_main_utf8.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpsd\/LATEST\/rpsd_main_utf8.zip", "file_size": "120 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/rpsd_main#en", "data_acquisition": "Protein Data Bank", "analysis": "", "data_number": "358 entries", "details": [ { "name": "PDB ID", "description": "PDB ID of the protein" }, { "name": "Japanese name", "description": "Japanese name of the organism species" }, { "name": "English name", "description": "English name of the organism species" }, { "name": "Scientific name", "description": "Scientific name of the organism species" }, { "name": "Protein name", "description": "Name of the protein" }, { "name": "Gene name", "description": "Gene name of the protein" }, { "name": "Source\/Organism", "description": "Organism species of the protein" }, { "name": "Compound", "description": "Compound of the protein" }, { "name": "Classification", "description": "Category of the protein" }, { "name": "EC number", "description": "Enzyme Commission number of the protein" }, { "name": "Authors", "description": "Authors of the reference" }, { "name": "Reference", "description": "Reference has published the structure of the protein" }, { "name": "Key word", "description": "Keyword of the function of the protein" }, { "name": "Cross reference", "description": "Cross-reference with other databases" }, { "name": "Experimental method", "description": "Experimental method for the protein structure determination" }, { "name": "Sequence characteristics", "description": "Characteristics of the amino acid sequence" }, { "name": "Sequence", "description": "Amino acid sequence of the protein" }, { "name": "Image", "description": "Image file name of the three-dimensional structure of the protein" } ] }, { "path": "en\/rpsd\/data-2.html", "name": "Images", "database_name": "RPSD", "doi": "10.18908\/lsdba.nbdc00749-002", "description": "Images of the three-dimensional structures of the proteins of plant seven kinds, such as rice.", "files": [ { "file_name": "rpsd_images.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/rpsd\/LATEST\/rpsd_images.zip", "file_size": "18.3 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "358 entries", "details": [] }, { "path": "en\/sahg\/data-1.html", "name": "Protein Basic Information", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-001", "description": "Basic information of the target protein. Amino acid sequence, RefSeq ID, etc.", "files": [ { "file_name": "sahg_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/sahg_protein.zip", "file_size": "8.1 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/sahg_protein#en", "data_acquisition": "Retrieved from RefSeq (NCBI Reference Sequence Database). Protein sequence search on EzCatDB (A Database of Enzyme Catalytic Mechanisms), Human Protein Reference Database (HPRD), UniProtKB\/Swiss-Prot.", "analysis": "", "data_number": "24,878 entries", "details": [ { "name": "RefSeqID", "description": "RefSeq ID" }, { "name": "domainSize", "description": "Number of linked Domain Modeling" }, { "name": "Link to Domain", "description": "(only in SimpleSearch pages) link to Domain Modeling of the same RefSeqID" }, { "name": "Link to Complex", "description": "(only in SimpleSearch pages) link to Complex Modeling of the same RefSeqID" }, { "name": "GeneID", "description": "Entrez Gene ID of the gene coding the protein" }, { "name": "Definition", "description": "Protein name in RefSeq database" }, { "name": "chromosome", "description": "Chromosome number of the gene" }, { "name": "Location", "description": "Locus of the gene" }, { "name": "Sequence", "description": "Amino acid sequence" }, { "name": "EC number", "description": "Enzyme Commission numbers" }, { "name": "EzCatDB", "description": "EzCatDB (A Database of Enzyme Catalytic Mechanisms) ID" }, { "name": "HPRD", "description": "Human Protein Reference Database (HPRD) ID" }, { "name": "Swiss-Prot", "description": "(only in SimpleSearch pages) link to UniProtKB\/Swiss-Prot" } ] }, { "path": "en\/sahg\/data-2.html", "name": "Domain Modeling", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-002", "description": "Predicted structure of the domain, information of the templates, predicted interactions.", "files": [ { "file_name": "sahg_domain.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/sahg_domain.zip", "file_size": "3.4 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/sahg_domain#en", "data_acquisition": "3D structures, protein-ligand interaction, and protein-protein interaction were predicted based on the amino acid sequece by our prediction pipeline (Motono et al., Nucleic Acids Research, 2011, 39, D487-D493).", "analysis": "", "data_number": "42,581 entries", "details": [ { "name": "RefSeqID", "description": "RefSeq ID" }, { "name": "Link to Protein", "description": "(only in SimpleSearch pages) link to Protein Basic Information of the same RefSeqID" }, { "name": "chromosome", "description": "Chromosome number of the gene" }, { "name": "domainIdx", "description": "Domain index (sequential) for a protein" }, { "name": "apoholoNum", "description": "1: Only apo form was modeled. 2:Only holo form. 3:Both apo and holo forms" }, { "name": "aafrom", "description": "Starting amino acid residue number." }, { "name": "aato", "description": "Ending amino acid residue number." }, { "name": "Domain description", "description": "Function of the domain region (predicted based on the template protein information)." }, { "name": "apo Template", "description": "Template protein in apo form." }, { "name": "apo model PDB", "description": "Link to the predicted structure." }, { "name": "holo Template", "description": "Template protein in holo form." }, { "name": "holo model PDB", "description": "Link to the predicted structure." }, { "name": "Detected by", "description": "Template search methods" }, { "name": "Ligand Binding Residues", "description": "Ligand binding residues" }, { "name": "Interface Residues", "description": "Protein-protein interaction residues" }, { "name": "Catalytic Residues", "description": "Catalytic residues (only for enzymes)" }, { "name": "Ligand", "description": "PDBchemical ID for the predicted ligands" }, { "name": "morphing", "description": "0: No animation data. 1: animation data presented." } ] }, { "path": "en\/sahg\/data-3.html", "name": "Complex Modeling", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-003", "description": "Protein-protein copmlex modeling predition", "files": [ { "file_name": "sahg_complex.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/sahg_complex.zip", "file_size": "147 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/sahg_complex#en", "data_acquisition": "If a target sequence was related to a given subunit of a template complex in PQS database with >=80% sequence identity by the BLAST search and all the other subunits were related to any target sequences, the complex model was constructed by MODELLER.", "analysis": "", "data_number": "8,667 entries", "details": [ { "name": "RefSeqID", "description": "RefSeq ID" }, { "name": "Link to Protein", "description": "(only in SimpleSearch pages) link to Protein Basic Information of the same RefSeqID" }, { "name": "regionFrom", "description": "Starting amino acid residue number." }, { "name": "regionTo", "description": "Ending amino acid residue number." }, { "name": "model PDB", "description": "(only in SimpleSearch pages) link to model structure (PDB)" }, { "name": "Oligomer", "description": "homo oligomer \/ hetero oligomer" }, { "name": "Model", "description": "Model index (sequential) for a protein" }, { "name": "Template", "description": "Template for the complex modeling" }, { "name": "Partner ID", "description": "RefSeq ID of the counterpart protein in the complex." } ] }, { "path": "en\/sahg\/data-4.html", "name": "Alignment", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-004", "description": "Alignment between target and template sequences", "files": [ { "file_name": "sahg_alignment.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/sahg_alignment.zip", "file_size": "12.0 MB" } ], "togodb_url": "", "data_acquisition": "3D structures was predicted based on the amino acid sequece by our prediction pipeline (Motono et al., Nucleic Acids Research, 2011, 39, D487-D493).", "analysis": "", "data_number": "46,664 entries", "details": [ { "name": "RefSeqID", "description": "RefSeq ID" }, { "name": "Domain_type", "description": "Type of domain structure (apo or holo)" }, { "name": "Template", "description": "Template protein name" }, { "name": "Query_from", "description": "Starting amino acid residue number of the aligned region of the target protein." }, { "name": "Query_to", "description": "Ending amino acid residue number of the aligned region of the target protein." }, { "name": "Query_alignment", "description": "Alignment sequence (query)" }, { "name": "Template_from", "description": "Starting amino acid residue number of the aligned region of the template protein." }, { "name": "Template_to", "description": "Ending amino acid residue number of the aligned region of the template protein." }, { "name": "Template_alignment", "description": "Alignment sequence (template)" }, { "name": "Alignment_line", "description": "Line of alignment" }, { "name": "Identity(%)", "description": "Sequence identity" } ] }, { "path": "en\/sahg\/data-5.html", "name": "Model Structure Thumbnail", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-005", "description": "Still\/animated images of the predicted protein domain sturctures.", "files": [ { "file_name": "model_structure_thumbnail.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/model_structure_thumbnail.zip", "file_size": "404 MB" } ], "togodb_url": "", "data_acquisition": "The predicted domain structres in PDB format were visualized by a software. When models of both apo and holo forms are available (green block on the bar), their structural changes upon ligand-binding are visualized by the morphing technique (the MORPH2).", "analysis": "", "data_number": "42,581 entries", "details": [] }, { "path": "en\/sahg\/data-6.html", "name": "Domain Model Structure", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-006", "description": "Predicted protein structure (PDB format).", "files": [ { "file_name": "domain_model_structure.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/domain_model_structure.zip", "file_size": "1.6 GB" } ], "togodb_url": "", "data_acquisition": "3D structures, protein-ligand interaction, and protein-protein interaction were predicted based on the amino acid sequece by our prediction pipeline (Motono et al., Nucleic Acids Research, 2011, 39, D487-D493).", "analysis": "", "data_number": "46,269 entries", "details": [] }, { "path": "en\/sahg\/data-7.html", "name": "Complex Model Structure", "database_name": "SAHG", "doi": "10.18908\/lsdba.nbdc01193-007", "description": "Predicted protein compex structure (PDB format).", "files": [ { "file_name": "complex_model_structure.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/sahg\/LATEST\/complex_model_structure.zip", "file_size": "1.1 GB" } ], "togodb_url": "", "data_acquisition": "If a target sequence was related to a given subunit of a template complex in PQS database with >=80% sequence identity by the BLAST search and all the other subunits were related to any target sequences, the complex model was constructed by MODELLER.", "analysis": "", "data_number": "8,667 entries", "details": [] }, { "path": "en\/kaiko\/data-1.html", "name": "Metadata of reference transcriptomic data", "database_name": "Silkworm, Bombyx mori, reference transcriptome data", "doi": "10.18908\/lsdba.nbdc02443-001", "description": "Metadata of Bombyx mori reference transcriptomic data is described in GFT2 file format.