{ "bcoid": "GLY_000758", "title": "Yeast Protein Information (NCBI RefSeq)", "description": "The Yeast Protein Information (NCBI RefSeq) dataset contains yeast [taxid:559292] protein information ...", "filename": "yeast_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": [ "Saccharomyces cerevisiae S288C" ], "molecule": [ "Protein" ], "tag": [ "Protein Information" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P0CE93-1...", "NP_009332..." ], [ "Q8TGK6-1...", "NP_878038..." ] ], "headers": [ "uniprotkb_ca...", "p_refseq_ac_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "p_refseq_ac_best_match" }, { "type": "string", "label": "refseq_protein_name" }, { "type": "string", "label": "refseq_protein_length" }, { "type": "string", "label": "refseq_protein_summary" } ], [ "P0CE93-1", "NP_009332", "seripauperin PAU8", "120", "" ], [ "Q8TGK6-1", "NP_878038", "uncharacterized protein", "75", "" ], [ "P39709-1", "NP_009333", "putative permease SEO1", "593", "" ], [ "O13511-1", "NP_009335", "uncharacterized protein", "128", "" ], [ "O13512-1", "NP_009336", "uncharacterized protein", "126", "" ], [ "Q6B2U8-1", "NP_058136", "Tda8p", "126", "" ], [ "P39711-1", "NP_009337", "uncharacterized protein", "94", "" ], [ "Q3E791-1", "NP_878039", "uncharacterized protein", "96", "" ], [ "P39712-1", "NP_009338", "flocculin FLO9", "1322", "" ], [ "P39708-1", "NP_009339", "glutamate dehydrogenase (NADP(+)) GDH3", "457", "" ], [ "P39713-1", "NP_009340", "putative dehydrogenase BDH2", "417", "" ], [ "P39714-1", "NP_009341", "(R,R)-butanediol dehydrogenase", "382", "" ], [ "P39715-1", "NP_009342", "Ecm1p", "212", "" ], [ "P27825-1", "NP_009343", "calnexin", "502", "" ], [ "P39717-1", "NP_009345", "Gpb2p", "880", "" ], [ "P39718-1", "NP_009346", "ubiquitin-protein transferase activating protein PEX22", "180", "" ], [ "Q01574-1", "NP_009347", "acetate--CoA ligase 1", "713", "" ], [ "P39719-1", "NP_009348", "flavin adenine dinucleotide transporter FLC2", "783", "" ], [ "P39720-1", "NP_009349", "oleate-activated transcription factor OAF1", "1047", "" ], [ "P39721-1", "NP_009350", "protein AIM2", "246", "" ], [ "P39722-1", "NP_009351", "ERMES complex Ca(2+)-binding regulatory GTPase GEM1", "662", "" ], [ "P39723-1", "NP_009352", "gamma-tubulin complex subunit SPC72", "622", "" ], [ "P39724-1", "NP_009353", "Bol3p", "118", "" ], [ "Q3E793-1", "NP_075206", "Bol1p", "110", "" ], [ "P39726-1", "NP_009355", "glycine decarboxylase subunit H", "170", "" ], [ "Q01329-1", "NP_009356", "RNA-processing protein PTA1", "785", "" ], [ "P39727-1", "NP_009358", "Erv46p", "415", "" ], [ "P11433-1", "NP_009359", "Rho family guanine nucleotide exchange factor CDC24", "854", "" ], [ "P13365-1", "NP_009360", "cyclin CLN3", "580", "" ], [ "P06182-1", "NP_009361", "holocytochrome c synthase CYC3", "269", "" ], [ "P00549-1", "NP_009362", "pyruvate kinase CDC19", "500", "" ], [ "Q3E741-1", "NP_878040", "uncharacterized protein", "30", "" ], [ "P39728-1", "NP_009363", "uncharacterized protein", "267", "" ], [ "P39729-1", "NP_009364", "GTP-binding protein RBG1", "369", "" ], [ "P39730-1", "NP_009365", "translation initiation factor eIF5B", "1002", "" ], [ "P39731-1", "NP_009367", "MIND complex subunit MTW1", "289", "" ], [ "P28003-1", "NP_009368", "Fun19p", "413", "" ], [ "P28005-1", "NP_009369", "RNA-binding protein POP5", "173", "" ], [ "P28004-1", "NP_009370", "mRNA splicing protein PRP45", "379", "" ], [ "P39732-1", "NP_009371", "protein phosphatase regulator GIP4", "760", "" ], [ "P31109-1", "NP_009372", "SNAP receptor SNC1", "117", "" ], [ "P32492-1", "NP_009373", "myosin 4", "1471", "" ], [ "P39734-1", "NP_009374", "Frt2p", "528", "" ], [ "P39735-1", "NP_009375", "DNA-binding protein SAW1", "261", "" ], [ "P39524-1", "NP_009376", "aminophospholipid-translocating P4-type ATPase DRS2", "1355", "" ], [ "P10962-1", "NP_009377", "ribosome biosynthesis protein MAK16", "306", "" ], [ "P07866-1", "NP_009378", "mitotic regulator LTE1", "1435", "" ], [ "P31382-1", "NP_009379", "dolichyl-phosphate-mannose-protein mannosyltransferase PMT2", "759", "" ], [ "P31381-1", "NP_009380", "nucleoside transmembrane transporter FUN26", "517", "" ], [ "P31384-1", "NP_009381", "CCR4-NOT core exoribonuclease subunit CCR4", "837", "" ], [ "P31386-1", "NP_009382", "Ats1p", "333", "" ], [ "P31380-1", "NP_009383", "DNA-dependent ATPase FUN30", "1131", "" ], [ "P31379-1", "NP_009384", "Lds1p", "325", "" ], [ "P31374-1", "NP_009385", "serine/threonine protein kinase PSK1", "1356", "" ], [ "P31383-1", "NP_009386", "protein phosphatase 2A structural subunit TPD3", "635", "" ], [ "P31378-1", "NP_009387", "bifunctional N-glycosylase/AP lyase NTG1", "399", "" ], [ "P31377-1", "NP_009388", "syntaxin", "255", "" ], [ "P31385-1", "NP_009389", "Rpd3L histone deacetylase complex subunit DEP1", "405", "" ], [ "P31373-1", "NP_009390", "cystathionine gamma-lyase CYS3", "394", "" ], [ "P31376-1", "NP_009391", "Swc3p", "625", "" ], [ "P18409-1", "NP_009392", "Mdm10p", "493", "" ], [ "P18410-1", "NP_009393", "Nem1-Spo7 phosphatase regulatory subunit SPO7", "259", "" ], [ "P18411-1", "NP_009394", "Fun14p", "198", "" ], [ "P39704-1", "NP_009395", "Erp2p", "215", "" ], [ "P10591-1", "NP_009396", "Hsp70 family ATPase SSA1", "642", "" ], [ "P32471-1", "NP_009398", "translation elongation factor 1 subunit beta", "206", "" ], [ "P39702-1", "NP_009399", "CORVET complex membrane-binding subunit VPS8", "1274", "" ], [ "P34111-1", "NP_009400", "transcription factor TFIIIC subunit TFC3", "1160", "" ], [ "P39705-1", "NP_009401", "FG-nucleoporin NUP60", "539", "" ], [ "Q05359-1", "NP_009402", "Erp1p", "219", "" ], [ "P39706-1", "NP_009403", "COMPASS subunit protein SWD1", "426", "" ], [ "P22336-1", "NP_009404", "replication factor A subunit protein RFA1", "621", "" ], [ "P39707-1", "NP_009405", "tRNA splicing endonuclease subunit SEN34", "275", "" ], [ "O13527-1", "NP_009406", "truncated gag-pol fusion protein", "1196", "" ], [ "P0CX58-1", "NP_009407", "gag protein", "440", "" ], [ "P27637-1", "NP_009408", "protein phosphatase regulator BUD14", "709", "" ], [ "P27616-1", "NP_009409", "phosphoribosylaminoimidazolesuccinocarboxamide synthase", "306", "" ], [ "P22209-1", "NP_009410", "serine/threonine protein kinase KIN3", "435", "" ], [ "P27636-1", "NP_009411", "serine/threonine protein kinase CDC15", "974", "" ], [ "P39545-1", "NP_009412", "seripauperin PAU7", "55", "" ], [ "D6VPM8-1", "NP_009413", "DUP240 family protein", "179", "" ], [ "P39547-1", "NP_009414", "DUP240 family protein UIP3", "235", "" ], [ "P39548-1", "NP_009415", "DUP240 family protein", "234", "" ], [ "P39549-1", "NP_009416", "DUP240 family protein", "74", "" ] ] }, "readme": "Name\n - Yeast Protein Information (NCBI RefSeq)\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2022-08-30T16:17:01.573604\n\nModified on\n - 2023-09-11T19:08:41\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - \n\nChecksum\n - \n\nUsability Domain\n - The Yeast Protein Information (NCBI RefSeq) dataset contains yeast [taxid:559292] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen\n\nDescription Domain\n Keywords\n - protein information\n - protein length\n - NCBI RefSeq\n - protein summary\n\n Pipeline Steps\n - Step-1: The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: yeast_protein_xref_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_xref_refseq.csv\n Name: refseq_protein_all_559292.gpff\n URI: https:/data.glygen.org/ln2downloads/ncbi/refseq/2023_10_12/refseq_protein_all_559292.gpff\n Output Subdomain\n Name: yeast_protein_info_refseq.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_refseq.csv\n Name: yeast_protein_info_refseq.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_info_refseq.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"5846\"\n Name: \"p_refseq_ac_best_match\"\n Description: \"Best match NCBI RefSeq protein accession to UniProtKB canonical accession\"\n Unique Values: \"5846\"\n Name: \"refseq_protein_name\"\n Description: \"Name of the protein in NCBI RefSeq database\"\n Unique Values: \"5074\"\n Name: \"refseq_protein_length\"\n Description: \"Length of the protein in NCBI RefSeq database\"\n Unique Values: \"1293\"\n Name: \"refseq_protein_summary\"\n Description: \"Function of the protein in NCBI RefSeq database\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/yeast_protein_info_refseq.csv" }