{ "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" ], "tags": [ "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", "153161303", "153210466", "1" ], [ "Q8BH27-1", "Megf9", "ENSMUSG00000039270", "4", "70427065", "70534995", "0" ], [ "Q9JHR7-1", "Ide", "ENSMUSG00000056999", "19", "37268743", "37337852", "0" ], [ "Q8VF66-1", "Olfr469", "ENSMUSG00000095910", "7", "107820566", "107825541", "0" ], [ "Q8VF65-1", "Olfr470", "ENSMUSG00000109542", "7", "107842905", "107847490", "0" ], [ "B2RXV4-1", "Flvcr1", "ENSMUSG00000066595", "1", "191005847", "191026158", "0" ], [ "E9Q3P4-1", "Cenpf", "ENSMUSG00000026605", "1", "189640606", "189688086", "0" ], [ "A0A087WRQ3-1", "Trav1", "ENSMUSG00000076758", "14", "52427928", "52428876", "1" ], [ "Q9CXG9-1", "Phf19", "ENSMUSG00000026873", "2", "34893757", "34914026", "0" ], [ "Q07968-1", "F13b", "ENSMUSG00000026368", "1", "139501702", "139523752", "1" ], [ "A5H0M4-1", "Poteg", "ENSMUSG00000063932", "8", "27447670", "27495172", "1" ], [ "Q9CXG3-1", "Ppil4", "ENSMUSG00000015757", "10", "7792891", "7823135", "1" ], [ "B1AQ89-1", "Gm11555", "ENSMUSG00000078130", "11", "99649599", "99650236", "0" ], [ "B1AQ87-1", "Gm14190", "ENSMUSG00000078276", "11", "99690588", "99690740", "0" ], [ "B1AQ85-1", "Krtap4-2", "ENSMUSG00000044649", "11", "99634111", "99635084", "0" ], [ "P03899-1", "mt-Nd3", "ENSMUSG00000064360", "MT", "9459", "9806", "1" ], [ "O35153-1", "Bet1l", "ENSMUSG00000025484", "7", "140853394", "140857577", "0" ], [ "Q9QYH9-1", "Tnfsf14", "ENSMUSG00000005824", "17", "57189492", "57194177", "0" ], [ "P52479-1", "Usp10", "ENSMUSG00000031826", "8", "119910360", "119957560", "1" ], [ "B1AXU1-1", "Gm6812", "ENSMUSG00000056815", "X", "68892375", "68893053", "0" ], [ "P02762-1", "Mup6", "ENSMUSG00000078689", "4", "59964294", "60007274", "1" ], [ "Q9QYH6-1", "Maged1", "ENSMUSG00000025151", "X", "94535474", "94542143", "0" ], [ "Q08AU7-1", "Myadml2", "ENSMUSG00000025141", "11", "120646031", "120648158", "0" ], [ "Q5EBH1-1", "Rassf5", "ENSMUSG00000026430", "1", "131176410", "131245258", "0" ], [ "A0A087WSM5-1", "Gm29049", "ENSMUSG00000099861", "Y", "7994833", "7997168", "0" ], [ "Q61409-1", "Pde3b", "ENSMUSG00000030671", "7", "114415281", "114539251", "1" ], [ "Q80YU0-1", "Abhd16b", "ENSMUSG00000055882", "2", "181493206", "181494980", "1" ], [ "Q61400-1", "Ceacam10", "ENSMUSG00000054169", "7", "24777206", "24784657", "1" ], [ "Q61406-1", "Cfhr1", "ENSMUSG00000057037", "1", "139547053", "139560272", "0" ], [ "Q5SRT8-1", "Ccnjl", "ENSMUSG00000044707", "11", "43528784", "43586997", "1" ], [ "A0A140LIA7-1", "Gm29797", "ENSMUSG00000108976", "2", "181657034", "181659467", "1" ], [ "P70419-1", "Galnt3", "ENSMUSG00000026994", "2", "66082766", "66124994", "0" ], [ "Q9EP78-1", "Chst7", "ENSMUSG00000037347", "X", "20059560", "20097521", "1" ], [ "Q9EP79-1", "Vmn1r52", "ENSMUSG00000060816", "6", "90174808", "90181248", "1" ], [ "Q3URK3-1", "Tet1", "ENSMUSG00000047146", "10", "62804570", "62908996", "0" ], [ "Q9EP73-1", "Cd274", "ENSMUSG00000016496", "19", "29367455", "29388095", "1" ], [ "Q9EP71-1", "Rai14", "ENSMUSG00000022246", "15", "10568969", "10714624", "0" ], [ "Q9EP75-1", "Cyp4f14", "ENSMUSG00000024292", "17", "32905070", "32917342", "0" ], [ "Q3URK1-1", "Ccdc190", "ENSMUSG00000070532", "1", "169928648", "169934653", "1" ], [ "Q8BYZ1-1", "Abi3", "ENSMUSG00000018381", "11", "95830074", "95842476", "0" ], [ "S4R213-1", "Lactbl1", "ENSMUSG00000070683", "4", "136622621", "136639110", "1" ], [ "P53702-1", "Hccs", "ENSMUSG00000031352", "X", "169250193", "169320372", "0" ], [ "Q8R349-1", "Cdc16", "ENSMUSG00000038416", "8", "13757676", "13781938", "1" ], [ "Q8R344-1", "Ccdc12", "ENSMUSG00000019659", "9", "110656503", "110711606", "1" ], [ "O08911-1", "Mapk12", "ENSMUSG00000022610", "15", "89130584", "89140703", "0" ], [ "Q80WC9-1", "Aasdh", "ENSMUSG00000055923", "5", "76873659", "76905514", "0" ], [ "O08912-1", "Galnt1", "ENSMUSG00000000420", "18", "24205344", "24286818", "1" ], [ "O08915-1", "Aip", "ENSMUSG00000024847", "19", "4114446", "4125858", "0" ], [ "O08914-1", "Faah", "ENSMUSG00000034171", "4", "115967145", "116017926", "0" ], [ "O08917-1", "Flot1", "ENSMUSG00000059714", "17", "35823230", "35832791", "1" ], [ "Q80WC3-1", "Tnrc18", "ENSMUSG00000039477", "5", "142724661", "142817662", "0" ], [ "O08918-1", "Ccng2", "ENSMUSG00000029385", "5", "93267257", "93276231", "1" ], [ "Q80WC1-1", "Ubn2", "ENSMUSG00000038538", "6", "38433950", "38524825", "1" ], [ "Q80WC7-1", "Agfg2", "ENSMUSG00000029722", "5", "137650463", "137684726", "0" ], [ "Q9JHY4-1", "Wfdc15b", "ENSMUSG00000018211", "2", "164214454", "164221660", "0" ], [ "Q8R3V5-4", "Sh3glb2", "ENSMUSG00000026860", "2", "30344809", "30359337", "0" ], [ "Q91ZK4-1", "Dmbx1", "ENSMUSG00000028707", "4", "115915119", "115939926", "0" ], [ "Q91ZK0-1", "Tfap2d", "ENSMUSG00000042596", "1", "19103022", "19166346", "1" ], [ "Q6ZQ93-1", "Usp34", "ENSMUSG00000056342", "11", "23306895", "23490560", "1" ], [ "E9PVB3-1", "Ccdc175", "ENSMUSG00000021086", "12", "72101300", "72185029", "0" ], [ "Q9D4U7-1", "4930556J24Rik", "ENSMUSG00000034493", "11", "3937541", "3976778", "0" ], [ "Q9D4U4-1", "H2al3", "ENSMUSG00000048994", "X", "9849703", "9850255", "1" ], [ "A0A3Q4EGJ1-1", "Gm5155", "ENSMUSG00000078793", "7", "17871767", "17919010", "1" ], [ "F8VQ94-1", "Pira2", "ENSMUSG00000089942", "7", "3836812", "3845051", "0" ], [ "Q811W0-1", "Sox21", "ENSMUSG00000061517", "14", "118233232", "118237030", "0" ], [ "Q811W1-1", "Aard", "ENSMUSG00000068522", "15", "52040107", "52045722", "1" ], [ "Q8BZM0-1", "Klhl12", "ENSMUSG00000026455", "1", "134455531", "134491018", "1" ], [ "Q8BZM1-1", "Glmn", "ENSMUSG00000029276", "5", "107548967", "107597888", "0" ], [ "A2BEI8-1", "Gm11757", "ENSMUSG00000096750", "4", "73887066", "73891112", "0" ], [ "A0A2I3BRZ3-1", "Klhl33", "ENSMUSG00000090799", "14", "50888582", "50897507", "0" ], [ "Q60819-1", "Il15ra", "ENSMUSG00000023206", "2", "11705290", "11734317", "1" ], [ "Q4VC33-1", "Maea", "ENSMUSG00000079562", "5", "33335509", "33373296", "1" ], [ "Q66GT5-1", "Ptpmt1", "ENSMUSG00000063235", "2", "90908716", "90918258", "0" ], [ "P50429-1", "Arsb", "ENSMUSG00000042082", "13", "93771630", "93943016", "1" ], [ "Q8BTJ4-1", "Enpp4", "ENSMUSG00000023961", "17", "44096308", "44105809", "0" ], [ "Q4G5Y1-1", "Klhdc2", "ENSMUSG00000020978", "12", "69296681", "69310687", "1" ], [ "P59708-1", "Sf3b6", "ENSMUSG00000037361", "12", "4817544", "4827659", "1" ], [ "F8VQK3-1", "Gucy1a2", "ENSMUSG00000041624", "9", "3532778", "3894736", "1" ], [ "Q9R1N9-1", "Col13a1", "ENSMUSG00000058806", "10", "61838236", "61979108", "0" ], [ "Q3V3Q4-1", "Ifi208", "ENSMUSG00000066677", "1", "173673675", "173698395", "1" ], [ "Q7M729-1", "Scn4b", "ENSMUSG00000046480", "9", "45138395", "45154152", "1" ], [ "Q3V3Q7-1", "Pacs2", "ENSMUSG00000021143", "12", "113014508", "113074401", "1" ], [ "Q7M724-1", "Tas2r106", "ENSMUSG00000057754", "6", "131677960", "131678886", "0" ], [ "Q7M725-1", "Tas2r107", "ENSMUSG00000053389", "6", "131659118", "131660149", "0" ] ] }, "readme": "Name\n - Mouse Gene Locus (Ensembl)\n\nVersion\n - v-2.1.1\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-2.1.1/reviewed/mouse_protein_masterlist.csv\n Name: Mus_musculus.GRCm38.95.gtf\n URI: /data/shared/glyds/downloads/ucsc/gtf/Mus_musculus.GRCm38.95.gtf\n Output Subdomain\n Name: mouse_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.csv\n Name: mouse_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"19330\"\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: \"19325\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"19325\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"27\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"19316\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"19285\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/mouse_protein_genelocus.csv" }