\r\nAbout GFT2 format, see the following site:\r\nhttp:\/\/mblab.wustl.edu\/GTF22.html", "files": [ { "file_name": "kaiko_transcript_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko\/LATEST\/kaiko_transcript_data.zip", "file_size": "3.9 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_transcript_data#en", "data_acquisition": "Tissues of silk gland, fat body, midgut, Malpighian tubules, testis and ovary were dissected on the 3rd day of fifth instar larva which is Silkworm P50T (daizo) strain. The silk gland was further subdivided into anterior silk gland, anterior part of the middle silk gland, middle part of the middle silk gland, posterior part of the middle silk gland and posterior silk gland . Each tissue was dissected from one individual and totally three biological replicates were obtained and analyzed separately. The tissues were homogenized using ISOGEN (NIPPON GENE, Tokyo, Japan) and SV Total RNA Isolation System (Promega, Madison, WI) was used for RNA extraction.　The extract total RNA samples were sequenced by Illumina Novaseq6000 (Macrogen Japan Corp., Kyoto, Japan) .", "analysis": "The raw RNA-seq data of the samples were trimmed by Trimmomatic-version 0.36. The trimmed RNA-seq data of each tissue was mapping to the new reference genome with new gene model by Hisat2 version 2.1.0. The each mapped data was assembled to transcript data by stringtie version 1.3.3. The transcript data was merged to one transcript data set we refer as “reference transcriptome” by the stringtie, and gtf file of the reference transcriptome had been gotten.", "data_number": "421,949 entries", "details": [ { "name": "seqname", "description": "Sequence name" }, { "name": "source", "description": "Analysis software" }, { "name": "feature", "description": "Feature of the sequence region" }, { "name": "start", "description": "Start sequence number of the region" }, { "name": "end", "description": "End sequence number of the region" }, { "name": "score", "description": "Confidence score of the region" }, { "name": "strand", "description": "Strand of the region" }, { "name": "frame", "description": "Codon frame of the region" }, { "name": "attributes", "description": "Other attributes" } ] }, { "path": "en\/kaiko\/data-2.html", "name": "Expression data of each transcript in mutiple tissue", "database_name": "Silkworm, Bombyx mori, reference transcriptome data", "doi": "10.18908\/lsdba.nbdc02443-002", "description": "This data file contains values of expressions (tpm value) in multiple tissues of Bombyx mori per each transcript.", "files": [ { "file_name": "kaiko_transcript_tpm_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/kaiko\/LATEST\/kaiko_transcript_tpm_data.zip", "file_size": "5.8 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_transcript_tpm_data#en", "data_acquisition": "Reference transcriptomic data and raw RNAseq data constructed with the method described in \"Metadata of reference transcriptomic data\"\r\nOther RNAseq data was downloaded from Sequence Read Archive(SRA): DRA005094, DRA005878, DRA005094.", "analysis": "Using the above data, estimation of tpm values of each transcript was performed by Kallisto ver0.44.0.", "data_number": "51,926 entries", "details": [ { "name": "ASG1", "description": "Anterior silk gland (biological replicate 1)" }, { "name": "ASG2", "description": "Anterior silk gland (biological replicate 2)" }, { "name": "ASG3", "description": "Anterior silk gland (biological replicate 3)" }, { "name": "MSG_A1", "description": "Anterior part of the middle silk gland (biological replicate 1)" }, { "name": "MSG_A2", "description": "Anterior part of the middle silk gland (biological replicate 2)" }, { "name": "MSG_A3", "description": "Anterior part of the middle silk gland (biological replicate 3)" }, { "name": "MSG_M1", "description": "Middle part of the middle silk gland (biological replicate 1)" }, { "name": "MSG_M2", "description": "Middle part of the middle silk gland (biological replicate 2)" }, { "name": "MSG_M3", "description": "Middle part of the middle silk gland (biological replicate 3)" }, { "name": "MSG_P1", "description": "Posterior part of the middle silk gland (biological replicate 1)" }, { "name": "MSG_P2", "description": "Posterior part of the middle silk gland (biological replicate 2)" }, { "name": "MSG_P3", "description": "Posterior part of the middle silk gland (biological replicate 3)" }, { "name": "PSG1", "description": "Posterior silk gland (biological replicate 1)" }, { "name": "PSG2", "description": "Posterior silk gland (biological replicate 2)" }, { "name": "PSG3", "description": "Posterior silk gland (biological replicate 3)" }, { "name": "MG1", "description": "Midgut (biological replicate 1)" }, { "name": "MG2", "description": "Midgut (biological replicate 2)" }, { "name": "MG3", "description": "Midgut (biological replicate 3)" }, { "name": "FB1", "description": "Fat body (biological replicate 1)" }, { "name": "FB2", "description": "Fat body (biological replicate 2)" }, { "name": "FB3", "description": "Fat body (biological replicate 3)" }, { "name": "MT1", "description": "Malpighian tubules (biological replicate 1)" }, { "name": "MT2", "description": "Malpighian tubules (biological replicate 2)" }, { "name": "MT3", "description": "Malpighian tubules (biological replicate 3)" }, { "name": "TT1", "description": "Testis (biological replicate 1)" }, { "name": "TT2", "description": "Testis (biological replicate 2)" }, { "name": "TT3", "description": "Testis (biological replicate 3)" }, { "name": "OV1", "description": "Ovary (biological replicate 1)" }, { "name": "OV2", "description": "Ovary (biological replicate 2)" }, { "name": "OV3", "description": "Ovary (biological replicate 3)" }, { "name": "BN_FB1", "description": "Fat body from SRA (biological replicate 1)" }, { "name": "BN_FB2", "description": "Fat body from SRA (biological replicate 2)" }, { "name": "BN_FB3", "description": "Fat body from SRA (biological replicate 3)" }, { "name": "BN_MG1", "description": "Midgut from SRA (biological replicate 1)" }, { "name": "BN_MG2", "description": "Midgut from SRA (biological replicate 2)" }, { "name": "BN_MG3", "description": "Midgut from SRA (biological replicate 3)" }, { "name": "BN_MT1", "description": "Malpighian tubules from SRA (biological replicate 1)" }, { "name": "BN_MT2", "description": "Malpighian tubules from SRA (biological replicate 2)" }, { "name": "BN_MT3", "description": "Malpighian tubules from SRA (biological replicate 3)" }, { "name": "BN_SG1", "description": "Silk gland from SRA (biological replicate 1)" }, { "name": "BN_SG2", "description": "Silk gland from SRA (biological replicate 2)" }, { "name": "BN_SG3", "description": "Silk gland from SRA (biological replicate 3)" }, { "name": "BN_TT1", "description": "Testis from SRA (biological replicate 1)" }, { "name": "BN_TT2", "description": "Testis from SRA (biological replicate 2)" }, { "name": "BN_TT3", "description": "Testis from SRA (biological replicate 3)" }, { "name": "target_id", "description": "Unique ID allocated to each transcript in reference transcriptomic data" } ] }, { "path": "en\/kaiko\/data-3.html", "name": "Annotations of each trascript (doing blast against human and Drosophila gene sets)", "database_name": "Silkworm, Bombyx mori, reference transcriptome data", "doi": "10.18908\/lsdba.nbdc02443-003", "description": "Functional annotations of each transcript. These annotations were performed by doing blast against human and Drosophila gene sets.", "files": [ { "file_name": "kaiko_annotation_human_drosophila_data.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/kaiko\/LATEST\/kaiko_annotation_human_drosophila_data.zip", "file_size": "391 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/kaiko_annotation_human_drosophila_data#en", "data_acquisition": "Blast Search of each transcript was done against human (version GRCh38)and Drosophila melanogaster (version BDGP6.22) protein data set in Ensemble database. Top hit gene in the results was converted to symbol description by Biomart.", "analysis": "Blast search", "data_number": "51,926 entries", "details": [ { "name": "human_gname", "description": "Symbol of top hit human gene." }, { "name": "fly_gname", "description": "Symbol of top hit Drosophila gene." }, { "name": "target_id", "description": "Unique ID allocated to each transcript in reference transcriptomic data" } ] }, { "path": "en\/kaiko\/data-4.html", "name": "Predicted amino acid sequences in the reference transcriptomic data", "database_name": "Silkworm, Bombyx mori, reference transcriptome data", "doi": "10.18908\/lsdba.nbdc02443-004", "description": "Multi fasta file of amino acid sequence predicted with Transcoder (v5.5.0) from the reference transcriptomic data.", "files": [ { "file_name": "kaiko_bm_ref_transcript_TSA.zip", "file_url": "https:\/\/biosciencedbc.jp\/archive\/kaiko\/LATEST\/kaiko_bm_ref_transcript_TSA.zip", "file_size": "11 MB" } ], "togodb_url": "", "data_acquisition": "Reference transcriptomic data", "analysis": "Transcoder (v5.5.0)", "data_number": "", "details": [] }, { "path": "en\/skip\/data-1.html", "name": "Stemcell Information", "database_name": "SKIP Stemcell Database", "doi": "10.18908\/lsdba.nbdc01524-001", "description": "Stemcell information from RIKEN BRC, NIBIO, Coriell, ATCC and many laboratories", "files": [ { "file_name": "skip_stemcell_data.ttl.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/skip\/LATEST\/skip_stemcell_data.ttl.zip", "file_size": "190 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/skip_stemcell_data#en", "data_acquisition": "Cited from articles and public databases", "analysis": "", "data_number": "1,064 entries", "details": [ { "name": "SKIP ID", "description": "SKIP ID" }, { "name": "Organism(En)", "description": "Organism of this cell (English)" }, { "name": "Organism(Ja)", "description": "Organism of this cell (Japanese)" }, { "name": "Cell Type(En)", "description": "Cell Type (English)" }, { "name": "Cell Type(Ja)", "description": "Cell Type (Japanese)" }, { "name": "Cell Tissue(En)", "description": "Cell Tissue (English)" }, { "name": "Cell Tissue(Ja)", "description": "Cell Tissue (Japanese)" }, { "name": "Cell Origin", "description": "Status of cell origin" }, { "name": "Cell Name 1(En)", "description": "Cell Name 1 (English)" }, { "name": "Cell Name 1(Ja)", "description": "Cell Name 1 (Japanese)" }, { "name": "Cell Name 2(En)", "description": "Cell Name 2 (English)" }, { "name": "Cell Name 2(Ja)", "description": "Cell Name 2 (Japanese)" }, { "name": "Disease Name 1(Ja)", "description": "Disease Name 1 (Japanese)" }, { "name": "ICD Code 1", "description": "ICD Code 1" }, { "name": "Disease Name 1(En)", "description": "Disease Name 1 (English)" }, { "name": "OMIM1", "description": "OMIM ID 1" }, { "name": "Disease Name 2(Ja)", "description": "Disease Name 2 (Japanese)" }, { "name": "ICD Code 2", "description": "ICD Code 2" }, { "name": "Disease Name 2(En)", "description": "Disease Name 2 (English)" }, { "name": "OMIM 2", "description": "OMIM ID 2" }, { "name": "Disease Name 3(Ja)", "description": "Disease Name 3 (Japanese)" }, { "name": "ICD Code 3", "description": "ICD Code 3" }, { "name": "Disease Name 3(En)", "description": "Disease Name 3 (English)" }, { "name": "OMIM 3", "description": "OMIM ID 3" }, { "name": "Age", "description": "Age of donor" }, { "name": "Age Range", "description": "Age range of donor" }, { "name": "Sex", "description": "Sex of donor" }, { "name": "Race(En)", "description": "Race of donor (English)" }, { "name": "Race(Ja)", "description": "Race of donor (Japanese)" }, { "name": "Genetic Diagnosis", "description": "Genetic Diagnosis or none" }, { "name": "Not Detected", "description": "Not Detected or detected in genetic diagnosis" }, { "name": "Description(En)", "description": "Description of this cell (English)" }, { "name": "Description(Ja)", "description": "Description of this cell (Japanese)" }, { "name": "Cell Morphology", "description": "Cell Morphology" }, { "name": "Grade", "description": "Cell provided by (research or clinic)" }, { "name": "Vector", "description": "Vector to cultivate this cell" }, { "name": "Transgene", "description": "Transgene to this cell" }, { "name": "Adhesiveness", "description": "Cell adhesiveness" }, { "name": "Feeder", "description": "Feeder cell is used or not" }, { "name": "Feeder Cell", "description": "Feeder cell name" }, { "name": "Medium", "description": "Medium to cultivate this cell" }, { "name": "Genome Editing", "description": "Genome Editing method in the cultivation" }, { "name": "CO2", "description": "CO2 concentration in the cultivation" }, { "name": "Mycoplasma", "description": "Detection of Contaminants Mycoplasma or none" }, { "name": "Detection of Contaminants