{ "bcoid": "GLY_000101", "title": "Human UniProtKB Xref GeneCards", "description": "The Human UniProtKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_genecards.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Genecards cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P30613-1...", "protein_xref..." ], [ "A0A1W2PQ27-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_label" } ], [ "P30613-1", "protein_xref_genecards", "PKLR", "" ], [ "A0A1W2PQ27-1", "protein_xref_genecards", "SSU72P7", "" ], [ "P23919-1", "protein_xref_genecards", "DTYMK", "" ], [ "Q8NHX4-1", "protein_xref_genecards", "SPATA3", "" ], [ "Q8NHX9-1", "protein_xref_genecards", "TPCN2", "" ], [ "H3BTG2-1", "protein_xref_genecards", "TEX46", "" ], [ "Q9C0H2-1", "protein_xref_genecards", "TTYH3", "" ], [ "Q9C0H5-1", "protein_xref_genecards", "ARHGAP39", "" ], [ "Q9C0H6-1", "protein_xref_genecards", "KLHL4", "" ], [ "Q9C0H9-5", "protein_xref_genecards", "SRCIN1", "" ], [ "Q96J66-1", "protein_xref_genecards", "ABCC11", "" ], [ "Q96J65-1", "protein_xref_genecards", "ABCC12", "" ], [ "Q9NYS7-1", "protein_xref_genecards", "WSB2", "" ], [ "P40424-1", "protein_xref_genecards", "PBX1", "" ], [ "P40425-1", "protein_xref_genecards", "PBX2", "" ], [ "P40426-1", "protein_xref_genecards", "PBX3", "" ], [ "P40429-1", "protein_xref_genecards", "RPL13A", "" ], [ "Q9H2I8-1", "protein_xref_genecards", "LRMDA", "" ], [ "P03891-1", "protein_xref_genecards", "MT-ND2", "" ], [ "P03897-1", "protein_xref_genecards", "MT-ND3", "" ], [ "P02768-1", "protein_xref_genecards", "ALB", "" ], [ "P02760-1", "protein_xref_genecards", "AMBP", "" ], [ "P02763-1", "protein_xref_genecards", "ORM1", "" ], [ "P02765-1", "protein_xref_genecards", "AHSG", "" ], [ "P82921-1", "protein_xref_genecards", "MRPS21", "" ], [ "P02766-1", "protein_xref_genecards", "TTR", "" ], [ "A0A494C086-1", "protein_xref_genecards", "SPDYE21", "" ], [ "Q9P2J5-1", "protein_xref_genecards", "LARS1", "" ], [ "H0YL14-1", "protein_xref_genecards", "TMEM250", "" ], [ "Q9P2J8-1", "protein_xref_genecards", "ZNF624", "" ], [ "O43399-1", "protein_xref_genecards", "TPD52L2", "" ], [ "Q9BXR3-1", "protein_xref_genecards", "ERVK-6", "" ], [ "Q9BXR3-1", "protein_xref_genecards", "ERVK-6", "" ], [ "Q5VVP1-1", "protein_xref_genecards", "SPATA31A6", "" ], [ "Q9BZG1-1", "protein_xref_genecards", "RAB34", "" ], [ "Q9BZG2-1", "protein_xref_genecards", "ACP4", "" ], [ "Q9BZG8-1", "protein_xref_genecards", "DPH1", "" ], [ "Q6NUK4-1", "protein_xref_genecards", "REEP3", "" ], [ "P01236-1", "protein_xref_genecards", "PRL", "" ], [ "Q8N865-1", "protein_xref_genecards", "C7orf31", "" ], [ "Q6NX49-1", "protein_xref_genecards", "ZNF544", "" ], [ "P09001-1", "protein_xref_genecards", "MRPL3", "" ], [ "P53708-1", "protein_xref_genecards", "ITGA8", "" ], [ "Q6NX45-1", "protein_xref_genecards", "ZNF774", "" ], [ "Q9H963-1", "protein_xref_genecards", "ZNF702P", "" ], [ "Q14568-1", "protein_xref_genecards", "HSP90AA2P", "" ], [ "Q9H967-1", "protein_xref_genecards", "WDR76", "" ], [ "Q14563-1", "protein_xref_genecards", "SEMA3A", "" ], [ "Q14562-1", "protein_xref_genecards", "DHX8", "" ], [ "Q14566-1", "protein_xref_genecards", "MCM6", "" ], [ "Q14565-1", "protein_xref_genecards", "DMC1", "" ], [ "A6NIR3-1", "protein_xref_genecards", "AGAP5", "" ], [ "Q6ZMG9-1", "protein_xref_genecards", "CERS6", "" ], [ "Q86VY4-1", "protein_xref_genecards", "TSPYL5", "" ], [ "Q86VY9-1", "protein_xref_genecards", "TMEM200A", "" ], [ "P19075-1", "protein_xref_genecards", "TSPAN8", "" ], [ "O60729-1", "protein_xref_genecards", "CDC14B", "" ], [ "A6NCL1-1", "protein_xref_genecards", "GMNC", "" ], [ "Q8WUF8-1", "protein_xref_genecards", "FAM172A", "" ], [ "Q96BT1-1", "protein_xref_genecards", "C3orf49", "" ], [ "Q8WUF5-1", "protein_xref_genecards", "PPP1R13L", "" ], [ "Q96BT3-1", "protein_xref_genecards", "CENPT", "" ], [ "Q96BT7-1", "protein_xref_genecards", "ALKBH8", "" ], [ "Q99519-1", "protein_xref_genecards", "NEU1", "" ], [ "O15417-1", "protein_xref_genecards", "TNRC18", "" ], [ "Q96RU7-1", "protein_xref_genecards", "TRIB3", "" ], [ "Q96RU3-1", "protein_xref_genecards", "FNBP1", "" ], [ "Q96RU2-1", "protein_xref_genecards", "USP28", "" ], [ "Q96RU8-1", "protein_xref_genecards", "TRIB1", "" ], [ "Q9ULV4-1", "protein_xref_genecards", "CORO1C", "" ], [ "Q9Y5A7-1", "protein_xref_genecards", "NUB1", "" ], [ "Q9Y5A6-1", "protein_xref_genecards", "ZSCAN21", "" ], [ "Q13643-1", "protein_xref_genecards", "FHL3", "" ], [ "Q13642-2", "protein_xref_genecards", "FHL1", "" ], [ "Q13641-1", "protein_xref_genecards", "TPBG", "" ], [ "Q9Y5A9-1", "protein_xref_genecards", "YTHDF2", "" ], [ "Q02127-1", "protein_xref_genecards", "DHODH", "" ], [ "Q6ZRV3-1", "protein_xref_genecards", "LINC00696", "" ], [ "Q6ZRV2-1", "protein_xref_genecards", "FAM83H", "" ], [ "Q5T6X5-1", "protein_xref_genecards", "GPRC6A", "" ], [ "A8MZ59-2", "protein_xref_genecards", "LEUTX", "" ], [ "Q9Y3T6-1", "protein_xref_genecards", "R3HCC1", "" ], [ "P16520-1", "protein_xref_genecards", "GNB3", "" ], [ "Q8NCJ5-1", "protein_xref_genecards", "SPRYD3", "" ] ] }, "readme": "Name\n - Human UniProtKB Xref GeneCards\n\nVersion\n - 1.9.9\n\nCreated on\n - 2019-03-15T12:10:45.775261\n\nModified on\n - 2020-04-10T11:34:28.717269\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 Human UniProtKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - GeneCards is a searchable, integrative database that provides comprehensive, user-friendly information on all annotated and predicted human genes. It automatically integrates gene-centric data from ~150 web sources, including genomic, transcriptomic, proteomic, genetic, clinical and functional information.\n\nDescription Domain\n Keywords\n - gene\n - GeneCards\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to GeneCards database accessions/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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_xref_genecards.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.csv\n Name: human_protein_xref_genecards.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"1\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"1\"\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"1\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"1\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"1\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"1\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.9.9/reviewed/human_protein_xref_genecards.csv" }