{ "bcoid": "GLY_000100", "title": "Mouse UniProtKB Xref ChEMBL", "description": "The Mouse UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced ...", "filename": "mouse_protein_xref_chembl.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "Chembl cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q9JHR7-1...", "protein_xref..." ], [ "O08537-1...", "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" } ], [ "Q9JHR7-1", "protein_xref_chembl", "CHEMBL3232680", "" ], [ "O08537-1", "protein_xref_chembl", "CHEMBL2995", "" ], [ "O08911-1", "protein_xref_chembl", "CHEMBL2111473", "" ], [ "O08914-1", "protein_xref_chembl", "CHEMBL3455", "" ], [ "P10649-1", "protein_xref_chembl", "CHEMBL3722", "" ], [ "Q6T3U4-1", "protein_xref_chembl", "CHEMBL1075296", "" ], [ "O88665-1", "protein_xref_chembl", "CHEMBL3822348", "" ], [ "Q9QUN7-1", "protein_xref_chembl", "CHEMBL1075106", "" ], [ "P00520-1", "protein_xref_chembl", "CHEMBL3099", "" ], [ "P35438-1", "protein_xref_chembl", "CHEMBL3885583", "" ], [ "Q67BT3-1", "protein_xref_chembl", "CHEMBL3769294", "" ], [ "P27467-1", "protein_xref_chembl", "CHEMBL5617", "" ], [ "Q61618-1", "protein_xref_chembl", "CHEMBL1075269", "" ], [ "Q61614-1", "protein_xref_chembl", "CHEMBL2286", "" ], [ "Q61616-1", "protein_xref_chembl", "CHEMBL3071", "" ], [ "P11416-1", "protein_xref_chembl", "CHEMBL2792", "" ], [ "P43117-1", "protein_xref_chembl", "CHEMBL5000", "" ], [ "O08663-1", "protein_xref_chembl", "CHEMBL1075272", "" ], [ "Q99P50-1", "protein_xref_chembl", "CHEMBL3428", "" ], [ "P22437-1", "protein_xref_chembl", "CHEMBL2649", "" ], [ "P34927-1", "protein_xref_chembl", "CHEMBL5066", "" ], [ "Q9EQC5-1", "protein_xref_chembl", "CHEMBL3721301", "" ], [ "P09690-1", "protein_xref_chembl", "CHEMBL3137264", "" ], [ "P09690-1", "protein_xref_chembl", "CHEMBL3038460", "" ], [ "P42225-1", "protein_xref_chembl", "CHEMBL1667670", "" ], [ "Q9EPK8-1", "protein_xref_chembl", "CHEMBL6126", "" ], [ "Q9JLF1-1", "protein_xref_chembl", "CHEMBL2094133", "" ], [ "Q9JMH7-1", "protein_xref_chembl", "CHEMBL4106181", "" ], [ "Q9JMH7-1", "protein_xref_chembl", "CHEMBL4296071", "" ], [ "Q9JMH3-1", "protein_xref_chembl", "CHEMBL4296071", "" ], [ "Q920A5-1", "protein_xref_chembl", "CHEMBL3259511", "" ], [ "Q9Z0Y2-1", "protein_xref_chembl", "CHEMBL4378", "" ], [ "Q9Z0Y9-1", "protein_xref_chembl", "CHEMBL2189152", "" ], [ "P49290-1", "protein_xref_chembl", "CHEMBL4295770", "" ], [ "Q9WTU6-1", "protein_xref_chembl", "CHEMBL2034797", "" ], [ "Q8VDP6-1", "protein_xref_chembl", "CHEMBL2176", "" ], [ "P26011-1", "protein_xref_chembl", "CHEMBL2111481", "" ], [ "Q8R0X7-1", "protein_xref_chembl", "CHEMBL5009", "" ], [ "Q8BGW1-1", "protein_xref_chembl", "CHEMBL3611964", "" ], [ "P43432-1", "protein_xref_chembl", "CHEMBL2176814", "" ], [ "Q9JIM1-1", "protein_xref_chembl", "CHEMBL1287611", "" ], [ "P05555-1", "protein_xref_chembl", "CHEMBL3603", "" ], [ "Q3U3Q1-1", "protein_xref_chembl", "CHEMBL3832", "" ], [ "Q6X1Y6-1", "protein_xref_chembl", "CHEMBL3232696", "" ], [ "Q01279-1", "protein_xref_chembl", "CHEMBL3608", "" ], [ "O35625-1", "protein_xref_chembl", "CHEMBL4295996", "" ], [ "O08786-1", "protein_xref_chembl", "CHEMBL2798", "" ], [ "O08788-1", "protein_xref_chembl", "CHEMBL2176787", "" ], [ "P18894-1", "protein_xref_chembl", "CHEMBL2331068", "" ], [ "P70658-1", "protein_xref_chembl", "CHEMBL1250365", "" ], [ "Q03311-1", "protein_xref_chembl", "CHEMBL2528", "" ], [ "P0C7A3-1", "protein_xref_chembl", "CHEMBL1255134", "" ], [ "P09242-1", "protein_xref_chembl", "CHEMBL2660", "" ], [ "Q5QD14-1", "protein_xref_chembl", "CHEMBL3784908", "" ], [ "Q5QD11-1", "protein_xref_chembl", "CHEMBL2176792", "" ], [ "P08113-1", "protein_xref_chembl", "CHEMBL3425396", "" ], [ "Q9Z1B7-1", "protein_xref_chembl", "CHEMBL2111473", "" ], [ "P23818-1", "protein_xref_chembl", "CHEMBL3502", "" ], [ "P23819-1", "protein_xref_chembl", "CHEMBL2096617", "" ], [ "O70423-1", "protein_xref_chembl", "CHEMBL4727", "" ], [ "P52332-1", "protein_xref_chembl", "CHEMBL2968", "" ], [ "Q8C165-1", "protein_xref_chembl", "CHEMBL4295889", "" ], [ "P0DMN7-1", "protein_xref_chembl", "CHEMBL3584", "" ], [ "P97391-1", "protein_xref_chembl", "CHEMBL4167", "" ], [ "Q8K1N1-1", "protein_xref_chembl", "CHEMBL3259504", "" ], [ "Q9DC28-1", "protein_xref_chembl", "CHEMBL5175", "" ], [ "Q99N23-1", "protein_xref_chembl", "CHEMBL5973", "" ], [ "Q05921-1", "protein_xref_chembl", "CHEMBL2687", "" ], [ "Q9WVE8-1", "protein_xref_chembl", "CHEMBL2176817", "" ], [ "Q80Y98-1", "protein_xref_chembl", "CHEMBL3259495", "" ], [ "Q9JLN9-1", "protein_xref_chembl", "CHEMBL1255165", "" ], [ "Q99MB1-1", "protein_xref_chembl", "CHEMBL2146340", "" ], [ "Q3UES3-1", "protein_xref_chembl", "CHEMBL3232703", "" ], [ "P20852-1", "protein_xref_chembl", "CHEMBL4085", "" ], [ "Q6ZWX6-1", "protein_xref_chembl", "CHEMBL1770036", "" ], [ "Q91WC9-1", "protein_xref_chembl", "CHEMBL5656", "" ], [ "Q04998-1", "protein_xref_chembl", "CHEMBL3588734", "" ], [ "P33435-1", "protein_xref_chembl", "CHEMBL3638350", "" ], [ "P33434-1", "protein_xref_chembl", "CHEMBL3095", "" ], [ "P24063-1", "protein_xref_chembl", "CHEMBL1075188", "" ], [ "P00186-1", "protein_xref_chembl", "CHEMBL1671611", "" ], [ "P00184-1", "protein_xref_chembl", "CHEMBL6171", "" ], [ "Q9WU19-1", "protein_xref_chembl", "CHEMBL4295985", "" ], [ "Q6WQJ1-1", "protein_xref_chembl", "CHEMBL5180", "" ] ] }, "readme": "Name\n - Mouse UniProtKB Xref ChEMBL\n\nVersion\n - 1.8.25\n\nCreated on\n - 2019-03-15T12:09:44.596916\n\nModified on\n - 2020-04-10T12:38:13.714242\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 Mouse UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL 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 - 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-mus-musculus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/source/uniprot-proteome-mus-musculus.nt\n Name: mouse_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/mouse_protein_masterlist.csv\n Output Subdomain\n Name: mouse_protein_xref_chembl.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/mouse_protein_xref_chembl.csv\n Name: mouse_protein_xref_chembl.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/mouse_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-1.8.25/reviewed/mouse_protein_xref_chembl.csv" }