Mycoplasma", "description": "Method of Detection of Contaminants Mycoplasma" }, { "name": "Pluripotent Markers", "description": "Pluripotent Markers Assay or none" }, { "name": "Pluripotent Markers Assay", "description": "Method of Pluripotent Markers Assay" }, { "name": "in vitro Differentiation", "description": "in vitro Differentiation Assay or none" }, { "name": "in vitro Differentiation Assay", "description": "Method of in vitro Differentiation Assay" }, { "name": "in vivo Differentiation", "description": "in vivo Differentiation Assay or none" }, { "name": "in vivo Differentiation Assay", "description": "Method of in vivo Differentiation Assay" }, { "name": "Other 1 Assay", "description": "Other 1 Assay or none" }, { "name": "Other 1 Assay Method", "description": "Method of Other 1 Assay" }, { "name": "Other 2 Assay", "description": "Other 2 Assay or none" }, { "name": "Other 2 Assay Method", "description": "Method of Other 2 Assay" }, { "name": "Other 3 Assay", "description": "Other 3 Assay or none" }, { "name": "Other 3 Assay Method", "description": "Method of Other 3 Assay" }, { "name": "Karyotype", "description": "Karyotype Assay or none" }, { "name": "Karyotype Assay", "description": "Method of Karyotype Assay" }, { "name": "Remaining Vector Detection", "description": "Remaining Vector Detection Assay or none" }, { "name": "Remaining Vector Detection Assay", "description": "Method of Remaining Vector Detection Assay" }, { "name": "STR", "description": "STR analysis or none" }, { "name": "HLA", "description": "HLA typing or none" }, { "name": "Stem Cell Transcriptome analysis", "description": "Stem Cell Transcriptome analysis or none" }, { "name": "Stem Cell Transcriptome analysis Assay", "description": "Stem Cell Transcriptome analysis Assay or none" }, { "name": "Author Name(En)", "description": "Author Name (English)" }, { "name": "Author Name(Ja)", "description": "Author Name (Japanese)" }, { "name": "Author Organization(En)", "description": "Author Organization (English)" }, { "name": "Author Organization(Ja)", "description": "Author Organization (Japanese)" }, { "name": "Author Contact Email", "description": "Author Contact Email" }, { "name": "PI Organization(En)", "description": "Principal Investigator (PI) Organization (English)" }, { "name": "PI Organization(Ja)", "description": "PI Organization (Japanese)" }, { "name": "PI Name(En)", "description": "PI Name (English)" }, { "name": "PI Name(Ja)", "description": "PI Name (Japanese)" }, { "name": "PI Contact Email", "description": "PI Contact Email" }, { "name": "Availability", "description": "Stemcell Availability" }, { "name": "Provider Organization(En)", "description": "Provider Organization (English)" }, { "name": "Provider Organization(Ja)", "description": "Provider Organization (Japanese)" }, { "name": "Provider Email", "description": "Provider Email" }, { "name": "Provider URL", "description": "Provider URL" }, { "name": "Ethical Statement(En)", "description": "Ethical Statement (English)" }, { "name": "Ethical Statement(Ja)", "description": "Ethical Statement (Japanese)" }, { "name": "Terms of Use(En)", "description": "Terms of Use (English)" }, { "name": "Terms of Use(Ja)", "description": "Terms of Use (Japanese)" }, { "name": "PubMed ID", "description": "PubMed ID of article (reference)" }, { "name": "DOI", "description": "DOI (Digital Object Identifier) of article" }, { "name": "Title", "description": "Article Title" }, { "name": "Authors", "description": "Article Authors" }, { "name": "Journal", "description": "Journal which contains the article" }, { "name": "Year", "description": "Publishing Year of the journal" }, { "name": "Volume", "description": "Volume of the journal" }, { "name": "Issue", "description": "Issue of the journal" }, { "name": "Pages", "description": "Pages in the journal" }, { "name": "URL", "description": "Article URL" }, { "name": "Free input", "description": "Others about the article" }, { "name": "Note", "description": "Comment" } ] }, { "path": "en\/lsdb-academycatalog\/data-1.html", "name": "Society Catalog Information", "database_name": "Society Catalog", "doi": "10.18908\/lsdba.nbdc00963-001", "description": "Information of the academic societies in Japan (organization name, website URL, contact address, etc.). You can download a flat text file.", "files": [ { "file_name": "AcademyCatalog_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/lsdb_academycatalog\/LATEST\/AcademyCatalog_en.zip", "file_size": "41.9 KB" } ], "togodb_url": "", "data_acquisition": "Survey of websites and documents.", "analysis": "", "data_number": "600 entries", "details": [ { "name": "URL", "description": "Website URL for the society" }, { "name": "Name", "description": "Society name" }, { "name": "Abbreviation", "description": "Abbreviation for the society name" }, { "name": "Class", "description": "Classification for the society" }, { "name": "Membership fee", "description": "Membership fee" }, { "name": "Academy remarks", "description": "Academy remarks" }, { "name": "Contact: E-Mail", "description": "Contact address" }, { "name": "Free public site: Free public site URL", "description": "Free public site URL" }, { "name": "Paid public site: Paid public site URL", "description": "Paid public site URL" }, { "name": "Academic journal: Name", "description": "Name for the academic journal published by the society" }, { "name": "Academic journal: Language of text", "description": "Language of text for the journal" }, { "name": "Academic journal: Language of abstract", "description": "Language of abstract for the journal" }, { "name": "Academic journal: URL", "description": "URL for the journal" }, { "name": "Academic journal: Print ISSN", "description": "Print ISSN for the journal" }, { "name": "Academic journal: Online ISSN", "description": "Online ISSN for the journal" }, { "name": "Academic journal: Online ISSN:URL of published range", "description": "URL of published range for the journal" }, { "name": "Academic journal: Term of issuance", "description": "Term of issuance for the journal" } ] }, { "path": "en\/spd\/data-1.html", "name": "Soybean protein data (gel-based)", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-001", "description": "Soybean protein data collected from samples in different organs, flood conditions and time course, and separated by two-dimensional polyacrylamide gel electrophoresis. See \" Soybean gel data\" for each gel.", "files": [ { "file_name": "soybean_based_proteomics_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_based_proteomics_list.zip", "file_size": "270 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_gelbased_proteomics_list#en", "data_acquisition": "Two-dimensional polyacrylamide gel electrophoresis", "analysis": "", "data_number": "484 entries", "details": [ { "name": "Accession", "description": "Identified protein accession number" }, { "name": "Gel ID", "description": "Gel ID where the protein is separated" }, { "name": "Spot ID", "description": "Spot ID on thegel" }, { "name": "Description", "description": "Description of the protein" }, { "name": "Exp pI", "description": "Measured isoelectric point of the protein" }, { "name": "Exp Mw", "description": "Measured molecular weight of the protein" } ] }, { "path": "en\/spd\/data-2.html", "name": "Soybean Gel data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-002", "description": "Gel data in the experiment where \"Soybean protein data (gel-based)\" is collected.", "files": [ { "file_name": "soybean_based_proteomics_gel.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_based_proteomics_gel.zip", "file_size": "6.1 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_gelbased_proteomics_gel#en", "data_acquisition": "Two-dimensional polyacrylamide gel electrophoresis", "analysis": "", "data_number": "36 entries", "details": [ { "name": "Gel ID", "description": "Gel ID" }, { "name": "Condition", "description": "Experiment sample condition" }, { "name": "pI", "description": "Range of measured isoelectric point in the gel" }, { "name": "Mw", "description": "Range of measured molecular weight in the gel" }, { "name": "Identified spots", "description": "Number of identified spots in the gel" }, { "name": "Identified proteins", "description": "Number of identified proteins in the gel" }, { "name": "Gel image", "description": "Gel image (only in simple search)" } ] }, { "path": "en\/spd\/data-3.html", "name": "Soybean Gel spot data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-003", "description": "Coordinate, pI and mw data on the gel spot in two-dimensional polyacrylamide gel electrophoresis.", "files": [ { "file_name": "soybean_based_proteomics_spot.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_based_proteomics_spot.zip", "file_size": "68 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_gelbased_proteomics_spot#en", "data_acquisition": "Two-dimensional polyacrylamide gel electrophoresis", "analysis": "", "data_number": "8,255 entries", "details": [ { "name": "Gel ID", "description": "Gel ID" }, { "name": "Spot ID", "description": "Spot ID" }, { "name": "X", "description": "X coordinate on the gel" }, { "name": "Y", "description": "Y coordinate on the gel" }, { "name": "pI", "description": "Protein isoelectric point on the spot" }, { "name": "Mw", "description": "Protein molocular weight on the spot" } ] }, { "path": "en\/spd\/data-4.html", "name": "Soybean protein data (gel-free)", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-004", "description": "Soybean protein data collected from samples in different organs, flood conditions and time course, and measured with mass spectrometer.", "files": [ { "file_name": "soybean_free_proteomics_info.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_free_proteomics_info.zip", "file_size": "1.8 MB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_gelfree_proteomics_info#en", "data_acquisition": "Measurement with mass spectrometer", "analysis": "", "data_number": "39,212 entries", "details": [ { "name": "Accession (Soybean)", "description": "Protein accession number in soybean" }, { "name": "Accession (Arabidopsis)", "description": "Protein accession number in arabidopsis" }, { "name": "Description", "description": "Description of the protein" }, { "name": "Stage", "description": "Soybean development stage (\"Seed\" or days after sowing)" }, { "name": "Organ", "description": "Organ of soybean" }, { "name": "Organelle", "description": "Organelle of soybean" }, { "name": "Stress", "description": "Condition of flood stress" }, { "name": "Mass", "description": "Protein molecular weight measured by mass spectrometer" }, { "name": "Protein content (mol %)", "description": "Protein molar concentration in the sample" }, { "name": "emPAI", "description": "Protein emPAI concentration in the sample" }, { "name": "Peptides", "description": "Number of peptides in the sample which match the protein" }, { "name": "Score", "description": "Matching score about the above" } ] }, { "path": "en\/spd\/data-5.html", "name": "Soybean transciptome data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-005", "description": "Samples are collected from soybean in different flood conditions and time course. mRNA are sequenced twice with HiCEP(High-Coverage Expression Profiling) method and clusetered.\r\nThe graph of 2nd clustering result is in TranscriptProf.pdf.", "files": [ { "file_name": "soybean_transcript.