{ "bcoid": "GLY_000227", "title": "Rat UniProtKB Xref ChEMBL", "description": "The Rat UniprotKB Xref ChEMBL contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...", "filename": "rat_protein_xref_chembl.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Chembl cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P30349-1...", "protein_xref..." ], [ "P20961-1...", "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" } ], [ "P30349-1", "protein_xref_chembl", "CHEMBL2400", "" ], [ "P20961-1", "protein_xref_chembl", "CHEMBL2155", "" ], [ "Q9WUD9-1", "protein_xref_chembl", "CHEMBL3014", "" ], [ "Q9WUD2-1", "protein_xref_chembl", "CHEMBL2863", "" ], [ "Q07969-1", "protein_xref_chembl", "CHEMBL2163174", "" ], [ "Q6P7Q4-1", "protein_xref_chembl", "CHEMBL2306", "" ], [ "P02764-1", "protein_xref_chembl", "CHEMBL3709434", "" ], [ "P02767-1", "protein_xref_chembl", "CHEMBL2151", "" ], [ "P43219-1", "protein_xref_chembl", "CHEMBL5001", "" ], [ "P83858-1", "protein_xref_chembl", "CHEMBL1949484", "" ], [ "P20814-1", "protein_xref_chembl", "CHEMBL3509596", "" ], [ "P24135-1", "protein_xref_chembl", "CHEMBL5230", "" ], [ "O88457-1", "protein_xref_chembl", "CHEMBL2629", "" ], [ "P22199-1", "protein_xref_chembl", "CHEMBL3507", "" ], [ "P22273-1", "protein_xref_chembl", "CHEMBL4289", "" ], [ "Q63009-1", "protein_xref_chembl", "CHEMBL1275220", "" ], [ "Q71MB6-1", "protein_xref_chembl", "CHEMBL2073710", "" ], [ "Q02765-1", "protein_xref_chembl", "CHEMBL1075217", "" ], [ "Q09QM4-1", "protein_xref_chembl", "CHEMBL4295807", "" ], [ "Q9QZH8-1", "protein_xref_chembl", "CHEMBL3509586", "" ], [ "Q99P96-1", "protein_xref_chembl", "CHEMBL2095943", "" ], [ "Q99P99-1", "protein_xref_chembl", "CHEMBL2095943", "" ], [ "Q4G017-1", "protein_xref_chembl", "CHEMBL5221", "" ], [ "Q8K5E0-1", "protein_xref_chembl", "CHEMBL4424", "" ], [ "Q80T02-1", "protein_xref_chembl", "CHEMBL1075223", "" ], [ "P14423-1", "protein_xref_chembl", "CHEMBL3686", "" ], [ "P51111-1", "protein_xref_chembl", "CHEMBL2439943", "" ], [ "P32305-1", "protein_xref_chembl", "CHEMBL3223", "" ], [ "P32301-1", "protein_xref_chembl", "CHEMBL5862", "" ], [ "P53563-1", "protein_xref_chembl", "CHEMBL1075182", "" ], [ "Q9JLB5-1", "protein_xref_chembl", "CHEMBL3461", "" ], [ "P15431-1", "protein_xref_chembl", "CHEMBL1907607", "" ], [ "P18113-1", "protein_xref_chembl", "CHEMBL3917", "" ], [ "P07872-1", "protein_xref_chembl", "CHEMBL4632", "" ], [ "Q64194-1", "protein_xref_chembl", "CHEMBL2352", "" ], [ "Q63633-1", "protein_xref_chembl", "CHEMBL1075108", "" ], [ "Q9JMD7-1", "protein_xref_chembl", "CHEMBL5797", "" ], [ "P47824-1", "protein_xref_chembl", "CHEMBL2530", "" ], [ "P17105-1", "protein_xref_chembl", "CHEMBL3261", "" ], [ "O35795-1", "protein_xref_chembl", "CHEMBL3300", "" ], [ "P23977-1", "protein_xref_chembl", "CHEMBL338", "" ], [ "P31016-1", "protein_xref_chembl", "CHEMBL3797015", "" ], [ "B0BNF9-1", "protein_xref_chembl", "CHEMBL2021746", "" ], [ "Q9R0Q2-1", "protein_xref_chembl", "CHEMBL2126", "" ], [ "P07340-1", "protein_xref_chembl", "CHEMBL4106147", "" ], [ "P07340-1", "protein_xref_chembl", "CHEMBL4106148", "" ], [ "P07340-1", "protein_xref_chembl", "CHEMBL4106149", "" ], [ "P07340-1", "protein_xref_chembl", "CHEMBL4106165", "" ], [ "Q9JIS4-1", "protein_xref_chembl", "CHEMBL3308951", "" ], [ "P30938-1", "protein_xref_chembl", "CHEMBL4318", "" ], [ "P40146-1", "protein_xref_chembl", "CHEMBL2095179", "" ], [ "Q62735-1", "protein_xref_chembl", "CHEMBL4105917", "" ], [ "Q62730-1", "protein_xref_chembl", "CHEMBL1914268", "" ], [ "P12392-1", "protein_xref_chembl", "CHEMBL2658", "" ], [ "O88944-1", "protein_xref_chembl", "CHEMBL5531", "" ], [ "O88943-1", "protein_xref_chembl", "CHEMBL5530", "" ], [ "P49088-1", "protein_xref_chembl", "CHEMBL2303", "" ], [ "Q8CGU9-1", "protein_xref_chembl", "CHEMBL3286063", "" ], [ "P17712-1", "protein_xref_chembl", "CHEMBL3882", "" ], [ "P08503-1", "protein_xref_chembl", "CHEMBL2176828", "" ], [ "P04176-1", "protein_xref_chembl", "CHEMBL3077", "" ], [ "P04177-1", "protein_xref_chembl", "CHEMBL2462", "" ], [ "Q63341-1", "protein_xref_chembl", "CHEMBL5506", "" ], [ "P97584-1", "protein_xref_chembl", "CHEMBL4166", "" ], [ "Q00959-1", "protein_xref_chembl", "CHEMBL310", "" ], [ "P05369-1", "protein_xref_chembl", "CHEMBL1075093", "" ], [ "P04631-1", "protein_xref_chembl", "CHEMBL3763006", "" ], [ "P07687-1", "protein_xref_chembl", "CHEMBL2299", "" ], [ "P09215-1", "protein_xref_chembl", "CHEMBL3633", "" ], [ "Q80Z39-1", "protein_xref_chembl", "CHEMBL4731", "" ], [ "P00502-1", "protein_xref_chembl", "CHEMBL2390", "" ], [ "P00507-1", "protein_xref_chembl", "CHEMBL2351", "" ], [ "Q63704-1", "protein_xref_chembl", "CHEMBL3216", "" ], [ "O88496-1", "protein_xref_chembl", "CHEMBL2744", "" ], [ "P35355-1", "protein_xref_chembl", "CHEMBL2977", "" ], [ "P35353-1", "protein_xref_chembl", "CHEMBL4649", "" ], [ "P35351-1", "protein_xref_chembl", "CHEMBL257", "" ], [ "Q62758-1", "protein_xref_chembl", "CHEMBL4317", "" ], [ "E9PU00-1", "protein_xref_chembl", "CHEMBL4295541", "" ], [ "P07335-1", "protein_xref_chembl", "CHEMBL2176812", "" ], [ "P10608-1", "protein_xref_chembl", "CHEMBL3754", "" ], [ "Q02294-1", "protein_xref_chembl", "CHEMBL5107", "" ], [ "Q02293-1", "protein_xref_chembl", "CHEMBL2095197", "" ], [ "P04799-1", "protein_xref_chembl", "CHEMBL1075125", "" ] ] }, "readme": "Name\n - Rat UniProtKB Xref ChEMBL\n\nVersion\n - 1.8.24\n\nCreated on\n - 2019-09-06T14:06:38.955413\n\nModified on\n - 2020-04-10T11:53:06.833357\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 Rat UniprotKB Xref ChEMBL contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties\n\nDescription Domain\n Keywords\n - bioactivity\n - ChEMBL\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL 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-rattus-norvegicus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_xref_chembl.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_chembl.csv\n Name: rat_protein_xref_chembl.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_chembl.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/rat_protein_xref_chembl.csv" }