{ "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", "tags": "Gene Coordinates", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D3ZB44-1...", "Zfp324..." ], [ "Q64627-1...", "Neu2..." ] ], "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", "65606520", "65611815", "0" ], [ "Q64627-1", "Neu2", "ENSRNOG00000016962", "9", "94702129", "94724902", "1" ], [ "D3ZB48-1", "Hook1", "ENSRNOG00000026226", "5", "114940053", "115000691", "1" ], [ "A0A0G2JVG5-1", "LOC102552378", "ENSRNOG00000030948", "12", "50211981", "50213400", "0" ], [ "P30938-1", "Sstr5", "ENSRNOG00000018834", "10", "14847749", "14853827", "0" ], [ "A0A0G2JVG8-1", "Olr410", "ENSRNOG00000048499", "3", "16318429", "16319367", "1" ], [ "A0A096MJY8-1", "Acat2l1", "ENSRNOG00000013975", "1", "47996521", "48026268", "1" ], [ "A0A096MJY4-1", "Mef2c", "ENSRNOG00000033134", "2", "11658568", "11822787", "1" ], [ "A0A096MJY1-1", "Gpc6", "ENSRNOG00000046660", "15", "102164751", "103170847", "1" ], [ "A0A096MJY2-1", "Stoml3", "ENSRNOG00000011006", "2", "142717281", "142735410", "1" ], [ "F7ES73-1", "Nub1", "ENSRNOG00000009282", "4", "6951478", "6978073", "0" ], [ "P30937-1", "Sstr4", "ENSRNOG00000004641", "3", "142739781", "142741644", "1" ], [ "O35152-1", "Bet1l", "ENSRNOG00000013165", "1", "213602850", "213605643", "0" ], [ "P30936-1", "Sstr3", "ENSRNOG00000007332", "7", "119760888", "119768082", "0" ], [ "O35158-1", "Cdon", "ENSRNOG00000011789", "8", "36625733", "36710949", "1" ], [ "Q9QYH1-1", "Mpp4", "ENSRNOG00000010486", "9", "65917917", "65957101", "0" ], [ "P02764-1", "Orm1", "ENSRNOG00000007886", "5", "79179417", "79182820", "1" ], [ "P02767-1", "Ttr", "ENSRNOG00000016275", "18", "15532963", "15540177", "0" ], [ "D4A4W8-1", "Tbxt", "ENSRNOG00000012229", "1", "52887067", "52894832", "0" ], [ "D4A4W0-1", "Olr338", "ENSRNOG00000048005", "1", "229107911", "229108849", "1" ], [ "D4A4W1-1", "Fam174b", "ENSRNOG00000012369", "1", "135083974", "135162685", "1" ], [ "D4A4W2-1", "Slc47a2", "ENSRNOG00000038055", "10", "47588497", "47630799", "0" ], [ "F7EN52-1", "Cyp46a1", "ENSRNOG00000007147", "6", "132242328", "132273787", "1" ], [ "D4A4W4-1", "Ephx3", "ENSRNOG00000027319", "7", "14212470", "14217778", "0" ], [ "D4A4W5-1", "Atp10b", "ENSRNOG00000003781", "10", "28449335", "28864255", "1" ], [ "D4A4W6-1", "Slirp", "ENSRNOG00000012314", "6", "111476768", "111486039", "1" ], [ "D4A4W7-1", "Mgarp", "ENSRNOG00000011923", "2", "140444965", "140453107", "0" ], [ "G3V6I3-1", "Cwc25", "ENSRNOG00000004091", "10", "85684898", "85709568", "0" ], [ "G3V6I6-1", "Adipor1", "ENSRNOG00000004143", "13", "51240911", "51260228", "1" ], [ "G3V6I4-1", "Marc1", "ENSRNOG00000004101", "13", "102698546", "102721218", "0" ], [ "P39020-1", "Meox2", "ENSRNOG00000006588", "6", "56625650", "56689238", "1" ], [ "Q0HA29-1", "Nmnat2", "ENSRNOG00000027697", "13", "70379346", "70559458", "1" ], [ "A0A0G2K0T8-1", "Fam25a", "ENSRNOG00000055025", "16", "10702263", "10706073", "0" ], [ "A0A0G2K0T7-1", "Zfp35", "ENSRNOG00000049137", "18", "15883182", "15898821", "1" ], [ "P01237-1", "Prl", "ENSRNOG00000017374", "17", "39814244", "39824299", "0" ], [ "Q4KLI1-1", "Zkscan1", "ENSRNOG00000001335", "12", "19231092", "19247387", "1" ], [ "P01230-1", "Lhb", "ENSRNOG00000047040", "1", "101410019", "101413724", "1" ], [ "M0RB72-1", "Prr15l", "ENSRNOG00000049162", "10", "84871680", "84871982", "1" ], [ "M0RB75-1", "Kdm4b", "ENSRNOG00000049221", "9", "10653216", "10734073", "0" ], [ "A0A0G2K1A9-1", "Nol11", "ENSRNOG00000052934", "10", "95388888", "95407997", "0" ], [ "Q9JHY8-1", "Lig1", "ENSRNOG00000014193", "1", "75356220", "75394758", "1" ], [ "Q9JHY1-1", "F11r", "ENSRNOG00000004414", "13", "89826254", "89850612", "1" ], [ "Q9JHY2-1", "Sfxn3", "ENSRNOG00000015442", "1", "264796812", "264805157", "1" ], [ "Q9JHY7-1", "Birc5", "ENSRNOG00000050819", "10", "106856097", "106864413", "1" ], [ "Q9EQZ1-1", "Tsc22d3", "ENSRNOG00000056135", "X", "111884295", "111887906", "0" ], [ "F1MAA4-1", "Atp13a2", "ENSRNOG00000008052", "5", "159512285", "159531637", "1" ], [ "Q02874-1", "H2afy", "ENSRNOG00000011523", "17", "9282675", "9344678", "1" ], [ "F1MAA5-1", "Rangap1", "ENSRNOG00000031789", "7", "122940376", "122967178", "0" ], [ "Q05474-1", "Fau", "ENSRNOG00000046393", "6", "86921721", "86922122", "1" ], [ "Q99JD4-1", "Clasp2", "ENSRNOG00000009161", "8", "122003916", "122185495", "1" ], [ "Q99JD1-1", "Defb22", "ENSRNOG00000007525", "3", "147961818", "147966097", "0" ], [ "Q99JD3-1", "Slc25a21", "ENSRNOG00000008931", "6", "77624385", "77848434", "0" ], [ "Q99JD2-1", "Tekt1", "ENSRNOG00000014973", "10", "58895674", "58924137", "0" ], [ "F1MAA7-1", "Lamc1", "ENSRNOG00000002680", "13", "70658707", "70783515", "0" ], [ "Q02294-1", "Cacna1b", "ENSRNOG00000004560", "3", "1740024", "1924827", "0" ], [ "M0R8G5-1", "Igip", "ENSRNOG00000049067", "18", "29124428", "29124589", "1" ], [ "Q02293-1", "Fntb", "ENSRNOG00000007660", "6", "99883959", "99966988", "1" ], [ "M0R8G9-1", "LOC100910599", "ENSRNOG00000059982", "15", "35571103", "35572047", "1" ], [ "D3ZGR8-1", "Olr1442", "ENSRNOG00000031246", "10", "44527468", "44528382", "1" ], [ "D3ZGR6-1", "Ccdc138", "ENSRNOG00000028581", "20", "28078500", "28157071", "1" ], [ "D3ZGR7-1", "Trir", "ENSRNOG00000003863", "19", "26142720", "26146136", "1" ], [ "D3ZGR5-1", "LOC100910483", "ENSRNOG00000048545", "9", "113814537", "113846053", "0" ], [ "F1MAA2-1", "Cops7a", "ENSRNOG00000016778", "4", "157479549", "157486914", "0" ], [ "Q8K5E0-1", "Lpar3", "ENSRNOG00000015260", "2", "252090669", "252159903", "1" ], [ "Q460M5-1", "Lrfn2", "ENSRNOG00000011803", "9", "13845757", "13877130", "0" ], [ "Q9R1N3-1", "Slc4a7", "ENSRNOG00000005957", "15", "11836286", "11912916", "0" ], [ "F1MAA3-1", "Ppp2r5d", "ENSRNOG00000016849", "9", "16586803", "16609631", "1" ], [ "D3ZIY3-1", "Ythdf3", "ENSRNOG00000010084", "2", "100677411", "100710417", "1" ], [ "D3ZSP1-1", "Snrpe", "ENSRNOG00000031127", "8", "129371556", "129371973", "0" ], [ "D3ZSP2-1", "LOC100912013", "ENSRNOG00000015527", "1", "74155828", "74181323", "0" ], [ "D3ZSP7-1", "Ttc3", "ENSRNOG00000001682", "11", "34598492", "34738791", "1" ], [ "P48550-1", "Kcnj6", "ENSRNOG00000001658", "11", "35024196", "35099383", "0" ], [ "D3ZFP5-1", "LOC691352", "ENSRNOG00000038422", "10", "44238354", "44243402", "0" ], [ "D3ZFP4-1", "Mcm3", "ENSRNOG00000012543", "9", "26914057", "26932201", "0" ], [ "D3ZFP7-1", "Insc", "ENSRNOG00000024712", "1", "184299250", "184407480", "1" ], [ "D3ZFP6-1", "Ticrr", "ENSRNOG00000015520", "1", "141391262", "141433109", "1" ], [ "D3ZYL2-1", "Kiaa0408L", "ENSRNOG00000042309", "1", "31040142", "31055453", "0" ], [ "D3ZYL3-1", "Vom2r8", "ENSRNOG00000017648", "AABR07024031.1", "18673", "58717", "0" ], [ "D3ZYL0-1", "Ripk1", "ENSRNOG00000017787", "17", "31537591", "31569904", "0" ], [ "Q6B4M5-1", "Pard6a", "ENSRNOG00000017746", "19", "37668133", "37672729", "1" ], [ "D4A131-1", "Mrpl4", "ENSRNOG00000020659", "8", "22021213", "22027228", "1" ], [ "D4A130-1", "Olr1388", "ENSRNOG00000046425", "10", "34564009", "34564944", "1" ], [ "D4A133-1", "Atp6v1a", "ENSRNOG00000001992", "11", "61531416", "61584634", "1" ], [ "D4A135-1", "Gramd1c", "ENSRNOG00000053406", "11", "61605937", "62634803", "1" ] ] }, "readme": "Name\n - Rat Gene Locus (Ensembl)\n\nVersion\n - 1.5.27\n\nCreated on\n - 2019-09-06T14:06:38.993695\n\nModified on\n - 2020-04-10T12:08:06.119863\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/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: uniprot-proteome-rattus-norvegicus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_genelocus.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/rat_protein_genelocus.csv\n Name: rat_protein_genelocus.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/rat_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"18762\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"80\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"18696\"\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: \"18696\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"18690\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"18695\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/rat_protein_genelocus.csv" }