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_transcript.zip", "file_size": "1.2 MB" }, { "file_name": "TranscriptProf.pdf", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/TranscriptProf.pdf", "file_size": "224 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_transcript#en", "data_acquisition": "Sequencing with HiCEP(High-Coverage Expression Profiling) method", "analysis": "Clusetering", "data_number": "29,388 entries", "details": [ { "name": "Primer", "description": "HiCEP primer set (5' end - 3' end)" }, { "name": "Peak No", "description": "Peak number of DNA sequences identified by sequencer" }, { "name": "2(0) Height min", "description": "Sample: 2 days after seeding, 0 days after flooding\r\nMinimum peak value in sequencing" }, { "name": "2(0) Height max", "description": "Sample: 2 days after seeding, 0 days after flooding\r\nMaximum peak value in sequencing" }, { "name": "2.5(0) Height min", "description": "Sample: 2.5 days after seeding, 0 days after flooding (control)\r\nMinimum peak value in sequencing" }, { "name": "2.5(0) Height max", "description": "Sample: 2.5 days after seeding, 0 days after flooding (control)\r\nMaximum peak value in sequencing" }, { "name": "2.5(0.5) Height min", "description": "Sample: 2.5 days after seeding, 0.5 days after flooding\r\nMinimum peak value in sequencing" }, { "name": "2.5(0.5) Height max", "description": "Sample: 2.5 days after seeding, 0.5 days after flooding\r\nMaximum peak value in sequencing" }, { "name": "3(0) Height min", "description": "Sample: 3 days after seeding, 0 days after flooding (control)\r\nMinimum peak value in sequencing" }, { "name": "3(0) Height max", "description": "Sample: 3 days after seeding, 0 days after flooding (control)\r\nMaximum peak value in sequencing" }, { "name": "3(1) Height min", "description": "Sample: 3 days after seeding, 1 days after flooding\r\nMinimum peak value in sequencing" }, { "name": "3(1) Height max", "description": "Sample: 3 days after seeding, 1 days after flooding\r\nMaximum peak value in sequencing" }, { "name": "3.5(0) Height min", "description": "Sample: 3.5 days after seeding, 0 days after flooding (control)\r\nMinimum peak value in sequencing" }, { "name": "3.5(0) Height max", "description": "Sample: 3.5 days after seeding, 0 days after flooding (control)\r\nMaximum peak value in sequencing" }, { "name": "3.5(1.5) Height min", "description": "Sample: 3.5 days after seeding, 1.5 days after flooding\r\nMinimum peak value in sequencing" }, { "name": "3.5(1.5) Height max", "description": "Sample: 3.5 days after seeding, 1.5 days after flooding\r\nMaximum peak value in sequencing" }, { "name": "4(0) Height min", "description": "Sample: 4 days after seeding, 0 days after flooding (control)\r\nMinimum peak value in sequencing" }, { "name": "4(0) Height max", "description": "Sample: 4 days after seeding, 0 days after flooding (control)\r\nMaximum peak value in sequencing" }, { "name": "4(2) Height min", "description": "Sample: 4 days after seeding, 2 days after flooding\r\nMinimum peak value in sequencing" }, { "name": "4(2) Height max", "description": "Sample: 4 days after seeding, 2 days after flooding\r\nMaximum peak value in sequencing" }, { "name": "Size min", "description": "Minimum molecular weight of DNA in seuquencing" }, { "name": "Size max", "description": "Maximum molecular weight of DNA in seuquencing" }, { "name": "1_Cluster_No", "description": "Cluseter number of 1st clustering (0-31)" }, { "name": "2_Cluster_No", "description": "Cluseter number of 2nd clustering (1-65)\r\nTarget records are filtered in the following conditions:\r\n・Classified in \"31\" of 1st clutering\r\n・max peak \/ min peak > 3" }, { "name": "3_Peak_No", "description": "Graph number in \"Soybean omics data\"\r\nTarget records are filtered in the following conditions:\r\n・peak value in treated \/ peak value in control > 20" } ] }, { "path": "en\/spd\/data-6.html", "name": "Soybean metabolites data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-006", "description": "Metabolites data collected from soybean in different flood conditions and time course, and measured. They are mapped on pathways.", "files": [ { "file_name": "soybean_metabolites.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_metabolites.zip", "file_size": "882 KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/spd\/data-7.html", "name": "Soybean omics data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-007", "description": "The table which is tabulated in metabolome, proteome and transcriptome from experiments and measurements.", "files": [ { "file_name": "soybean_omics.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_omics.zip", "file_size": "4.5 MB" } ], "togodb_url": "", "data_acquisition": "Two-dimensional polyacrylamide gel electrophoresis\r\nMeasurement with mass spectrometer", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/spd\/data-8.html", "name": "References", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-008", "description": "Experiment protocols and other references", "files": [ { "file_name": "soybean_description.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_description.zip", "file_size": "659 KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/spd\/data-9.html", "name": "Soybean comparative protein data", "database_name": "SPD", "doi": "10.18908\/lsdba.nbdc00238-009", "description": "Soybean protein data collected from samples in 3 organs (leaf, hypocotyl and root) under 3 stresses (flooding, drought and salt), and separated by two-dimensional polyacrylamide gel electrophoresis.", "files": [ { "file_name": "soybean_comp_proteomics_list.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/spd\/LATEST\/soybean_comp_proteomics_list.zip", "file_size": "8 KB" } ], "togodb_url": "https:\/\/togodb.biosciencedbc.jp\/togodb\/view\/soybean_comp_proteomics_list#en", "data_acquisition": "Two-dimensional polyacrylamide gel electrophoresis", "analysis": "", "data_number": "349 entries", "details": [ { "name": "Organ", "description": "Organ of soybean" }, { "name": "Stress", "description": "Stress on soybean" }, { "name": "Spot No", "description": "Spot No on gels" }, { "name": "Homologous protein", "description": "Homologous protein of measured one" }, { "name": "Accession No", "description": "Accession No of homologous protein" }, { "name": "Mr(kDa)-theory", "description": "Theoretical molecular weight of homologous protein" }, { "name": "Mr(kDa)-exp", "description": "Measured molecular weight" }, { "name": "pI-theory", "description": "Protein isoelectric point of homologous protein" }, { "name": "pI-exp", "description": "Measured protein isoelectric point" }, { "name": "F.C.", "description": "Fold change compared with no treatment (without stress) soybean samples" } ] }, { "path": "en\/ssbd\/data-1.html", "name": "BDML Datasets", "database_name": "SSBD", "doi": "10.18908\/lsdba.nbdc01349-001", "description": "Dataset summary and the resource from which it is derived", "files": [ { "file_name": "ssbd_bdml_dataset.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ssbd\/LATEST\/ssbd_bdml_dataset.zip", "file_size": "2.0KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ssbd_bdml_dataset#en", "data_acquisition": "", "analysis": "", "data_number": "9 entries", "details": [ { "name": "Organism", "description": "Name of a targeted organism." }, { "name": "Datatype", "description": "Describes specific type of data that was represented in the BDML file" }, { "name": "Basedon", "description": "Speficifies whether the data was gathered from an in vivo measurement or from a computer simulation." }, { "name": "Contributor", "description": "Names of contributors who produced\/collected the data." }, { "name": "Number of BDML-files", "description": "Number of BDML-files" }, { "name": "Contact Information", "description": "Contact information for the BDML file." }, { "name": "Summary of methods", "description": "Methods\/procedures used to obtain the data described in the BDML file." }, { "name": "PubMed ID", "description": "PubMed ID of the original published paper." }, { "name": "License", "description": "License information of the BDML file." }, { "name": "Data Scale (XYZ,T)", "description": "Scale and unit of coordinates and time." }, { "name": "Dataset Description", "description": "Description about the dataset." } ] }, { "path": "en\/ssbd\/data-2.html", "name": "BDML Metadata", "database_name": "SSBD", "doi": "10.18908\/lsdba.nbdc01349-002", "description": "Meta-information of quantitative data in BDML format", "files": [ { "file_name": "ssbd_bdml_metadata.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/ssbd\/LATEST\/ssbd_bdml_metadata.zip", "file_size": "467KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/ssbd_bdml_metadata#en", "data_acquisition": "", "analysis": "", "data_number": "516 entries", "details": [ { "name": "Title", "description": "Title of the BDML file." }, { "name": "Description", "description": "Detailed information about the data described in the BDML file" }, { "name": "Organism", "description": "Name of a targeted organism." }, { "name": "Datatype", "description": "Describes specific type of data that was represented in the BDML file" }, { "name": "Local ID", "description": "Internal or local identifier used to identify the BDML file." }, { "name": "Basedon", "description": "Speficifies whether the data was gathered from an in vivo measurement or from a computer simulation." }, { "name": "Contributor", "description": "Names of contributors who produced\/collected the data." }, { "name": "Contact Information", "description": "Contact information for the BDML file." }, { "name": "Summary of methods", "description": "Methods\/procedures used to obtain the data described in the BDML file." }, { "name": "PubMed ID", "description": "PubMed ID of the original published paper." }, { "name": "License", "description": "License information of the BDML file." }, { "name": "Schema", "description": "Version of BDML schema." }, { "name": "BDML ID", "description": "Unique ID of the BDML file." }, { "name": "Data Scale (XYZ,T)", "description": "Scale and unit of coordinates and time." }, { "name": "Source", "description": "A URL link to original sources such as microscope images for an experimental measurement or files of mathematical model for a computer simulation." }, { "name": "BDML file", "description": "A URL link to download a BDML file" }, { "name": "PDPML file", "description": "A URL link to download a PDPML file" }, { "name": "SSBD web page", "description": "A URL link to view a summay page" }, { "name": "SSBD-OMERO web page", "description": "A URL link to view a set of microscopy images" } ] }, { "path": "en\/taxonomy-icon\/data-1.html", "name": "Taxonomy Icon Data", "database_name": "Taxonomy Icon", "doi": "10.18908\/lsdba.nbdc00805-001", "description": "Illustrations (icons) of biological species. Four different types of illustrations are provided; Large, Small, Large with No Background, Small with No Background. You can use image files of illustrations and also place icons on a website using URLs of the icons.\r\nIn a simple search table, you can narrow down the icons using a taxonomy tree view, located on top of the table.", "files": [ { "file_name": "taxonomy_icon_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/taxonomy-icon\/LATEST\/taxonomy_icon_en.zip", "file_size": "14.1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/taxonomy_icon_en", "data_acquisition": "Illustrations (icons) are created based on picture books and other materials.", "analysis": "", "data_number": "220 entries", "details": [ { "name": "Name", "description": "English common name of species" }, { "name": "Scientific Name", "description": "Scientific name of species" }, { "name": "Taxonomy ID", "description": "NCBI Taxonomy ID (Link to NCBI in Simple Search)" }, { "name": "Icon Taxonomy", "description": "Taxonomy information which were used to refine icons in original database interface." }, { "name": "Icon (Large)", "description": "File name of the large-sized icon (The icon is displayed in Simple Search.)" }, { "name": "Icon (Large) No Background", "description": "File name of the large-sized icon with no background (The icon is displayed in Simple Search.)" }, { "name": "Icon (Small)", "description": "File name of the small-sized icon (The icon is displayed in Simple Search.)" }, { "name": "Icon (Small) No Background", "description": "File name of the small-sized icon with no background (The icon is displayed in Simple Search.)" }, { "name": "URL of Icon (Large)", "description": "URL to diplay the large-sized icon" }, { "name": "URL of Icon (Large) No Background", "description": "URL to diplay the large-sized icon with no background" }, { "name": "URL of Icon (Small)", "description": "URL to diplay the small-sized icon" }, { "name": "URL of Icon (Small) No Background", "description": "URL to diplay the small-sized icon with no background" }, { "name": "Comment", "description": "Link to Simple Search for comment" } ] }, { "path": "en\/taxonomy-icon\/data-2.html", "name": "Taxonomy Icon Images (PNG format)", "database_name": "Taxonomy Icon", "doi": "10.18908\/lsdba.nbdc00805-002", "description": "Illustrations (icons) of biological species. Four different types of illustrations are provided; Large, Small, Large with No Background, Small with No Background.", "files": [ { "file_name": "taxonomy_icon_png.