{ "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" ], "tags": [ "Gene Coordinates" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P40796-1...", "La..." ], [ "P40797-1...", "pnut..." ] ], "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" } ], [ "P40796-1", "La", "FBgn0011638", "2L", "20348393", "20350012", "0" ], [ "P40797-1", "pnut", "FBgn0013726", "2R", "8237271", "8240297", "1" ], [ "P40794-1", "bnk", "FBgn0004389", "3R", "31193362", "31194389", "1" ], [ "P40795-1", "fog", "FBgn0000719", "X", "22824317", "22855194", "0" ], [ "P40792-1", "Rac1", "FBgn0010333", "3L", "1300879", "1302683", "0" ], [ "P40793-1", "Cdc42", "FBgn0010341", "X", "19697091", "19699938", "1" ], [ "P40791-1", "Mef2", "FBgn0011656", "2R", "9913496", "9958858", "0" ], [ "P40798-1", "stc", "FBgn0001978", "2L", "15113480", "15118069", "1" ], [ "P40421-1", "rdgC", "FBgn0265959", "3L", "20248080", "20265554", "1" ], [ "P40423-1", "sqh", "FBgn0003514", "X", "6223061", "6225140", "0" ], [ "P40427-1", "exd", "FBgn0000611", "X", "15992468", "15996509", "1" ], [ "P08841-1", "betaTub60D", "FBgn0003888", "2R", "24305881", "24313099", "1" ], [ "Q9VE87-1", "hmw", "FBgn0038607", "3R", "18361994", "18364277", "1" ], [ "Q9VE86-1", "WRNexo", "FBgn0038608", "3R", "18364244", "18366162", "0" ], [ "Q9VE85-1", "Nup43", "FBgn0038609", "3R", "18366638", "18367913", "1" ], [ "P05389-1", "RpLP2", "FBgn0003274", "2R", "16586129", "16586732", "1" ], [ "P04388-1", "Ras64B", "FBgn0003206", "3L", "4139076", "4141398", "1" ], [ "A1ZB42-1", "MED9", "FBgn0260401", "2R", "18167255", "18168380", "1" ], [ "Q9VLI9-1", "Trs23", "FBgn0260861", "2L", "8686231", "8687052", "1" ], [ "Q9VLI1-1", "LManIV", "FBgn0032067", "2L", "8769159", "8772344", "0" ], [ "Q9VLI0-1", "LManV", "FBgn0032068", "2L", "8772946", "8776263", "0" ], [ "Q9VLI2-1", "LManIII", "FBgn0032066", "2L", "8765273", "8768710", "0" ], [ "Q9VLI4-1", "raw", "FBgn0003209", "2L", "8709880", "8740660", "0" ], [ "Q02870-1", "hay", "FBgn0001179", "3L", "10631079", "10633969", "1" ], [ "Q7JUM3-1", "PIG-A", "FBgn0034270", "2R", "17737622", "17739685", "0" ], [ "M9PB30-1", "dpy", "FBgn0053196", "2L", "4477462", "4614300", "0" ], [ "Q9VME8-1", "ppk14", "FBgn0031803", "2L", "6354956", "6356672", "1" ], [ "Q9VME9-1", "ppk7", "FBgn0031802", "2L", "6352324", "6354331", "0" ], [ "Q9VME2-1", "Nepl6", "FBgn0259716", "2L", "6383435", "6385512", "0" ], [ "Q9VME3-1", "Nepl5", "FBgn0031808", "2L", "6381266", "6383419", "1" ], [ "Q9VVS1-1", "Dic4", "FBgn0036808", "3L", "18696402", "18698412", "0" ], [ "A0A0B4KFC0-1", "shn", "FBgn0003396", "2R", "11159086", "11217394", "1" ], [ "A0A0B4KFC4-1", "rib", "FBgn0003254", "2R", "19270078", "19281396", "1" ], [ "Q9VZZ4-1", "Pxn", "FBgn0011828", "3L", "2601455", "2630064", "0" ], [ "Q7KN74-1", "Ttc7", "FBgn0021847", "2R", "6209782", "6214122", "0" ], [ "Q7KN75-1", "Dp1", "FBgn0027835", "2R", "18412027", "18421124", "1" ], [ "Q9VWS4-1", "wgn", "FBgn0030941", "X", "18624042", "18634908", "0" ], [ "Q9VWS0-1", "Ing3", "FBgn0030945", "X", "18650718", "18653091", "0" ], [ "Q9VWS2-1", "Nup35", "FBgn0030943", "X", "18648182", "18649489", "1" ], [ "Q9VWS3-1", "Rip11", "FBgn0027335", "X", "18635642", "18647648", "0" ], [ "G4LU05-1", "Neto", "FBgn0265416", "X", "13445903", "13527282", "1" ], [ "P48554-1", "Rac2", "FBgn0014011", "3L", "7432762", "7435190", "0" ], [ "P48555-1", "Rala", "FBgn0015286", "X", "3704610", "3719635", "0" ], [ "A0A0B4JDC9-1", "Rbp", "FBgn0262483", "3R", "15374635", "15402543", "1" ], [ "Q9V969-1", "Gr57a", "FBgn0041240", "2R", "20685605", "20686910", "0" ], [ "Q9V968-1", "galla-1", "FBgn0034543", "2R", "20670636", "20673495", "1" ], [ "P21663-1", "Anp", "FBgn0000094", "3R", "30209948", "30210382", "1" ], [ "P11996-1", "Lsp1beta", "FBgn0002563", "2L", "898500", "901316", "1" ], [ "P11997-1", "Lsp1gamma", "FBgn0002564", "3L", "66430", "68995", "1" ], [ "P11995-1", "Lsp1alpha", "FBgn0002562", "X", "12490291", "12492982", "1" ], [ "A1Z8T6-1", "OSCP1", "FBgn0033685", "2R", "12143191", "12144533", "0" ], [ "P03896-1", "mt:ND2", "FBgn0013680", "mitochondrion_genome", "240", "1263", "1" ], [ "M9PJN5-1", "HDAC6", "FBgn0026428", "X", "15333310", "15340360", "1" ], [ "M9PDV2-1", "Tsp5D", "FBgn0029837", "X", "6069131", "6074857", "0" ], [ "Q86BY9-1", "rig", "FBgn0250850", "2R", "20633876", "20640681", "0" ], [ "Q9NB04-1", "Patj", "FBgn0067864", "3L", "1798803", "1802184", "1" ], [ "A1Z9R1-1", "Achl", "FBgn0033936", "2R", "14420324", "14424764", "1" ], [ "A1Z9R4-1", "Oaz", "FBgn0284250", "2R", "14435899", "14465881", "1" ], [ "Q9VTC4-1", "galla-2", "FBgn0036107", "3L", "10882890", "10883573", "1" ], [ "Q9VTC8-1", "Cpr67Fb", "FBgn0036110", "3L", "10894173", "10894693", "1" ], [ "Q7JQ32-1", "Gyc76C", "FBgn0266136", "3L", "19750943", "19793569", "0" ], [ "A1ZBY3-1", "dpr1", "FBgn0040726", "2R", "20698483", "20750442", "1" ], [ "A1ZBY1-1", "Fem-1", "FBgn0034542", "2R", "20662474", "20667306", "0" ], [ "Q7KUN4-1", "obst-H", "FBgn0053983", "3L", "15528265", "15529243", "0" ], [ "A0A0B4K753-1", "hemo", "FBgn0262823", "3R", "18564264", "18565173", "0" ], [ "Q9W1G7-1", "Nap1", "FBgn0015268", "2R", "23905175", "23907294", "0" ], [ "Q9W1G0-1", "Taldo", "FBgn0023477", "2R", "23940410", "23942114", "1" ], [ "Q9VY42-1", "Tat", "FBgn0035989", "3L", "9413596", "9426758", "0" ], [ "Q9VY44-1", "mRNA-cap", "FBgn0030556", "X", "14240266", "14242822", "0" ], [ "Q9VY48-1", "mRpL38", "FBgn0030552", "X", "14226289", "14227949", "1" ], [ "Q9VCT9-1", "Usp12-46", "FBgn0039025", "3R", "22750901", "22776374", "1" ], [ "Q9VCT2-1", "Gbp3", "FBgn0039031", "3R", "22977270", "22978164", "1" ], [ "Q9VCT4-1", "klg", "FBgn0017590", "3R", "22899284", "22961731", "1" ], [ "A8JUS1-1", "inaF-D", "FBgn0260812", "X", "11724668", "11729099", "0" ], [ "P06602-1", "eve", "FBgn0000606", "2R", "9979319", "9980795", "1" ], [ "P06603-1", "alphaTub84B", "FBgn0003884", "3R", "7086599", "7088839", "1" ], [ "P06601-1", "prd", "FBgn0003145", "2L", "12082995", "12085827", "0" ], [ "P06606-1", "alphaTub67C", "FBgn0087040", "3L", "9681268", "9683370", "1" ], [ "P06607-1", "Yp3", "FBgn0004047", "X", "13759546", "13761547", "1" ], [ "P06604-1", "alphaTub85E", "FBgn0003886", "3R", "9731221", "9733250", "0" ], [ "P06605-1", "alphaTub84D", "FBgn0003885", "3R", "7530753", "7532732", "1" ], [ "P18475-1", "tor", "FBgn0003733", "2R", "7705183", "7709184", "0" ], [ "Q9VWN3-1", "SdhBL", "FBgn0030975", "X", "18894446", "18896581", "1" ], [ "A0A0B4K6G5-1", "Nha2", "FBgn0263390", "3R", "22981459", "22998528", "0" ] ] }, "readme": "Name\n - Fruitfly Gene Locus (Ensembl)\n\nVersion\n - v-2.1.1\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], 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-2.1.1/reviewed/fruitfly_protein_masterlist.csv\n Name: Drosophila_melanogaster.BDGP6.32.104.gtf\n URI: /data/shared/glyds/downloads/ucsc/gtf/Drosophila_melanogaster.BDGP6.32.104.gtf\n Output Subdomain\n Name: fruitfly_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.csv\n Name: fruitfly_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"7240\"\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: \"7233\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"7233\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"9\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"7168\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"7169\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/fruitfly_protein_genelocus.csv" }