{ "bcoid": "GLY_000640", "title": "Fruitfly Gene Locus (Ensembl)", "description": "The Fruitfly Gene Locus (Ensembl) contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped ...", "filename": "fruitfly_protein_genelocus.csv", "filetype": "csv", "categories": { "species": [ "Drosophila melanogaster" ], "molecule": [ "Protein" ], "tag": [ "Gene Coordinates" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "M9PJ12-1...", "CG32778..." ], [ "P40796-1...", "La..." ] ], "headers": [ "uniprotkb_ca...", "gene_symbol..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_symbol" }, { "type": "string", "label": "ensembl_gene_id" }, { "type": "string", "label": "chromosome_id" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "strand" } ], [ "M9PJ12-1", "CG32778", "FBgn0263772", "X", "4075743", "4092237", "0" ], [ "P40796-1", "La", "FBgn0011638", "2L", "20348393", "20350012", "1" ], [ "P40797-1", "pnut", "FBgn0013726", "2R", "8237271", "8240297", "0" ], [ "P40794-1", "bnk", "FBgn0004389", "3R", "31193362", "31194389", "0" ], [ "P40795-1", "fog", "FBgn0000719", "X", "22824317", "22855194", "1" ], [ "P40792-1", "Rac1", "FBgn0010333", "3L", "1300879", "1302683", "1" ], [ "P40793-1", "Cdc42", "FBgn0010341", "X", "19697091", "19699938", "0" ], [ "P40791-1", "Mef2", "FBgn0011656", "2R", "9913496", "9958858", "1" ], [ "P40798-1", "stc", "FBgn0001978", "2L", "15113480", "15118069", "0" ], [ "P40421-1", "rdgC", "FBgn0265959", "3L", "20248080", "20265554", "0" ], [ "P40423-1", "sqh", "FBgn0003514", "X", "6223061", "6225140", "1" ], [ "P40427-1", "exd", "FBgn0000611", "X", "15992468", "15996509", "0" ], [ "A2VEV2-1", "Dmel\\CG34323", "FBgn0085352", "X", "12070437", "12071263", "0" ], [ "A2VEV0-1", "Dmel\\CG34302", "FBgn0085331", "3R", "9822999", "9823823", "1" ], [ "P08841-1", "betaTub60D", "FBgn0288686", "2R", "24305881", "24313099", "0" ], [ "Q9VE87-1", "hmw", "FBgn0038607", "3R", "18361994", "18364277", "0" ], [ "Q9VE86-1", "WRNexo", "FBgn0038608", "3R", "18364244", "18366162", "1" ], [ "Q9VE85-1", "Nup43", "FBgn0038609", "3R", "18366638", "18367913", "0" ], [ "P05389-1", "RpLP2", "FBgn0003274", "2R", "16586129", "16586732", "0" ], [ "A0A6H2EE55-1", "Dmel\\CG14431", "FBgn0029922", "X", "6908277", "6968829", "0" ], [ "A0A6F7UCJ3-1", "GH14785", "FBgn0262353", "2L", "12507939", "12508504", "0" ], [ "Q9VRR2-1", "PXo", "FBgn0035649", "3L", "5917905", "5921316", "1" ], [ "Q9VRR3-1", "CG10727", "FBgn0052407", "3L", "5922055", "5923567", "0" ], [ "Q9VRR0-1", "Dmel\\CG10486", "FBgn0035647", "3L", "5904211", "5906699", "1" ], [ "P04388-1", "Ras64B", "FBgn0003206", "3L", "4139076", "4141398", "0" ], [ "A1ZB47-1", "CG5719", "FBgn0053958", "2R", "18184382", "18192851", "1" ], [ "A1ZB42-1", "MED9", "FBgn0260401", "2R", "18167255", "18168380", "0" ], [ "A1ZB48-1", "Dmel\\CG14500", "FBgn0034318", "2R", "18188978", "18189654", "0" ], [ "A1ZB49-1", "Dmel\\CG30114", "FBgn0050114", "2R", "18207755", "18208978", "0" ], [ "Q9VLI9-1", "Trs23", "FBgn0260861", "2L", "8686231", "8687052", "0" ], [ "Q9VLI1-1", "LManIV", "FBgn0032067", "2L", "8769159", "8772344", "1" ], [ "Q9VLI0-1", "LManV", "FBgn0032068", "2L", "8772946", "8776263", "1" ], [ "Q9VLI3-1", "Dmel\\CG12438", "FBgn0032065", "2L", "8752285", "8753209", "0" ], [ "Q9VLI2-1", "LManIII", "FBgn0032066", "2L", "8765273", "8768710", "1" ], [ "Q9VLI4-1", "raw", "FBgn0003209", "2L", "8709880", "8740660", "1" ], [ "Q9VLI6-1", "CatB", "FBgn0032061", "2L", "8705572", "8707527", "0" ], [ "Q02870-1", "hay", "FBgn0001179", "3L", "10631079", "10633969", "0" ], [ "Q7JUM3-1", "PIG-A", "FBgn0034270", "2R", "17737622", "17739685", "1" ], [ "Q8SXV2-1", "Dmel\\CG31675", "FBgn0051675", "2L", "20867755", "20869650", "0" ], [ "M9PB30-1", "dpy", "FBgn0053196", "2L", "4477462", "4614300", "1" ], [ "Q8SXV4-1", "BcDNA:RH68528", "FBgn0032283", "2L", "10686124", "10687066", "1" ], [ "Q9VGW4-1", "Dmel\\CG14692", "FBgn0037836", "3R", "10794058", "10803955", "1" ], [ "Q8SXV9-1", "Dmel\\CG12998", "FBgn0030829", "X", "17218667", "17219787", "0" ], [ "Q9VGW5-1", "BcDNA:RE74890", "FBgn0037835", "3R", "10792904", "10793643", "0" ], [ "Q9VME8-1", "ppk14", "FBgn0031803", "2L", "6354956", "6356672", "0" ], [ "Q9VME9-1", "ppk7", "FBgn0031802", "2L", "6352324", "6354331", "1" ], [ "Q9VME0-1", "Dmel\\CG13982", "FBgn0031811", "2L", "6412315", "6415335", "0" ], [ "Q9VME1-1", "CG33295", "FBgn0259715", "2L", "6395853", "6397249", "1" ], [ "Q9VME2-1", "Nepl6", "FBgn0259716", "2L", "6383435", "6385512", "1" ], [ "Q9VME3-1", "Nepl5", "FBgn0031808", "2L", "6381266", "6383419", "0" ], [ "Q9VVS1-1", "Dic4", "FBgn0036808", "3L", "18696402", "18698412", "1" ], [ "Q9VVS3-1", "anon-WO0118547.731", "FBgn0036810", "3L", "18744488", "18745699", "0" ], [ "Q9VME7-1", "AAF52372", "FBgn0031804", "2L", "6357005", "6358318", "1" ], [ "A0A0B4KFC0-1", "shn", "FBgn0003396", "2R", "11159086", "11217394", "0" ], [ "A0A0B4KFC4-1", "rib", "FBgn0003254", "2R", "19270078", "19281396", "0" ], [ "Q59E14-1", "CT35363", "FBgn0053543", "2L", "1997102", "2006313", "1" ], [ "A0A0B4KFC9-1", "Dmel\\CG10073", "FBgn0034440", "2R", "19380543", "19384965", "0" ], [ "Q9VZZ7-1", "BcDNA:GH02340", "FBgn0028504", "3L", "2595842", "2599579", "1" ], [ "Q9VZZ4-1", "Pxn", "FBgn0011828", "3L", "2601455", "2630064", "1" ], [ "Q7KN74-1", "Ttc7", "FBgn0021847", "2R", "6209782", "6214122", "1" ], [ "Q7KN75-1", "Dp1", "FBgn0027835", "2R", "18412027", "18421124", "0" ], [ "Q9VWS8-1", "Dmel\\CG15042", "FBgn0030937", "X", "18526862", "18528266", "1" ], [ "Q9VWS9-1", "Dmel\\CG6481", "FBgn0030936", "X", "18521074", "18522445", "1" ], [ "Q9VWS4-1", "wgn", "FBgn0030941", "X", "18624042", "18634908", "1" ], [ "Q9VWS5-1", "Dmel\\CG15040", "FBgn0030940", "X", "18606610", "18617589", "1" ], [ "Q9VWS7-1", "Dmel\\CG15047", "FBgn0030938", "X", "18528683", "18529593", "0" ], [ "Q9VWS0-1", "Ing3", "FBgn0030945", "X", "18650718", "18653091", "1" ], [ "Q9VWS1-1", "Hou", "FBgn0030944", "X", "18649396", "18650444", "1" ], [ "Q9VWS2-1", "Nup35", "FBgn0030943", "X", "18648182", "18649489", "0" ], [ "Q9VWS3-1", "Rip11", "FBgn0027335", "X", "18635642", "18647648", "1" ], [ "G4LU05-1", "Neto", "FBgn0265416", "X", "13445903", "13527282", "0" ], [ "Q9VUR8-1", "Dmel\\CG13449", "FBgn0036520", "3L", "15610631", "15612828", "1" ], [ "P48554-1", "Rac2", "FBgn0014011", "3L", "7432762", "7435190", "1" ], [ "P48555-1", "Rala", "FBgn0015286", "X", "3704610", "3719635", "1" ], [ "Q9VZZ8-1", "BcDNA:AT01695", "FBgn0062517", "3L", "2595781", "2596998", "0" ], [ "A0A0B4JDC9-1", "Rbp", "FBgn0262483", "3R", "15374635", "15402543", "0" ], [ "Q9VBR8-1", "anon-96CDa", "FBgn0028647", "3R", "25335257", "25340088", "0" ], [ "Q9V969-1", "Gr57a", "FBgn0041240", "2R", "20685605", "20686910", "1" ], [ "Q9V968-1", "galla-1", "FBgn0034543", "2R", "20670636", "20673495", "0" ], [ "Q9VBR9-1", "Dmel\\CG10669", "FBgn0039329", "3R", "25331363", "25335243", "1" ], [ "P21663-1", "Anp", "FBgn0000094", "3R", "30209948", "30210382", "0" ], [ "Q9VE80-1", "Dmel\\CG7675", "FBgn0038610", "3R", "18378124", "18381178", "1" ], [ "P11996-1", "Lsp1beta", "FBgn0002563", "2L", "898500", "901316", "0" ], [ "P11997-1", "Lsp1gamma", "FBgn0002564", "3L", "66430", "68995", "0" ] ] }, "readme": "Name\n - Fruitfly Gene Locus (Ensembl)\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2020-04-10T11:29:22.824792\n\nModified on\n - 2022-09-26T09:08:12.732452\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Fruitfly Gene Locus (Ensembl) contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - gene coordinates\n - chromosome\n - start position\n - end position\n - Ensembl\n - strand\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset\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: fruitfly_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_masterlist.csv\n Name: uniprot-proteome-drosophila-melanogaster.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-drosophila-melanogaster.nt\n Output Subdomain\n Name: fruitfly_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_genelocus.csv\n Name: fruitfly_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"13425\"\n Name: \"gene_symbol\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\"\n Unique Values: \"13344\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"13340\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"10\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"13118\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"13124\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/fruitfly_protein_genelocus.csv" }