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/taxonomy-icon\/LATEST\/taxonomy_icon_png.zip", "file_size": "7.9 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "A total of 880 files: 220 files for each type of icon (Large, Small, Large with No Background, Small with No Background)", "details": [] }, { "path": "en\/taxonomy-icon\/data-3.html", "name": "Comment", "database_name": "Taxonomy Icon", "doi": "10.18908\/lsdba.nbdc00805-003", "description": "Comments and images posted on icon entries through the Taxonomy Icon original website.", "files": [ { "file_name": "taxonomy_icon_comment_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/taxonomy-icon\/LATEST\/taxonomy_icon_comment_en.zip", "file_size": "5.7 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/taxonomy_icon_comment_en", "data_acquisition": "", "analysis": "", "data_number": "88 entries", "details": [ { "name": "Species Name", "description": "English common name of species" }, { "name": "Scientific Name", "description": "Scientific name of species" }, { "name": "Icon", "description": "File name of the icon (The icon is displayed in Simple Search.)" }, { "name": "Image", "description": "File name of the image posted on the icon entry (The image is displayed in Simple Search.)" }, { "name": "License", "description": "License of the image posted on the icon entry (This License information is shown at \"Image\" column in Simple Search.)" }, { "name": "Comment", "description": "Comment posted on the icon entry" }, { "name": "Name", "description": "Name who posted the commnet" }, { "name": "Created Date", "description": "Date when the comment was posted" }, { "name": "Last Modified Date", "description": "Last modified date of the comment" } ] }, { "path": "en\/taxonomy-icon\/data-4.html", "name": "Images on Comment （PNG format)", "database_name": "Taxonomy Icon", "doi": "10.18908\/lsdba.nbdc00805-004", "description": "Images (PNG format) posted on icon entries through the Taxonomy Icon original website.", "files": [ { "file_name": "taxonomy_icon_comment_png_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/taxonomy-icon\/LATEST\/taxonomy_icon_comment_png_en.zip", "file_size": "15.8 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "Image: 36 files\r\nAttribution of each image: 1 file", "details": [] }, { "path": "en\/agritogo-rice-phenome\/data-1.html", "name": "The list of strains and growth conditions", "database_name": "The Rice Growth Monitoring for the Phenotypic Functional Analysis", "doi": "10.18908\/lsdba.nbdc00945-001", "description": "The list of strains and growth conditions for respective samples.", "files": [ { "file_name": "phenome_data.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/agritogo-rice-phenome\/LATEST\/data\/phenome_data.zip", "file_size": "1KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/agritogo_phenome_data_list#en", "data_acquisition": "", "analysis": "", "data_number": "7 entries", "details": [ { "name": "ID", "description": "ID of the test" }, { "name": "Type", "description": "Type of the measuring instrument" }, { "name": "Species", "description": "Species (Oryza sativa)" }, { "name": "Material", "description": "Strain" }, { "name": "Light condition", "description": "Light condition" }, { "name": "Temperature", "description": "Temperature" }, { "name": "Humidity", "description": "Humidity" }, { "name": "Medium", "description": "Medium" }, { "name": "Growth Chamber", "description": "Growth Chamber" }, { "name": "Soil", "description": "Soil" }, { "name": "Imaging system", "description": "Imaging system" }, { "name": "Camera", "description": "Camera" }, { "name": "Induction of germination \/ Period", "description": "Period of imaging (for ID=1) or start time of germination induction and imaging (for other entries)" }, { "name": "Duration of observation", "description": "Duration of observation" }, { "name": "Intervals of imaging", "description": "Intervals of imaging" }, { "name": "Growth data", "description": "Graph of chronological changes in growth" }, { "name": "Image list", "description": "Name list of images" }, { "name": "Large image", "description": "The zip file of the images (Large image)" }, { "name": "Small image", "description": "The zip file of the images (Small image)" }, { "name": "First image", "description": "First image (only Simple search site)" }, { "name": "Last image", "description": "Last image (only Simple search site)" } ] }, { "path": "en\/agritogo-rice-phenome\/data-2.html", "name": "The list of growth image files", "database_name": "The Rice Growth Monitoring for the Phenotypic Functional Analysis", "doi": "10.18908\/lsdba.nbdc00945-002", "description": "The list of growth image files for each samples.", "files": [ { "file_name": "images_list.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/agritogo-rice-phenome\/LATEST\/data\/images_list.zip", "file_size": "16KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "7 entries", "details": [] }, { "path": "en\/agritogo-rice-phenome\/data-3.html", "name": "Graph of growth data", "database_name": "The Rice Growth Monitoring for the Phenotypic Functional Analysis", "doi": "10.18908\/lsdba.nbdc00945-003", "description": "The graph of chronological changes in root, coleoptile, the first leaf, and the second leaf.", "files": [ { "file_name": "growth_data_graph.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/agritogo-rice-phenome\/LATEST\/data\/growth_data_graph.zip", "file_size": "36KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "4 entries", "details": [] }, { "path": "en\/agritogo-rice-phenome\/data-4.html", "name": "The rice growth image files", "database_name": "The Rice Growth Monitoring for the Phenotypic Functional Analysis", "doi": "10.18908\/lsdba.nbdc00945-004", "description": "The rice growth image files categorized based on file size.", "files": [ { "file_name": "image files (directory)", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/agritogo-rice-phenome\/LATEST\/images", "file_size": "233MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "14 entries", "details": [] }, { "path": "en\/agritogo-rice-phenome\/data-5.html", "name": "Explanation of the project", "database_name": "The Rice Growth Monitoring for the Phenotypic Functional Analysis", "doi": "10.18908\/lsdba.nbdc00945-005", "description": "The data consist of static web pages, which are able to be accessed from the top page of the web site. These pages explain the project.", "files": [ { "file_name": "phenome_outline.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/agritogo-rice-phenome\/LATEST\/phenome_outline.zip", "file_size": "377KB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "", "details": [] }, { "path": "en\/tmbeta-genome\/data-1.html", "name": "Sequence Collection", "database_name": "TMBETA-GENOME", "doi": "10.18908\/lsdba.nbdc00713-001", "description": "A collection of complete genomes annotated with β-barrel membrane protein predictions. For a genome that have multiple chromosomes, the entry set for each chormosome is given individually.", "files": [ { "file_name": "tmbeta_genome_sequence_collection.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tmbeta-genome\/LATEST\/tmbeta_genome_sequence_collection.zip", "file_size": "8.8 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tmbeta_genome_sequence_collection#en", "data_acquisition": "275 complete genomes, including 23 genomes from archaea, 237 from bacteria and 15 from eukaryote, were taken from the NCBI database.", "analysis": "", "data_number": "427 entries", "details": [ { "name": "Sequence Collection ID", "description": "Sequential serial number assigned to each genome." }, { "name": "Classification", "description": "Biological classification (Archaea, Bacteria and Eukaryota)" }, { "name": "Organism Name", "description": "Name of the organism. Chromosome number is added to the name if the organism has multiple chromosomes." }, { "name": "Locus", "description": "RefSeq ID of the genome sequence." }, { "name": "FASTA File", "description": "Name of the FASTA file where the genome sequence is listed." } ] }, { "path": "en\/tmbeta-genome\/data-2.html", "name": "Sequence Classification", "database_name": "TMBETA-GENOME", "doi": "10.18908\/lsdba.nbdc00713-002", "description": "Results of predicting β-barrel membrane proteins or transmembrane helical proteins by applying statistical and machine learning methods to each amino acid sequence in the genomes. Statistical methods are based on amino acid composition, residue pair preference (dipeptide) and motifs (2 amino acid residues with an in-between residue gap). In machine learning methods, the combination of amino acid and dipeptide compositions has been used as main attributes.", "files": [ { "file_name": "tmbeta_genome_sequence_classification.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tmbeta-genome\/LATEST\/tmbeta_genome_sequence_classification.zip", "file_size": "177 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tmbeta_genome_sequence_classification#en", "data_acquisition": "Amino acid sequences were taken from the NCBI database.", "analysis": "", "data_number": "903,989 entries", "details": [ { "name": "Sequence ID", "description": "Sequential serial number assigned to each amino acid sequence." }, { "name": "Sequence Collection ID", "description": "Sequential serial number assigned to each genome." }, { "name": "New Approach", "description": "Result of predicting transmembrane helical protein using a newly developed method which is performed by the following steps.\r\n\r\nIdentify the β-barrel membrane proteins using the dipeptide compositions of β-barrel membrane proteins and globular proteins.\r\nRefine the search using the dipeptide compositions of β-barrel membrane proteins and transmembrane helical proteins.\r\nRemove the shorter sequences (proteins with less than 50 amino acid residues).\r\nEliminate transmembrane helical proteins using SOSUI, a prediction system for transmembrane helical proteins, using the criterion that it identified at least two membrane spanning helical segments.\r\nExclude globular and transmembrane helical proteins which have > 70% sequence identity and 80% coverage with that deposited in PDB.\r\nExclude globular and transmembrane helical proteins which have > 80% sequence identity with that deposited in SWISS-PROT database." }, { "name": "SOSUI", "description": "Result of predicting transmembrane helical protein using SOSUI." }, { "name": "Amino Acid", "description": "Result of predicting β-barrel membrane protein with a statistical method using amino acid composition. (TMBETADISC-COMP)" }, { "name": "Dipeptide", "description": "Result of predicting β-barrel membrane protein with a statistical method using residue pair preference. (TMBETADISC_DIPEPTIDE)" }, { "name": "Motif", "description": "Result of predicting β-barrel membrane protein with a statistical method using motifs. (TMBETADISC-MOTIF)" }, { "name": "SVM", "description": "Result of predicting β-barrel membrane protein with a machine learning method using amino acid composition and residue pair preference. (TMBETA-SVM)" }, { "name": "Header", "description": "Header line of the amino acid sequence entry in the FASTA file." }, { "name": "Sequence", "description": "Amino acid sequence" } ] }, { "path": "en\/tmfunction\/data-1.html", "name": "TMFunction data", "database_name": "TMFunction", "doi": "10.18908\/lsdba.nbdc00714-001", "description": "TMFunction is a database of functional residues in alpha-helical and beta-barrel membrane proteins. Each protein is identified with its name and source alongwith the UniProt code. The protein data bank (PDB) codes are also given for available proteins. Different methods and experimental parameters, for example, affinity, dissociation constant, IC50, activity etc. are given in the database. Further, we have provided the numerical experimental value for each residue (or mutant) in a protein. The experimental data are collected from the literature both by searching the journals as well as with the keyword search at PubMed. In addition, complete reference is given with journal citation and PMID number.", "files": [ { "file_name": "tmfunction.