{ "bcoid": "GLY_000082", "title": "Mouse Gene Locus (Ensembl)", "description": "The Mouse Gene Locus dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the ...", "filename": "mouse_protein_genelocus.csv", "filetype": "csv", "categories": { "species": [ "Mus musculus" ], "molecule": [ "Protein" ], "tag": [ "Gene Coordinates" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q8BH24-1...", "Tm9sf4..." ], [ "Q8BH27-1...", "Megf9..." ] ], "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" } ], [ "Q8BH24-1", "Tm9sf4", "ENSMUSG00000068040", "2", "153003223", "153052386", "0" ], [ "Q8BH27-1", "Megf9", "ENSMUSG00000039270", "4", "70345302", "70453232", "1" ], [ "Q8BH26-1", "Lyset", "ENSMUSG00000046675", "12", "102710021", "102713820", "0" ], [ "Q8VF69-1", "Or2aa1", "ENSMUSG00000048919", "11", "59479323", "59484115", "1" ], [ "Q9JHR7-1", "Ide", "ENSMUSG00000056999", "19", "37246142", "37340010", "1" ], [ "Q8VF63-1", "Or8b35", "ENSMUSG00000060583", "9", "37903121", "37907704", "0" ], [ "Q8VF66-1", "Or5p50", "ENSMUSG00000095910", "7", "107419773", "107424748", "1" ], [ "Q8VF65-1", "Or5p51", "ENSMUSG00000109542", "7", "107442112", "107446697", "1" ], [ "Q8VF64-1", "Or8b36", "ENSMUSG00000094461", "9", "37937104", "37938033", "0" ], [ "B2RXV4-1", "Flvcr1", "ENSMUSG00000066595", "1", "190738044", "190758355", "1" ], [ "E9Q3P4-1", "Cenpf", "ENSMUSG00000026605", "1", "189372803", "189420283", "1" ], [ "A0A087WRQ3-1", "Trav1", "ENSMUSG00000076758", "14", "52665385", "52666333", "0" ], [ "Q9CXG9-1", "Phf19", "ENSMUSG00000026873", "2", "34783769", "34804038", "1" ], [ "Q07968-1", "F13b", "ENSMUSG00000026368", "1", "139429440", "139451490", "0" ], [ "A5H0M4-1", "Poteg", "ENSMUSG00000063932", "8", "27937698", "27985200", "0" ], [ "Q9CXG3-1", "Ppil4", "ENSMUSG00000015757", "10", "7668655", "7698899", "0" ], [ "B1AQ89-1", "Gm11555", "ENSMUSG00000078130", "11", "99540425", "99541062", "1" ], [ "A0A1B0GST8-1", "Gm55978", "ENSMUSG00000118272", "1", "34840875", "34841045", "0" ], [ "B1AQ87-1", "Gm14190", "ENSMUSG00000078276", "11", "99581414", "99581566", "1" ], [ "B1AQ85-1", "Krtap4-2", "ENSMUSG00000044649", "11", "99524937", "99525910", "1" ], [ "A0A1B0GST0-1", "Or51f1", "ENSMUSG00000060888", "7", "102504544", "102507972", "1" ], [ "Q3UU21-1", "Zpld2", "ENSMUSG00000073747", "4", "133918115", "133930315", "1" ], [ "P03899-1", "mt-Nd3", "ENSMUSG00000064360", "Mitochondrion", "9459", "9806", "0" ], [ "O35153-1", "Bet1l", "ENSMUSG00000025484", "7", "140433307", "140437490", "1" ], [ "Q9QYH9-1", "Tnfsf14", "ENSMUSG00000005824", "17", "57496492", "57501177", "1" ], [ "P52479-1", "Usp10", "ENSMUSG00000031826", "8", "120637099", "120684299", "0" ], [ "P02762-1", "Mup6", "ENSMUSG00000078689", "4", "59964294", "60007274", "0" ], [ "Q9QYH6-1", "Maged1", "ENSMUSG00000025151", "X", "93579080", "93585749", "1" ], [ "Q3SXJ3-1", "Or4c29", "ENSMUSG00000075113", "2", "88735286", "88745501", "1" ], [ "Q08AU7-1", "Myadml2", "ENSMUSG00000025141", "11", "120536857", "120538984", "1" ], [ "Q5EBH1-1", "Rassf5", "ENSMUSG00000026430", "1", "131104147", "131172995", "1" ], [ "A0A087WSM5-1", "Gm29049", "ENSMUSG00000099861", "Y", "7994833", "7997168", "1" ], [ "Q61409-1", "Pde3b", "ENSMUSG00000030671", "7", "114014516", "114138486", "0" ], [ "A2AVK5-1", "Or4a15", "ENSMUSG00000075090", "2", "89190357", "89195209", "1" ], [ "Q80YU0-1", "Abhd16b", "ENSMUSG00000055882", "2", "181134999", "181136773", "0" ], [ "Q61400-1", "Ceacam10", "ENSMUSG00000054169", "7", "24476631", "24484082", "0" ], [ "Q61406-1", "Cfhr1", "ENSMUSG00000057037", "1", "139474791", "139488010", "1" ], [ "Q5SRT8-1", "Ccnjl", "ENSMUSG00000044707", "11", "43419611", "43477824", "0" ], [ "A0A140LIA7-1", "Gm29797", "ENSMUSG00000108976", "2", "181298827", "181301260", "0" ], [ "P70419-1", "Galnt3", "ENSMUSG00000026994", "2", "65913110", "65955338", "1" ], [ "Q9EP78-1", "Chst7", "ENSMUSG00000037347", "X", "19925799", "19963760", "0" ], [ "Q9EP79-1", "Vmn1r52", "ENSMUSG00000060816", "6", "90151790", "90158230", "0" ], [ "Q3URK3-1", "Tet1", "ENSMUSG00000047146", "10", "62640349", "62744775", "1" ], [ "Q9EP73-1", "Cd274", "ENSMUSG00000016496", "19", "29344855", "29365495", "0" ], [ "Q9EP71-1", "Rai14", "ENSMUSG00000022246", "15", "10569055", "10714710", "1" ], [ "Q9EP75-1", "Cyp4f14", "ENSMUSG00000024292", "17", "33124044", "33136316", "1" ], [ "Q3URK1-1", "Ccdc190", "ENSMUSG00000070532", "1", "169756217", "169762222", "0" ], [ "Q8BYZ1-1", "Abi3", "ENSMUSG00000018381", "11", "95720900", "95733302", "1" ], [ "S4R213-1", "Lactbl1", "ENSMUSG00000070683", "4", "136349932", "136366421", "0" ], [ "P53702-1", "Hccs", "ENSMUSG00000031352", "X", "168033189", "168103368", "1" ], [ "Q8R349-1", "Cdc16", "ENSMUSG00000038416", "8", "13807676", "13831938", "0" ], [ "Q8R344-1", "Ccdc12", "ENSMUSG00000019659", "9", "110485571", "110540674", "0" ], [ "O08911-1", "Mapk12", "ENSMUSG00000022610", "15", "89014787", "89024906", "1" ], [ "Q80WC9-1", "Aasdh", "ENSMUSG00000055923", "5", "77021506", "77053361", "1" ], [ "O08912-1", "Galnt1", "ENSMUSG00000000420", "18", "24338401", "24419875", "0" ], [ "O08915-1", "Aip", "ENSMUSG00000024847", "19", "4164446", "4175858", "1" ], [ "O08914-1", "Faah", "ENSMUSG00000034171", "4", "115824342", "115875123", "1" ], [ "O08917-1", "Flot1", "ENSMUSG00000059714", "17", "36134122", "36143683", "0" ], [ "Q80WC3-1", "Tnrc18", "ENSMUSG00000039477", "5", "142710416", "142803417", "1" ], [ "O08918-1", "Ccng2", "ENSMUSG00000029385", "5", "93415116", "93424090", "0" ], [ "Q80WC1-1", "Ubn2", "ENSMUSG00000038538", "6", "38410885", "38501760", "0" ], [ "Q80WC7-1", "Agfg2", "ENSMUSG00000029722", "5", "137648725", "137682988", "1" ], [ "Q9JHY4-1", "Wfdc15b", "ENSMUSG00000018211", "2", "164056374", "164063580", "1" ], [ "Q8R3V5-4", "Sh3glb2", "ENSMUSG00000026860", "2", "30234821", "30249349", "1" ], [ "Q91ZK4-1", "Dmbx1", "ENSMUSG00000028707", "4", "115772316", "115797123", "1" ], [ "Q91ZK0-1", "Tfap2d", "ENSMUSG00000042596", "1", "19173246", "19236570", "0" ], [ "Q6ZQ93-1", "Usp34", "ENSMUSG00000056342", "11", "23256895", "23440560", "0" ], [ "E9PVB3-1", "Ccdc175", "ENSMUSG00000021086", "12", "72148074", "72231803", "1" ], [ "Q9D4U7-1", "4930556J24Rik", "ENSMUSG00000034493", "11", "3887541", "3926778", "1" ], [ "Q9D4U4-1", "H2al3", "ENSMUSG00000048994", "X", "9715942", "9716494", "0" ], [ "A0A3Q4EGJ1-1", "Ceacam23", "ENSMUSG00000078793", "7", "17605692", "17652935", "0" ], [ "F8VQ94-1", "Pira2", "ENSMUSG00000089942", "7", "3839811", "3848050", "1" ], [ "Q811W0-1", "Sox21", "ENSMUSG00000061517", "14", "118470644", "118474442", "1" ], [ "Q811W1-1", "Aard", "ENSMUSG00000068522", "15", "51903503", "51909118", "0" ], [ "Q8BZM0-1", "Klhl12", "ENSMUSG00000026455", "1", "134383269", "134418756", "0" ], [ "Q8BZM1-1", "Glmn", "ENSMUSG00000029276", "5", "107696833", "107745754", "1" ], [ "A2BEI8-1", "Gm11757", "ENSMUSG00000096750", "4", "73805303", "73809349", "1" ], [ "A0A2I3BRZ3-1", "Klhl33", "ENSMUSG00000090799", "14", "51126039", "51134964", "1" ], [ "Q60819-1", "Il15ra", "ENSMUSG00000023206", "2", "11710101", "11739128", "0" ], [ "Q4VC33-1", "Maea", "ENSMUSG00000079562", "5", "33492853", "33530640", "0" ], [ "Q66GT5-1", "Ptpmt1", "ENSMUSG00000063235", "2", "90739060", "90748389", "1" ], [ "P50429-1", "Arsb", "ENSMUSG00000042082", "13", "93908138", "94079524", "0" ], [ "Q8BTJ4-1", "Enpp4", "ENSMUSG00000023961", "17", "44407199", "44416700", "1" ], [ "Q4G5Y1-1", "Klhdc2", "ENSMUSG00000020978", "12", "69343455", "69357461", "0" ] ] }, "readme": "Name\n - Mouse Gene Locus (Ensembl)\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2019-01-23T17:21:05.950210\n\nModified on\n - 2022-09-26T08:48:18.861939\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]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Mouse Gene Locus dataset contains mouse [taxid:10090] 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 - 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: mouse_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_masterlist.csv\n Name: uniprot-proteome-mus-musculus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-mus-musculus.nt\n Output Subdomain\n Name: mouse_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_genelocus.csv\n Name: mouse_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20965\"\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: \"20959\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"20959\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"23\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"20950\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"20917\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/mouse_protein_genelocus.csv" }