{ "bcoid": "GLY_000751", "title": "Yeast Gene Locus (Ensembl)", "description": "The Yeast Gene Locus (Ensembl) contains yeast [taxid:559292] UniProtKB canonical accessions mapped to ...", "filename": "yeast_protein_genelocus.csv", "filetype": "csv", "categories": { "species": [ "Saccharomyces cerevisiae S288C" ], "molecule": [ "Protein" ], "tag": [ "Gene Coordinates" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P25378-1...", "RHB1..." ], [ "P25374-1...", "NFS1..." ] ], "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" } ], [ "P25378-1", "RHB1", "YCR027C", "III", "167370", "167999", "1" ], [ "P25374-1", "NFS1", "YCL017C", "III", "92777", "94270", "1" ], [ "P25370-1", "GFD2", "YCL036W", "III", "59026", "60726", "0" ], [ "Q00539-1", "NAM8", "YHR086W", "VIII", "278153", "279724", "0" ], [ "P40422-1", "RPC10", "YHR143W-A", "VIII", "387233", "387445", "0" ], [ "P48566-1", "MSB3", "YNL293W", "XIV", "80640", "82541", "0" ], [ "Q08742-1", "RDL2", "YOR286W", "XV", "850280", "850729", "0" ], [ "P32917-1", "STE5", "YDR103W", "IV", "658350", "661103", "0" ], [ "P32911-1", "SUI1", "YNL244C", "XIV", "187170", "187496", "1" ], [ "P32913-1", "VPS17", "YOR132W", "XV", "573175", "574830", "0" ], [ "P32912-1", "VAM7", "YGL212W", "VII", "91432", "92382", "0" ], [ "Q04437-1", "YKU80", "YMR106C", "XIII", "478301", "480190", "1" ], [ "P00546-1", "CDC28", "YBR160W", "II", "560078", "560974", "0" ], [ "P04386-1", "GAL4", "YPL248C", "XVI", "79711", "82356", "1" ], [ "Q08299-1", "ENB1", "YOL158C", "XV", "19491", "21311", "1" ], [ "Q08562-1", "ULS1", "YOR191W", "XV", "692475", "697334", "0" ], [ "P25377-1", "ADH7", "YCR105W", "III", "309070", "310155", "0" ], [ "P25376-1", "AGP1", "YCL025C", "III", "76018", "77919", "1" ], [ "P00729-1", "PRC1", "YMR297W", "XIII", "861922", "863520", "0" ], [ "P23542-1", "AAT2", "YLR027C", "XII", "196829", "198085", "1" ], [ "P38968-1", "SEC31", "YDL195W", "IV", "107208", "111029", "0" ], [ "P38967-1", "TAT2", "YOL020W", "XV", "286172", "287950", "0" ], [ "P15180-1", "KRS1", "YDR037W", "IV", "525440", "527215", "0" ], [ "Q03180-1", "PIR3", "YKL163W", "XI", "144401", "145378", "0" ], [ "Q3E7B2-1", "COA3", "YJL062W-A", "X", "316723", "316980", "0" ], [ "Q3E7B6-1", "VMA9", "YCL005W-A", "III", "107023", "107417", "0" ], [ "P16521-1", "YEF3", "YLR249W", "XII", "636780", "639914", "0" ], [ "Q12511-1", "PTC5", "YOR090C", "XV", "491123", "492841", "1" ], [ "P39708-1", "GDH3", "YAL062W", "I", "31567", "32940", "0" ], [ "P39702-1", "VPS8", "YAL002W", "I", "143707", "147531", "0" ], [ "P39707-1", "SEN34", "YAR008W", "I", "158966", "159793", "0" ], [ "P39706-1", "SWD1", "YAR003W", "I", "155005", "156285", "0" ], [ "Q08176-1", "MIM1", "YOL026C", "XV", "274012", "274353", "1" ], [ "Q08179-1", "MDM38", "YOL027C", "XV", "272003", "273724", "1" ], [ "Q00764-1", "TPS1", "YBR126C", "II", "488905", "490392", "1" ], [ "P17695-1", "GRX2", "YDR513W", "IV", "1471017", "1471448", "0" ], [ "P08525-1", "QCR8", "YJL166W", "X", "106434", "106718", "0" ], [ "P08524-1", "ERG20", "YJL167W", "X", "105014", "106072", "0" ], [ "Q99216-1", "PNO1", "YOR145C", "XV", "605347", "606171", "1" ], [ "P15436-1", "POL3", "YDL102W", "IV", "276872", "280165", "0" ], [ "Q12355-1", "PST1", "YDR055W", "IV", "563527", "564861", "0" ], [ "P11433-1", "CDC24", "YAL041W", "I", "62840", "65404", "0" ], [ "P47821-1", "SSN8", "YNL025C", "XIV", "584320", "585291", "1" ], [ "P47822-1", "SRB7", "YDR308C", "IV", "1078027", "1078449", "1" ], [ "P89105-1", "CTR9", "YOL145C", "XV", "49555", "52788", "1" ], [ "P50896-1", "PSP1", "YDR505C", "IV", "1456695", "1459220", "1" ], [ "P39958-1", "GDI1", "YER136W", "V", "439616", "440971", "0" ], [ "P17106-1", "CBF1", "YJR060W", "X", "548759", "549814", "0" ], [ "Q02207-1", "FOX2", "YKR009C", "XI", "454352", "457054", "1" ], [ "P39953-1", "YEA6", "YEL006W", "V", "144327", "145334", "0" ], [ "P32263-1", "PRO3", "YER023W", "V", "201076", "201936", "0" ], [ "Q02202-1", "ECM9", "YKR004C", "XI", "446799", "448036", "1" ], [ "P02293-1", "HTB1", "YDR224C", "IV", "914317", "914712", "1" ], [ "P32266-1", "MGM1", "YOR211C", "XV", "738924", "741569", "1" ], [ "P29465-1", "CHS3", "YBR023C", "II", "284428", "287925", "1" ], [ "Q08548-1", "ALE1", "YOR175C", "XV", "659815", "661674", "1" ], [ "P53720-1", "SMM1", "YNR015W", "XIV", "653387", "654541", "0" ], [ "P00549-1", "CDC19", "YAL038W", "I", "71786", "73288", "0" ], [ "P43497-1", "CWP2", "YKL096W-A", "XI", "259253", "259531", "0" ], [ "P32939-1", "YPT7", "YML001W", "XIII", "267174", "267800", "0" ], [ "P41895-1", "TFG1", "YGR186W", "VII", "867774", "869981", "0" ], [ "Q05498-1", "FCF1", "YDR339C", "IV", "1149951", "1150520", "1" ], [ "P06843-1", "SPT2", "YER161C", "V", "499347", "500348", "1" ], [ "P38806-1", "YNG2", "YHR090C", "VIII", "283777", "284625", "1" ], [ "P38801-1", "LRP1", "YHR081W", "VIII", "267538", "268092", "0" ], [ "P40327-1", "RPT2", "YDL007W", "IV", "438047", "439360", "0" ], [ "Q12168-1", "ACF2", "YLR144C", "XII", "429677", "432016", "1" ], [ "P12754-1", "GCD2", "YGR083C", "VII", "644860", "646815", "1" ], [ "Q03433-1", "VPS71", "YML041C", "XIII", "194913", "195755", "1" ], [ "Q03435-1", "NHP10", "YDL002C", "IV", "446967", "447578", "1" ], [ "P47050-1", "RTT101", "YJL047C", "X", "349580", "352108", "1" ], [ "Q08484-1", "GYP1", "YOR070C", "XV", "455907", "457820", "1" ], [ "P10591-1", "SSA1", "YAL005C", "I", "139503", "141431", "1" ], [ "P10592-1", "SSA2", "YLL024C", "XII", "95566", "97485", "1" ], [ "Q06629-1", "HDA2", "YDR295C", "IV", "1052623", "1054647", "1" ], [ "Q06628-1", "ATG13", "YPR185W", "XVI", "907218", "909434", "0" ], [ "Q06624-1", "AOS1", "YPR180W", "XVI", "895961", "897004", "0" ], [ "Q06623-1", "HDA3", "YPR179C", "XVI", "893797", "895764", "1" ], [ "P38237-1", "UBP14", "YBR058C", "II", "353672", "356017", "1" ], [ "P39723-1", "SPC72", "YAL047C", "I", "54989", "56857", "1" ], [ "P39722-1", "GEM1", "YAL048C", "I", "52801", "54789", "1" ], [ "P39720-1", "OAF1", "YAL051W", "I", "48564", "51707", "0" ], [ "P39727-1", "ERV46", "YAL042W", "I", "61316", "62563", "0" ], [ "P39729-1", "RBG1", "YAL036C", "I", "75043", "76152", "1" ] ] }, "readme": "Name\n - Yeast Gene Locus (Ensembl)\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2020-04-10T11:29:22.824792\n\nModified on\n - 2023-09-11T19:00:43\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], 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 Yeast Gene Locus (Ensembl) contains yeast [taxid:559292] 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: yeast_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_masterlist.csv\n Name: uniprot-proteome-saccharomyces-cerevisiae.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-saccharomyces-cerevisiae.nt\n Output Subdomain\n Name: yeast_protein_genelocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_genelocus.csv\n Name: yeast_protein_genelocus.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_genelocus.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1751\"\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: \"1751\"\n Name: \"ensembl_gene_id\"\n Description: \"Gene Identifier in Ensembl database\"\n Unique Values: \"1751\"\n Name: \"chromosome_id\"\n Description: \"Chromosome number identifier\"\n Unique Values: \"17\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"1750\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"1749\"\n Name: \"strand\"\n Description: \"The strand of the gene\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/yeast_protein_genelocus.csv" }