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tmfunction\/LATEST\/tmfunction.zip", "file_size": "48.5 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tmfunction#en", "data_acquisition": "UniProt, PDB, PubMed", "analysis": "", "data_number": "2,907 entries", "details": [ { "name": "Entry", "description": "Entry" }, { "name": "Residue(mutation)", "description": "Name of residue with mutation" }, { "name": "Residue", "description": "Name of residue" }, { "name": "Functionally important", "description": "Functionally important or not" }, { "name": "Function of the protein", "description": "Function of the protein" }, { "name": "Location", "description": "Location of residue in the protein" }, { "name": "Protein Name(abbreviation)", "description": "Protein Name(abbreviation)" }, { "name": "Source(scientific name)", "description": "Source of protein (scientific name)" }, { "name": "Source(english name)", "description": "Source(english name)" }, { "name": "Authors", "description": "Authors of reference" }, { "name": "Journal Reference", "description": "Journal Reference" }, { "name": "PMID", "description": "PubMed ID of reference" }, { "name": "Experiments", "description": "Experiments" }, { "name": "Experimental data", "description": "The value with \"Parameter\" shows a measurement value in experiments." }, { "name": "Parameter", "description": "Experimental parameter" }, { "name": "Methods\/conditions", "description": "Experimental methods\/conditions" }, { "name": "PDB ID", "description": "PDB ID of the protein structure" }, { "name": "ASA", "description": "Accessible surface area" }, { "name": "Sec. Str", "description": "Secondary structure of this protein\r\n- G: 3-10 helix\r\n- H: Helix\r\n- L: Loop" }, { "name": "Uniprot ID", "description": "UniProt ID of protein" }, { "name": "Type", "description": "Type of protein" }, { "name": "Remarks", "description": "Remarks" }, { "name": "Keywords", "description": "Keywords" } ] }, { "path": "en\/togo-pic\/data-1.html", "name": "Image collection", "database_name": "Togo Picture Gallery", "doi": "", "description": "It is the image collection for life science. Images are provided in 3 file format (PNG, AI, SVG).", "files": [ { "file_name": "Image list (CSV)", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/togo-pic\/image\/20180926_togopic_masterfile.csv", "file_size": "123 KB" }, { "file_name": "image", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/togo-pic\/image\/", "file_size": "1.2 GB" }, { "file_name": "png_format.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/togo-pic\/LATEST\/png_format.zip", "file_size": "186 MB" }, { "file_name": "ai_format.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/togo-pic\/LATEST\/ai_format.zip", "file_size": "313 MB" }, { "file_name": "svg_format.zip", "file_url": "https:\/\/dbarchive.biosciencedbc.jp\/data\/togo-pic\/LATEST\/svg_format.zip", "file_size": "127 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/togo_pic_image#en", "data_acquisition": "", "analysis": "", "data_number": "539 entries", "details": [ { "name": "Picture ID", "description": "Picture ID" }, { "name": "Thumbnail", "description": "Thumbnail" }, { "name": "Title (jp)", "description": "Title (Japanese)" }, { "name": "Title (en)", "description": "Title (English)" }, { "name": "Scientific Name", "description": "Scientific Name" }, { "name": "Taxonomy ID", "description": "Taxonomy ID" }, { "name": "Tags", "description": "Tags associated with the image" } ] }, { "path": "en\/tpatlas\/data-1.html", "name": "Main", "database_name": "TP Atlas", "doi": "10.18908\/lsdba.nbdc01161-001", "description": "It is a summary table of achievements in the Targeted Proteins Research Program (TPRP)-structural biology project in Japan; including background, highlight and references of each project.", "files": [ { "file_name": "tp_atlas_en.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tp_atlas\/LATEST\/tp_atlas_en.zip", "file_size": "20.1 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tp_atlas_en", "data_acquisition": "", "analysis": "", "data_number": "35 entries", "details": [ { "name": "Project ID", "description": "Project ID" }, { "name": "Project Theme", "description": "Theme of the project" }, { "name": "Project Theme (short)", "description": "Theme of the project (short ver.)" }, { "name": "Principal Investigator", "description": "Principal Investigator of the project" }, { "name": "Affiliation", "description": "Affiliation of the project" }, { "name": "Backgrounds", "description": "Backgrounds of the project" }, { "name": "Highlights", "description": "Highlights of the project" }, { "name": "Outline", "description": "Outline of the project" }, { "name": "Review", "description": "Reviews or original papers on the project\r\n(In the cases of multiple items, they are arranged in the same order as PubMed ID.)" }, { "name": "PubMed ID", "description": "PubMed ID\r\n(In the cases of multiple items, they are arranged in the same order as Review.)" }, { "name": "CSML File", "description": "Name of the Network data (CSML file) (Linked to the Network data in the Simple Search site.)" } ] }, { "path": "en\/tpatlas\/data-2.html", "name": "Protein", "database_name": "TP Atlas", "doi": "10.18908\/lsdba.nbdc01161-002", "description": "It is a summary table of protein information in individual projects; such as protein name, abbreviation, organism and terms for searching protein information on other websites.", "files": [ { "file_name": "tp_atlas_protein.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tp_atlas\/LATEST\/tp_atlas_protein.zip", "file_size": "49.8 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/tp_atlas_protein#en", "data_acquisition": "", "analysis": "", "data_number": "849 entries", "details": [ { "name": "Project ID", "description": "Project ID" }, { "name": "Sub Group", "description": "Sub group of the protein" }, { "name": "Symbol", "description": "Symbol of the protein" }, { "name": "Synonym", "description": "Synonym of the protein" }, { "name": "Wiki", "description": "Search term in wikipedia" }, { "name": "Full Name", "description": "Full name of the protein" }, { "name": "Other Names", "description": "Other names of the protein" }, { "name": "TaxId", "description": "Taxon identifer in UniProt Taxonomy" }, { "name": "Organism", "description": "Organism of the protein" }, { "name": "Entrez", "description": "Gene ID in NCBI Gene" }, { "name": "UniProt", "description": "UniProt KB accession number" }, { "name": "GNP", "description": "Gene ID in GNP (Genome Network Platform) (NCBI Gene ID)" }, { "name": "Struct. PDB", "description": "PDB ID in PDBj (Protein Data Bank Japan)" }, { "name": "Struct. P3K", "description": "PDB ID in Protein 3000 Structure Gallery" }, { "name": "Struct. TPRP", "description": "PDB ID in TP Structure Gallery" }, { "name": "PPI GNP", "description": "Gene ID in PPI in GNP (NCBI Gene ID)" }, { "name": "PCI", "description": "PDB ID in PCI" }, { "name": "TP Article", "description": "PMID (PubMed ID) in PubMed" }, { "name": "Press Release", "description": "TP press release ID" } ] }, { "path": "en\/tpatlas\/data-3.html", "name": "Network File", "database_name": "TP Atlas", "doi": "10.18908\/lsdba.nbdc01161-003", "description": "Network diagrams (in CSML format) for each project. One project has one pathway file originally drawn by Cell Illustrator.", "files": [ { "file_name": "tp_atlas_csml.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tp_atlas\/LATEST\/tp_atlas_csml.zip", "file_size": "2.02 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "35 entries", "details": [] }, { "path": "en\/tpatlas\/data-4.html", "name": "Image File", "database_name": "TP Atlas", "doi": "10.18908\/lsdba.nbdc01161-004", "description": "Network diagrams (in PNG format) for each project. One project has one pathway file originally drawn by Cell Illustrator.", "files": [ { "file_name": "tp_atlas_png.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/tp_atlas\/LATEST\/tp_atlas_png.zip", "file_size": "6.93 MB" } ], "togodb_url": "", "data_acquisition": "", "analysis": "", "data_number": "35 entries", "details": [] }, { "path": "en\/trnadb-ce\/data-1.html", "name": "tRNA sequence data, annotation data and curation data", "database_name": "tRNADB-CE", "doi": "10.18908\/lsdba.nbdc00720-001", "description": "Data of tRNA search results and curation data. Three prediction programs (tRNAScan-SE, Aragorn and tRNA finder) were used together to search tRNA genes. If the prediction results did not match, curation was carried out by experts.\r\nThe following three types of determinations are used for determining the results.\r\n- reliable tRNA gene　(\"circle\" mark at the original website.)\r\n- ambiguous case　(\"triangle\" mark at the original website.)\r\n- not tRNA gene　(\"x\" mark at the original website.)\r\n\r\nThe data are classified into nine types as follows according to sources.\r\n- Prokaryotic complete genome: 95,512 entries.\r\n- Prokaryotic draft genome (WGS): 196,032 entries.\r\n- Plant: 1,608 entries.\r\n- Fungus: 2,773 entries.\r\n- Virus: 151 entries.\r\n- Phage: 962 entries.\r\n- Chloroplast: 4,376 entries.\r\n- Environmental sample (ENV) from GenBank: 101,837 entries.\r\n- Environmental sample (ENV) from Sequence Read Archive: 54,872 entries.\r\n\r\nThe number of data is 458,123 in total. The data are given in a CSV format text file.", "files": [ { "file_name": "trnadb_ce.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/trnadb_ce\/LATEST\/trnadb_ce.zip", "file_size": "22.7 MB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/trnadb_ce#en", "data_acquisition": "", "analysis": "Three prediction programs (tRNAScan-SE, Aragorn and tRNA finder) were used together to search tRNA genes. If the prediction results did not match, curation was carried out by experts.", "data_number": "458,123 entries", "details": [ { "name": "Data type", "description": "Types of acquired data. Classified into nine types including \"Prokaryotic complete genome\", \"Prokaryotic draft genome (WGS)\", \"Plant\", \"Fungus\", \"Virus\", \"Phage\", \"Chloroplast\", \"Environmental sample (ENV) from GenBank\" and \"Environmental sample (ENV) from Sequence Read Archive\"." }, { "name": "Sequence ID", "description": "Sequence ID" }, { "name": "Genome ID", "description": "Genome ID (Genome ID of DDBJ GIB is used.)" }, { "name": "Phylum\/Class", "description": "Taxon name" }, { "name": "Species", "description": "Species name" }, { "name": "Start position", "description": "tRNA gene start position on the genome" }, { "name": "End position", "description": "tRNA gene end position on the genome" }, { "name": "Direction", "description": "Direction of tRNA gene on the genome" }, { "name": "Amino Acid", "description": "Amino acid type" }, { "name": "Anticodon", "description": "Anticodon" }, { "name": "1st Intron start position", "description": "Start position of first intron" }, { "name": "1st Intron end position", "description": "End position of first intron" }, { "name": "Seq", "description": "tRNA sequence" }, { "name": "Upstream seq.", "description": "tRNA gene upstream sequence (10 bps)" }, { "name": "tRNA1-7", "description": "1st to 7th nucleotides in the clover-leaf secondary structures (*1) of tRNA gene" }, { "name": "tRNA8-9", "description": "8th to 9th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA10-13", "description": "10th to 13th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA14-21", "description": "14th to 21st nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA22-25", "description": "22nd to 25th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA26", "description": "26th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA27-31", "description": "27th to 31st nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA32-38", "description": "32nd to 38th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA39-43", "description": "39th to 43rd nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA44-48", "description": "44th to 48th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA49-53", "description": "49th