{ "bcoid": "GLY_000092", "title": "Human UniProtKB Xref BioMuta", "description": "The Human UniprotKB Xref BioMuta contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_biomuta.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Biomuta", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8TBF5-1...", "protein_xref..." ], [ "Q8TBF4-1...", "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" } ], [ "Q8TBF5-1", "protein_xref_biomuta", "Q8TBF5", "" ], [ "Q8TBF4-1", "protein_xref_biomuta", "Q8TBF4", "" ], [ "Q9NRJ4-1", "protein_xref_biomuta", "Q9NRJ4", "" ], [ "Q9NQ79-1", "protein_xref_biomuta", "Q9NQ79", "" ], [ "Q9NVL8-1", "protein_xref_biomuta", "Q9NVL8", "" ], [ "Q9NRQ5-1", "protein_xref_biomuta", "Q9NRQ5", "" ], [ "Q8IZF5-1", "protein_xref_biomuta", "Q8IZF5", "" ], [ "P30613-1", "protein_xref_biomuta", "P30613", "" ], [ "Q5H9L4-1", "protein_xref_biomuta", "Q5H9L4", "" ], [ "Q9BZL4-1", "protein_xref_biomuta", "Q9BZL4", "" ], [ "Q9NVL1-1", "protein_xref_biomuta", "Q9NVL1", "" ], [ "Q5QJ38-1", "protein_xref_biomuta", "Q5QJ38", "" ], [ "Q9NQ75-1", "protein_xref_biomuta", "Q9NQ75", "" ], [ "P20930-1", "protein_xref_biomuta", "P20930", "" ], [ "P20933-1", "protein_xref_biomuta", "P20933", "" ], [ "P20936-1", "protein_xref_biomuta", "P20936", "" ], [ "A0A1W2PQ27-1", "protein_xref_biomuta", "A0A1W2PQ27", "" ], [ "Q8NFX7-1", "protein_xref_biomuta", "Q8NFX7", "" ], [ "Q9UM21-1", "protein_xref_biomuta", "Q9UM21", "" ], [ "Q496A3-1", "protein_xref_biomuta", "Q496A3", "" ], [ "P83859-1", "protein_xref_biomuta", "P83859", "" ], [ "P40617-1", "protein_xref_biomuta", "P40617", "" ], [ "Q70EL4-1", "protein_xref_biomuta", "Q70EL4", "" ], [ "Q8TBF2-1", "protein_xref_biomuta", "Q8TBF2", "" ], [ "Q15573-1", "protein_xref_biomuta", "Q15573", "" ], [ "Q15572-1", "protein_xref_biomuta", "Q15572", "" ], [ "Q9BQP9-1", "protein_xref_biomuta", "Q9BQP9", "" ], [ "Q9H999-1", "protein_xref_biomuta", "Q9H999", "" ], [ "P23919-1", "protein_xref_biomuta", "P23919", "" ], [ "Q8NHX4-1", "protein_xref_biomuta", "Q8NHX4", "" ], [ "Q8NHX9-1", "protein_xref_biomuta", "Q8NHX9", "" ], [ "A8MU46-1", "protein_xref_biomuta", "A8MU46", "" ], [ "Q6ZNW5-1", "protein_xref_biomuta", "Q6ZNW5", "" ], [ "Q9NXR8-1", "protein_xref_biomuta", "Q9NXR8", "" ], [ "Q9C0H2-1", "protein_xref_biomuta", "Q9C0H2", "" ], [ "Q9C0H5-1", "protein_xref_biomuta", "Q9C0H5", "" ], [ "Q4VXU2-1", "protein_xref_biomuta", "Q4VXU2", "" ], [ "Q9C0H6-1", "protein_xref_biomuta", "Q9C0H6", "" ], [ "Q9C0H9-5", "protein_xref_biomuta", "Q9C0H9", "" ], [ "Q9NXR1-2", "protein_xref_biomuta", "Q9NXR1", "" ], [ "Q00537-1", "protein_xref_biomuta", "Q00537", "" ], [ "Q00536-1", "protein_xref_biomuta", "Q00536", "" ], [ "Q9NXR5-1", "protein_xref_biomuta", "Q9NXR5", "" ], [ "Q00532-1", "protein_xref_biomuta", "Q00532", "" ], [ "Q96J66-1", "protein_xref_biomuta", "Q96J66", "" ], [ "O00244-1", "protein_xref_biomuta", "O00244", "" ], [ "Q9UBM8-1", "protein_xref_biomuta", "Q9UBM8", "" ], [ "Q9H2V7-1", "protein_xref_biomuta", "Q9H2V7", "" ], [ "O00241-1", "protein_xref_biomuta", "O00241", "" ], [ "O00716-1", "protein_xref_biomuta", "O00716", "" ], [ "Q8IX01-1", "protein_xref_biomuta", "Q8IX01", "" ], [ "Q3LI54-1", "protein_xref_biomuta", "Q3LI54", "" ], [ "Q9UBM1-1", "protein_xref_biomuta", "Q9UBM1", "" ], [ "A8MTA8-1", "protein_xref_biomuta", "A8MTA8", "" ], [ "Q9UBM4-1", "protein_xref_biomuta", "Q9UBM4", "" ], [ "P24522-1", "protein_xref_biomuta", "P24522", "" ], [ "Q13835-1", "protein_xref_biomuta", "Q13835", "" ], [ "Q7Z3T1-1", "protein_xref_biomuta", "Q7Z3T1", "" ], [ "A0AVF1-1", "protein_xref_biomuta", "A0AVF1", "" ], [ "P40424-1", "protein_xref_biomuta", "P40424", "" ], [ "P40425-1", "protein_xref_biomuta", "P40425", "" ], [ "P40426-1", "protein_xref_biomuta", "P40426", "" ], [ "Q8IZK6-1", "protein_xref_biomuta", "Q8IZK6", "" ], [ "P40429-1", "protein_xref_biomuta", "P40429", "" ], [ "P51991-1", "protein_xref_biomuta", "P51991", "" ], [ "Q13838-1", "protein_xref_biomuta", "Q13838", "" ], [ "O00337-1", "protein_xref_biomuta", "O00337", "" ], [ "Q8TDW7-3", "protein_xref_biomuta", "Q8TDW7", "" ], [ "Q5M775-1", "protein_xref_biomuta", "Q5M775", "" ], [ "Q8WTV0-1", "protein_xref_biomuta", "Q8WTV0", "" ], [ "Q9H2I8-1", "protein_xref_biomuta", "Q9H2I8", "" ], [ "A0A075B6S2-1", "protein_xref_biomuta", "A0A075B6S2", "" ], [ "P08842-1", "protein_xref_biomuta", "P08842", "" ], [ "P03891-1", "protein_xref_biomuta", "P03891", "" ], [ "Q5VUR7-1", "protein_xref_biomuta", "Q5VUR7", "" ], [ "P48960-1", "protein_xref_biomuta", "P48960", "" ], [ "P03897-1", "protein_xref_biomuta", "P03897", "" ], [ "P02768-1", "protein_xref_biomuta", "P02768", "" ], [ "A0A075B7E8-1", "protein_xref_biomuta", "A0A075B7E8", "" ], [ "P20645-1", "protein_xref_biomuta", "P20645", "" ], [ "P05386-1", "protein_xref_biomuta", "P05386", "" ], [ "P05387-1", "protein_xref_biomuta", "P05387", "" ], [ "P24863-1", "protein_xref_biomuta", "P24863", "" ], [ "P08559-1", "protein_xref_biomuta", "P08559", "" ] ] }, "readme": "Name\n - Human UniProtKB Xref BioMuta\n\nVersion\n - 1.8.24\n\nCreated on\n - 2019-03-15T11:44:11.813164\n\nModified on\n - 2020-04-10T11:32:04.779812\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 BioMuta contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BioMuta database accessions/identifiers. BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates. The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - mutation\n - BioMuta\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to BioMuta 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/ln2data/releases/data/v-1.8.24/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_xref_biomuta.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_xref_biomuta.csv\n Name: human_protein_xref_biomuta.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/human_protein_xref_biomuta.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\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: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.24/reviewed/human_protein_xref_biomuta.csv" }