{ "bcoid": "GLY_000267", "title": "Rat Gene Locus (Ensembl)", "description": "The Rat Gene Locus (Ensembl) contains rat [taxid:10116] UniProtKB canonical accessions mapped to the ...", "filename": "rat_protein_genelocus.csv", "filetype": "csv", "categories": { "species": [ "Rattus norvegicus" ], "molecule": [ "Protein" ], "tag": [ "Gene Coordinates" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "D3ZB44-1...", "Zfp324..." ], [ "D3ZB49-1...", "Osgin2..." ] ], "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" } ], [ "D3ZB44-1", "Zfp324", "ENSRNOG00000027436", "1", "73591491", "73597894", "0" ], [ "D3ZB49-1", "Osgin2", "ENSRNOG00000009358", "5", "29500408", "29520831", "1" ], [ "D3ZB48-1", "Hook1", "ENSRNOG00000026226", "5", "110824501", "110887787", "0" ], [ "A0A0G2JVG6-1", "Zfp59", "ENSRNOG00000053366", "1", "83309355", "83330251", "1" ], [ "P30938-1", "Sstr5", "ENSRNOG00000018834", "10", "14506868", "14512946", "1" ], [ "A0A8I6A2G6-1", "LOC102551431", "ENSRNOG00000066828", "X", "60478376", "60478837", "0" ], [ "A0A096MJY4-1", "Mef2c", "ENSRNOG00000033134", "2", "13993438", "14132880", "0" ], [ "A0A096MJY7-1", "Lsm14a", "ENSRNOG00000021133", "1", "86964828", "87009276", "1" ], [ "A0A096MJY1-1", "Gpc6", "ENSRNOG00000046660", "15", "94029884", "95024006", "0" ], [ "A0A096MJY2-1", "Stoml3", "ENSRNOG00000011006", "2", "137572691", "137590681", "0" ], [ "A0A8J8XIU8-1", "Rbm39", "ENSRNOG00000019848", "3", "144663001", "144696213", "1" ], [ "P30937-1", "Sstr4", "ENSRNOG00000004641", "3", "135854826", "135856689", "0" ], [ "O35152-1", "Bet1l", "ENSRNOG00000013165", "1", "195931411", "195935040", "1" ], [ "P30936-1", "Sstr3", "ENSRNOG00000007332", "7", "110092575", "110099769", "1" ], [ "O35158-1", "Cdon", "ENSRNOG00000011789", "8", "33806183", "33859033", "0" ], [ "F7FI04-1", "Snx10", "ENSRNOG00000011944", "4", "80612669", "80676996", "0" ], [ "Q9QYH1-1", "Mpp4", "ENSRNOG00000010486", "9", "60569734", "60611797", "1" ], [ "P02764-1", "Orm1", "ENSRNOG00000007886", "5", "76772941", "76776154", "0" ], [ "P02767-1", "Ttr", "ENSRNOG00000016275", "18", "11943789", "11951008", "0" ], [ "D4A4W8-1", "Tbxt", "ENSRNOG00000012229", "1", "52298099", "52305864", "1" ], [ "D4A4W9-1", "Rpl34-ps1", "ENSRNOG00000038045", "17", "74874707", "74875153", "0" ], [ "D4A4W0-1", "Or5b95", "ENSRNOG00000063913", "1", "209748563", "209753706", "0" ], [ "D4A4W1-1", "Fam174b", "ENSRNOG00000012369", "1", "127514041", "127596128", "0" ], [ "D4A4W2-1", "Slc47a2", "ENSRNOG00000038055", "10", "45991095", "46033904", "1" ], [ "F7EN52-1", "Cyp46a1", "ENSRNOG00000007147", "6", "127243315", "127274760", "0" ], [ "D4A4W4-1", "Ephx3", "ENSRNOG00000027319", "7", "11206812", "11212122", "1" ], [ "D4A4W5-1", "Atp10b", "ENSRNOG00000003781", "10", "27408747", "27749637", "0" ], [ "D4A4W6-1", "Slirp", "ENSRNOG00000012314", "6", "107088403", "107097791", "0" ], [ "D4A4W7-1", "Mgarp", "ENSRNOG00000011923", "2", "135431283", "135439612", "1" ], [ "G3V6I6-1", "Adipor1", "ENSRNOG00000004143", "13", "45859533", "45879241", "0" ], [ "P39020-1", "Meox2", "ENSRNOG00000006588", "6", "53856758", "53917467", "0" ], [ "Q0HA29-1", "Nmnat2", "ENSRNOG00000027697", "13", "65105950", "65278484", "0" ], [ "A0A0G2K0T8-1", "Fam25a", "ENSRNOG00000055025", "16", "9680668", "9684474", "1" ], [ "A0A0G2K0T4-1", "AC105645.5", "ENSRNOG00000059654", "8", "44808140", "44808496", "1" ], [ "A0A8I6AEL0-1", "Map3k5", "ENSRNOG00000031700", "1", "14685492", "14904800", "0" ], [ "A0A096MJK8-1", "Slfn2", "ENSRNOG00000037113", "10", "67953171", "67959458", "0" ], [ "A0A8I6AEL5-1", "Arid5b", "ENSRNOG00000000635", "20", "20307731", "20487433", "0" ], [ "A0A8I6AEL4-1", "Zfp51l1", "ENSRNOG00000043341", "1", "61460443", "61474159", "0" ], [ "P01237-1", "Prl", "ENSRNOG00000017374", "17", "37860007", "37870062", "1" ], [ "A0A8I6AEL7-1", "AABR07038788.1", "ENSRNOG00000029559", "X", "56396804", "56399326", "0" ], [ "P01230-1", "Lhb", "ENSRNOG00000047040", "1", "95898267", "95901963", "0" ], [ "Q9JHY8-1", "Lig1", "ENSRNOG00000014193", "1", "74165842", "74204413", "0" ], [ "Q9JHY1-1", "F11r", "ENSRNOG00000004414", "13", "83873797", "83897402", "0" ], [ "Q9JHY2-1", "Sfxn3", "ENSRNOG00000015442", "1", "243907751", "243917073", "0" ], [ "Q9JHY7-1", "Birc5", "ENSRNOG00000050819", "10", "103073408", "103081380", "0" ], [ "Q9EQZ1-1", "Tsc22d3", "ENSRNOG00000056135", "X", "104217925", "104276861", "1" ], [ "F1MAA4-1", "Atp13a2", "ENSRNOG00000008052", "5", "153292751", "153312139", "0" ], [ "A0A8I5ZLZ6-1", "Or6c7", "ENSRNOG00000070885", "7", "5362978", "5367644", "0" ], [ "Q02874-2", "Macroh2a1", "ENSRNOG00000011523", "17", "8479372", "8542072", "0" ], [ "A0A8L2QVZ0-1", "LOC120102993", "ENSRNOG00000031506", "5", "144647541", "144648477", "0" ], [ "A0A8I6APZ4-1", "Or4k77", "ENSRNOG00000065733", "3", "98014495", "98018368", "0" ], [ "Q99JD4-1", "Clasp2", "ENSRNOG00000009161", "8", "113677284", "113858731", "0" ], [ "A0A8I6ADP7-1", "Acer3", "ENSRNOG00000036866", "1", "152504186", "152606591", "1" ], [ "Q99JD1-1", "Defb22", "ENSRNOG00000007525", "3", "140957090", "140961373", "1" ], [ "Q99JD3-1", "Slc25a21", "ENSRNOG00000008931", "6", "74203440", "74702680", "1" ], [ "Q99JD2-1", "Tekt1", "ENSRNOG00000014973", "10", "56952167", "56980572", "1" ], [ "A0A8I5Y6V4-1", "Msantd1", "ENSRNOG00000064777", "14", "75835380", "75844183", "1" ], [ "Q02294-1", "Cacna1b", "ENSRNOG00000004560", "3", "7380922", "7546091", "1" ], [ "A6IUC3-1", "Spsb1", "ENSRNOG00000017212", "5", "160358308", "160418468", "1" ], [ "A0A8I5Y1B9-1", "Zfp949", "ENSRNOG00000043223", "8", "89523115", "89550253", "0" ], [ "M0R8G9-1", "Or8g26", "ENSRNOG00000067794", "8", "39589477", "39597766", "1" ], [ "D3ZGR6-1", "Ccdc138", "ENSRNOG00000028581", "20", "26495235", "26572376", "0" ], [ "D3ZGR7-1", "Trir", "ENSRNOG00000003863", "19", "23125083", "23128510", "1" ], [ "A0A8I6ABF2-1", "Lmf1", "ENSRNOG00000000230", "10", "14597594", "14684119", "0" ], [ "A0A8I6ABF4-1", "AABR07018058.1", "ENSRNOG00000057750", "15", "31592001", "31592384", "1" ], [ "Q8K5E0-1", "Lpar3", "ENSRNOG00000064204", "2", "235149065", "235193357", "0" ], [ "Q460M5-1", "Lrfn2", "ENSRNOG00000011803", "9", "11897468", "11939931", "1" ], [ "Q9R1N3-1", "Slc4a7", "ENSRNOG00000005957", "15", "10588979", "10664781", "1" ], [ "D3ZSP7-1", "Ttc3", "ENSRNOG00000001682", "11", "33688952", "33788975", "0" ], [ "P48550-1", "Kcnj6", "ENSRNOG00000001658", "11", "34061708", "34308758", "1" ], [ "D3ZFP4-1", "Mcm3", "ENSRNOG00000012543", "9", "23219169", "23237314", "1" ], [ "D3ZFP7-1", "Insc", "ENSRNOG00000024712", "1", "168993032", "169100433", "0" ], [ "D3ZFP6-1", "Ticrr", "ENSRNOG00000015520", "1", "133597716", "133639523", "0" ], [ "D3ZYL2-1", "Kiaa0408L", "ENSRNOG00000042309", "1", "28615606", "28630309", "1" ], [ "D3ZYL0-1", "Ripk1", "ENSRNOG00000017787", "17", "30839650", "30871824", "1" ], [ "Q6B4M5-1", "Pard6a", "ENSRNOG00000017746", "19", "33589542", "33591900", "0" ], [ "D4A131-1", "Mrpl4", "ENSRNOG00000020659", "8", "19539593", "19545608", "0" ], [ "D4A138-1", "Nanos3", "ENSRNOG00000031593", "19", "23985504", "23988932", "0" ], [ "F1LWI7-1", "Ezhip", "ENSRNOG00000039305", "X", "16368962", "16372256", "1" ], [ "A6KSB3-1", "Apon", "ENSRNOG00000033466", "7", "686927", "688392", "1" ], [ "F1LWI8-1", "Cfap251", "ENSRNOG00000001342", "12", "33261476", "33293932", "1" ], [ "D3ZCS5-1", "Eme1", "ENSRNOG00000024420", "10", "79586729", "79595435", "1" ], [ "D3ZCS4-1", "Iqgap3", "ENSRNOG00000027894", "2", "173542110", "173583956", "0" ], [ "D3ZHE2-1", "Yipf7", "ENSRNOG00000002224", "14", "38571066", "38599055", "0" ] ] }, "readme": "Name\n - Rat Gene Locus (Ensembl)\n\nVersion\n - v-2.4.1\n\nCreated on\n - 2019-09-06T14:06:38.993695\n\nModified on\n - 2022-09-26T09:04:48.000439\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 Rat Gene Locus (Ensembl) contains rat [taxid:10116] 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. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - gene coordinates\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: rat_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_masterlist.csv\n Name: uniprot-proteome-rattus-norvegicus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_13/uniprot-proteome-rattus-norvegicus.nt\n Output Subdomain\n Name: rat_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_genelocus.csv\n Name: rat_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"19057\"\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: \"19039\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"19039\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"31\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"19025\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"19018\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/rat_protein_genelocus.csv" }