to 53rd nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA54-60", "description": "54th to 60th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA61-65", "description": "61st to 65th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA66-72", "description": "66th to 72nd nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "tRNA73-76", "description": "73rd to 76th nucleotides in the clover-leaf secondary structures of tRNA gene" }, { "name": "Downstream seq.", "description": "tRNA gene downstream sequence (10 bps)" }, { "name": "1st Intron seq.", "description": "First intron sequence" }, { "name": "2nd Intron start position", "description": "Start position of second intron" }, { "name": "2nd Intron end position", "description": "End position of second intron" }, { "name": "2st Intron seq.", "description": "Second intron sequence" }, { "name": "Decision from Dr. Muto", "description": "Determination 1 (Dr. Muto)" }, { "name": "Decision from Dr. Inokuchi", "description": "Determination 2 (Dr. Inokuchi)" }, { "name": "Decision from Dr. Yamada", "description": "Determination 3 (Dr. Yamada)" }, { "name": "Comment of Dr. Muto", "description": "Comment 1 (Dr. Muto)" }, { "name": "Comment of Dr. Inokuchi", "description": "Comment 2 (Dr. Inokuchi)" }, { "name": "Comment of Dr. Yamada", "description": "Comment 3 (Dr. Yamada)" }, { "name": "Final decision", "description": "Final Determination" }, { "name": "Comments", "description": "Comment" }, { "name": "Original database", "description": "Genome sequence source information" } ] }, { "path": "en\/trypanosome\/data-1.html", "name": "Protein", "database_name": "Trypanosomes Database", "doi": "10.18908\/lsdba.nbdc01243-001", "description": "It is a summaly table of protein information; such as sequences of mRNA and Amino acids, functions and metabolic pathways related to the protein. There is also information of candidate inhibitor of the protein.", "files": [ { "file_name": "trypanosome.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/trypanosome\/LATEST\/trypanosome.zip", "file_size": "1.4 KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/trypanosome#en", "data_acquisition": "", "analysis": "", "data_number": "17 entries", "details": [ { "name": "symbol", "description": "Symbol of the protein" }, { "name": "name", "description": "Name of the protein" }, { "name": "organism", "description": "Organism of the protein" }, { "name": "mRNA sequence", "description": "GI number of the mRNA sequence (Link to the NCBI Nucleotide in the Simple search site)" }, { "name": "protein sequence", "description": "GI number of the Amino Acid sequence (Link to the NCBI Protein in the Simple search site)" }, { "name": "entrez", "description": "Gene ID (NCBI Gene)" }, { "name": "uniprot", "description": "UniProt Accession number" }, { "name": "wikipedia", "description": "Search term in Wikipedia" }, { "name": "ec", "description": "Enzyme Commission number" }, { "name": "omim", "description": "OMIM ID (Online Mendelian inheritance in Man)" }, { "name": "map", "description": "Location of the gene on a chromosome or its chromosome number" }, { "name": "pdb", "description": "PDB ID (PDBj: Protein Data Bank Japan)" }, { "name": "kegg pathway", "description": "ID of the KEGG pathway" }, { "name": "candidate inhibitor", "description": "Name of candidate inhibitor of the protein" }, { "name": "drugport id", "description": "DrugBank ID of candidate inhibitor" } ] }, { "path": "en\/yeast-y2h\/data-1.html", "name": "Core Data of Yeast Interacting Proteins Database (Annotation Updated Version)", "database_name": "Yeast Interacting Proteins Database", "doi": "10.18908\/lsdba.nbdc00742-001", "description": "Highly reproducible interaction data in the Yeast Interacting Proteins Database with the \"IST hit\" (to be described in the table below) of 3 or more. Annotation (gene name and description) is updated by the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/, August 15, 2009). The number of data is 841. The data are given in a CSV format text file.", "files": [ { "file_name": "core_updated.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_y2h\/LATEST\/core_updated.zip", "file_size": "77KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/yipd_core_updated#en", "data_acquisition": "Yeast two-hybrid method. (Fields, S. & Song, O. K. (1989) Nature (London) 340, 245-246.)", "analysis": "As the indicator of reliability of the interactions obtained by the experiment, the literature information described about the yeast proteins and their interactions are required. Several sources including YPD (Yeast Proteome Database, Costanzo, M. C., Hogan, J. D., Cusick, M. E., Davis, B. P., Fancher, A. M., Hodges, P. E., Kondu, P., Lengieza, C., Lew-Smith, J. E., Lingner, C., et al. (2000) Nucleic Acids Res. 28, 73-76.) are used for literature collection.", "data_number": "841 interactions", "details": [ { "name": "Bait ORF", "description": "The ORF name of Bait, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/)." }, { "name": "Bait gene name", "description": "The gene name of Bait, and the standard name in the SGD." }, { "name": "Bait description", "description": "The annotation of Bait, and description in the SGD." }, { "name": "Rows with this bait as bait", "description": "The number of rows (interactions) having this Bait ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this bait as prey", "description": "The number of rows (interactions) having this Bait ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Prey ORF", "description": "The ORF name of Prey, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org)." }, { "name": "Prey gene name", "description": "The gene name of Prey, and the standard name in the SGD." }, { "name": "Prey description", "description": "The annotation of Prey, and description in the SGD." }, { "name": "Rows with this prey as prey", "description": "The number of rows (interactions) having this Prey ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this prey as bait", "description": "The number of rows (interactions) having this Prey ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Literature on bait(YPD)", "description": "The number of articles concerning Bait, obtained from YPD (Yeast Proteome Database)(*1)." }, { "name": "Literature on prey(YPD)", "description": "The number of articles concerning Prey, obtained from YPD." }, { "name": "Literature shared by bait and prey", "description": "The number of articles common to Bait and Prey, as calculated on the basis of the number of articles obtained from the YPD." }, { "name": "Literature sharing score", "description": "The score concerning co-occurrence of Prey and Bait in the literature, calculated by the calculation formula.\r\nCalculation formula for the score:\r\nhttps:\/\/dbarchive.biosciencedbc.jp\/images\/db_meta\/yeast_y2h\/literature_sharing_score.png" }, { "name": "CuraGen(0 or 1)", "description": "Investigation by CuraGen (0 or 1), obtained from Uetz et al.(*2)" }, { "name": "S. Fields(0 or 1)", "description": "Investigation by S. Fields (0 or 1), obtained from Uetz et al." }, { "name": "Association(0 or 1,YPD)", "description": "Association (0 or 1), obtained from the YPD." }, { "name": "Complex (0 or 1,YPD)", "description": "Formation of complex (0 or 1), obtained from the YPD." }, { "name": "Synthetic lethality(0 or 1,YPD)", "description": "Synthetic lethality (0 or 1), obtained from the YPD." }, { "name": "Co-induced by(YPD)", "description": "Factor that induces expression of both genes, obtained from the YPD." }, { "name": "Co-repressed by(YPD)", "description": "Factor that suppresses expression of both genes, obtained from the YPD." }, { "name": "Not affected by(YPD)", "description": "Factor that does not affect expression of these genes, obtained from the YPD." }, { "name": "Interologs", "description": "The number of interactions that exist between the interacting protein and the ortholog of other species, obtained from the Database of Interacting Proteins(*3)." }, { "name": "Expression similarity (BRITE)", "description": "Expression data obtained from KEGG BRITE(*4). (High values only, 0.9 or greater)" }, { "name": "Alternative path with 1 intervening protein", "description": "The number of paths other than this interaction mediated by one intermediate protein, calculated from the full data." }, { "name": "Alternative path with 2 intervening proteins", "description": "The number of paths other than this interaction mediated by two intermediate proteins, calculated from the full data." }, { "name": "IST hit", "description": "Number of hits of Interaction Sequence Tags (IST) (The number of detected interactions and the indicator of reproducibility)" }, { "name": "IST hit in the opposite bait\/prey orientation", "description": "The IST hit number for a combination in which Bait and Prey are in the reverse direction." } ] }, { "path": "en\/yeast-y2h\/data-2.html", "name": "Full Data of Yeast Interacting Proteins Database (Annotation Updated Version)", "database_name": "Yeast Interacting Proteins Database", "doi": "10.18908\/lsdba.nbdc00742-002", "description": "The entire data in the Yeast Interacting Proteins Database. Annotation (gene name and description) is updated by the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/, August 15, 2009). The number of data is 4,549. The data are given in a CSV format text file.", "files": [ { "file_name": "full_updated.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_y2h\/LATEST\/full_updated.zip", "file_size": "372KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/yipd_full_updated#en", "data_acquisition": "Yeast two-hybrid method. (Fields, S. & Song, O. K. (1989) Nature (London) 340, 245-246.)", "analysis": "As the indicator of reliability of the interactions obtained by the experiment, the literature information described about the yeast proteins and their interactions are required. Several sources including YPD (Yeast Proteome Database, Costanzo, M. C., Hogan, J. D., Cusick, M. E., Davis, B. P., Fancher, A. M., Hodges, P. E., Kondu, P., Lengieza, C., Lew-Smith, J. E., Lingner, C., et al. (2000) Nucleic Acids Res. 28, 73-76.) are used for literature collection.", "data_number": "841 interactions", "details": [ { "name": "Bait ORF", "description": "The ORF name of Bait, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/)." }, { "name": "Bait gene name", "description": "The gene name of Bait, and the standard name in the SGD." }, { "name": "Bait description", "description": "The annotation of Bait, and description in the SGD." }, { "name": "Rows with this bait as bait", "description": "The number of rows (interactions) having this Bait ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this bait as prey", "description": "The number of rows (interactions) having this Bait ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Prey ORF", "description": "The ORF name of Prey, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org)." }, { "name": "Prey gene name", "description": "The gene name of Prey, and the standard name in the SGD." }, { "name": "Prey description", "description": "The annotation of Prey, and description in the SGD." }, { "name": "Rows with this prey as prey", "description": "The number of rows (interactions) having this Prey ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this prey as bait", "description": "The number of rows (interactions) having this Prey ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Literature on bait(YPD)", "description": "The number of articles concerning Bait, obtained from YPD (Yeast Proteome Database)(*1)." }, { "name": "Literature on prey(YPD)", "description": "The number of articles concerning Prey, obtained from YPD." }, { "name": "Literature shared by bait and prey", "description": "The number of articles common to Bait and Prey, as calculated on the basis of the number of articles obtained from the YPD." }, { "name": "Literature sharing score", "description": "The score concerning co-occurrence of Prey and Bait in the literature, calculated by the calculation formula.\r\nCalculation formula for the score:\r\nhttps:\/\/dbarchive.biosciencedbc.jp\/images\/db_meta\/yeast_y2h\/literature_sharing_score.png" }, { "name": "CuraGen(0 or 1)", "description": "Investigation by CuraGen (0 or 1), obtained from Uetz et al.(*2)" }, { "name": "S. Fields(0 or 1)", "description": "Investigation by S. Fields (0 or 1), obtained from Uetz et al." }, { "name": "Association(0 or 1,YPD)", "description": "Association (0 or 1), obtained from the YPD." }, { "name": "Complex (0 or 1,YPD)", "description": "Formation of complex (0 or 1), obtained from the YPD." }, { "name": "Synthetic lethality(0 or 1,YPD)", "description": "Synthetic lethality (0 or 1), obtained from the YPD." }, { "name": "Co-induced by(YPD)", "description": "Factor that induces expression of both genes, obtained from the YPD." }, { "name": "Co-repressed by(YPD)", "description": "Factor that suppresses expression of both genes, obtained from the YPD." }, { "name": "Not affected by(YPD)", "description": "Factor that does not affect expression of these genes, obtained from the YPD." }, { "name": "Interologs", "description": "The number of interactions that exist between the interacting protein and the ortholog of other species, obtained from the Database of Interacting Proteins(*3)." }, { "name": "Expression similarity (BRITE)", "description": "Expression data obtained from KEGG BRITE(*4). (High values only, 0.9 or greater)" }, { "name": "Alternative path with 1 intervening protein", "description": "The number of paths other than this interaction mediated by one intermediate protein, calculated from the full data." }, { "name": "Alternative path with 2 intervening proteins", "description": "The number of paths other than this interaction mediated by two intermediate proteins, calculated from the full data." }, { "name": "IST hit", "description": "Number of hits of Interaction Sequence Tags (IST) (The number of detected interactions and the indicator of reproducibility)" }, { "name": "IST hit in the opposite bait\/prey orientation", "description": "The IST hit number for a combination in which Bait and Prey are in the reverse direction." } ] }, { "path": "en\/yeast-y2h\/data-3.html", "name": "Core Data of Yeast Interacting Proteins Database (Original Version)", "database_name": "Yeast Interacting Proteins Database", "doi": "10.18908\/lsdba.nbdc00742-003", "description": "Highly reproducible interaction data in the Yeast Interacting Proteins Database with the \"IST hit\" (to be described in the table below) of 3 or more. The gene information (gene name and description) is the data at the time the paper(*1) was published. The number of data is 841. The data are given in a CSV format text file.", "files": [ { "file_name": "ore_original.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_y2h\/LATEST\/core_original.zip", "file_size": "37KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/yipd_core#en", "data_acquisition": "", "analysis": "", "data_number": "", "details": [ { "name": "Bait ORF", "description": "The ORF name of Bait, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/)." }, { "name": "Bait gene name", "description": "The gene name of Bait, and the standard name in the SGD." }, { "name": "Bait description", "description": "The annotation of Bait, and description in the SGD." }, { "name": "Rows with this bait as bait", "description": "The number of rows (interactions) having this Bait ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this bait as prey", "description": "The number of rows (interactions) having this Bait ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Prey ORF", "description": "The ORF name of Prey, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org)." }, { "name": "Prey gene name", "description": "The gene name of Prey, and the standard name in the SGD." }, { "name": "Prey description", "description": "The annotation of Prey, and description in the SGD." }, { "name": "Rows with this prey as prey", "description": "The number of rows (interactions) having this Prey ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this prey as bait", "description": "The number of rows (interactions) having this Prey ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Literature on bait(YPD)", "description": "The number of articles concerning Bait, obtained from YPD (Yeast Proteome Database)(*2)." }, { "name": "Literature on prey(YPD)", "description": "The number of articles concerning Prey, obtained from YPD." }, { "name": "Literature shared by bait and prey", "description": "The number of articles common to Bait and Prey, as calculated on the basis of the number of articles obtained from the YPD." }, { "name": "Literature sharing score", "description": "The score concerning co-occurrence of Prey and Bait in the literature, calculated by the calculation formula.\r\nCalculation formula for the score:\r\nhttps:\/\/dbarchive.biosciencedbc.jp\/images\/db_meta\/yeast_y2h\/literature_sharing_score.png" }, { "name": "CuraGen(0 or 1)", "description": "Investigation by CuraGen (0 or 1), obtained from Uetz et al.(*3)" }, { "name": "S. Fields(0 or 1)", "description": "Investigation by S. Fields (0 or 1), obtained from Uetz et al." }, { "name": "Association(0 or 1,YPD)", "description": "Association (0 or 1), obtained from the YPD." }, { "name": "Complex (0 or 1,YPD)", "description": "Formation of complex (0 or 1), obtained from the YPD." }, { "name": "Synthetic lethality(0 or 1,YPD)", "description": "Synthetic lethality (0 or 1), obtained from the YPD." }, { "name": "Co-induced by(YPD)", "description": "Factor that induces expression of both genes, obtained from the YPD." }, { "name": "Co-repressed by(YPD)", "description": "Factor that suppresses expression of both genes, obtained from the YPD." }, { "name": "Not affected by(YPD)", "description": "Factor that does not affect expression of these genes, obtained from the YPD." }, { "name": "Interologs", "description": "The number of interactions that exist between the interacting protein and the ortholog of other species, obtained from the Database of Interacting Proteins(*4)." }, { "name": "Expression similarity (BRITE)", "description": "Expression data obtained from KEGG BRITE(*5). (High values only, 0.9 or greater)" }, { "name": "Alternative path with 1 intervening protein", "description": "The number of paths other than this interaction mediated by one intermediate protein, calculated from the full data." }, { "name": "Alternative path with 2 intervening proteins", "description": "The number of paths other than this interaction mediated by two intermediate proteins, calculated from the full data." }, { "name": "IST hit", "description": "Number of hits of Interaction Sequence Tags (IST) (The number of detected interactions and the indicator of reproducibility)" }, { "name": "IST hit in the opposite bait\/prey orientation", "description": "The IST hit number for a combination in which Bait and Prey are in the reverse direction." } ] }, { "path": "en\/yeast-y2h\/data-4.html", "name": "Full Data of Yeast Interacting Proteins Database (Original Version)", "database_name": "Yeast Interacting Proteins Database", "doi": "10.18908\/lsdba.nbdc00742-004", "description": "The entire data in the Yeast Interacting Proteins Database. The gene information (gene name and description) is the data at the time the paper(*1) was published. The number of data is 841. The data are given in a CSV format text file.", "files": [ { "file_name": "ore_original.zip", "file_url": "ftp:\/\/ftp.biosciencedbc.jp\/archive\/yeast_y2h\/LATEST\/core_original.zip", "file_size": "37KB" } ], "togodb_url": "http:\/\/togodb.biosciencedbc.jp\/togodb\/view\/yipd_full#en", "data_acquisition": "Yeast two-hybrid method. (Fields, S. & Song, O. K. (1989) Nature (London) 340, 245-246.)", "analysis": "As the indicator of reliability of the interactions obtained by the experiment, the literature information described about the yeast proteins and their interactions are required. Several sources including YPD (Yeast Proteome Database, Costanzo, M. C., Hogan, J. D., Cusick, M. E., Davis, B. P., Fancher, A. M., Hodges, P. E., Kondu, P., Lengieza, C., Lew-Smith, J. E., Lingner, C., et al. (2000) Nucleic Acids Res. 28, 73-76.) are used for literature collection.", "data_number": "", "details": [ { "name": "Bait ORF", "description": "The ORF name of Bait, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org\/)." }, { "name": "Bait gene name", "description": "The gene name of Bait, and the standard name in the SGD." }, { "name": "Bait description", "description": "The annotation of Bait, and description in the SGD." }, { "name": "Rows with this bait as bait", "description": "The number of rows (interactions) having this Bait ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this bait as prey", "description": "The number of rows (interactions) having this Bait ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Prey ORF", "description": "The ORF name of Prey, and the systematic name in the SGD (Saccharomyces Genome Database;http:\/\/www.yeastgenome.org)." }, { "name": "Prey gene name", "description": "The gene name of Prey, and the standard name in the SGD." }, { "name": "Prey description", "description": "The annotation of Prey, and description in the SGD." }, { "name": "Rows with this prey as prey", "description": "The number of rows (interactions) having this Prey ORF as the Prey ORF, and the link to the search results (for TogoDB only)." }, { "name": "Rows with this prey as bait", "description": "The number of rows (interactions) having this Prey ORF as the Bait ORF, and the link to the search results (for TogoDB only)." }, { "name": "Literature on bait(YPD)", "description": "The number of articles concerning Bait, obtained from YPD (Yeast Proteome Database)(*2)." }, { "name": "Literature on prey(YPD)", "description": "The number of articles concerning Prey, obtained from YPD." }, { "name": "Literature shared by bait and prey", "description": "The number of articles common to Bait and Prey, as calculated on the basis of the number of articles obtained from the YPD." }, { "name": "Literature sharing score", "description": "The score concerning co-occurrence of Prey and Bait in the literature, calculated by the calculation formula.\r\nCalculation formula for the score:\r\nhttps:\/\/dbarchive.biosciencedbc.jp\/images\/db_meta\/yeast_y2h\/literature_sharing_score.png" }, { "name": "CuraGen(0 or 1)", "description": "Investigation by CuraGen (0 or 1), obtained from Uetz et al.(*3)" }, { "name": "S. Fields(0 or 1)", "description": "Investigation by S. Fields (0 or 1), obtained from Uetz et al." }, { "name": "Association(0 or 1,YPD)", "description": "Association (0 or 1), obtained from the YPD." }, { "name": "Complex (0 or 1,YPD)", "description": "Formation of complex (0 or 1), obtained from the YPD." }, { "name": "Synthetic lethality(0 or 1,YPD)", "description": "Synthetic lethality (0 or 1), obtained from the YPD." }, { "name": "Co-induced by(YPD)", "description": "Factor that induces expression of both genes, obtained from the YPD." }, { "name": "Co-repressed by(YPD)", "description": "Factor that suppresses expression of both genes, obtained from the YPD." }, { "name": "Not affected by(YPD)", "description": "Factor that does not affect expression of these genes, obtained from the YPD." }, { "name": "Interologs", "description": "The number of interactions that exist between the interacting protein and the ortholog of other species, obtained from the Database of Interacting Proteins(*4)." }, { "name": "Expression similarity (BRITE)", "description": "Expression data obtained from KEGG BRITE(*5). (High values only, 0.9 or greater)" }, { "name": "Alternative path with 1 intervening protein", "description": "The number of paths other than this interaction mediated by one intermediate protein, calculated from the full data." }, { "name": "Alternative path with 2 intervening proteins", "description": "The number of paths other than this interaction mediated by two intermediate proteins, calculated from the full data." }, { "name": "IST hit", "description": "Number of hits of Interaction Sequence Tags (IST) (The number of detected interactions and the indicator of reproducibility)" }, { "name": "IST hit in the opposite bait\/prey orientation", "description": "The IST hit number for a combination in which Bait and Prey are in the reverse direction." } ] } ] }