{ "bcoid": "GLY_000001", "title": "Human Proteome Masterlist (UniProtKB)", "description": "The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped ...", "filename": "human_protein_masterlist.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Protein Canonical Accessions", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q9Y6C9-1...", "reviewed..." ], [ "Q658T7-1...", "reviewed..." ] ], "headers": [ "uniprotkb_ca...", "status..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "status" }, { "type": "string", "label": "gene_name" }, { "type": "string", "label": "reviewed_isoforms" }, { "type": "string", "label": "unreviewed_isoforms" } ], [ "Q9Y6C9-1", "reviewed", "MTCH2", "Q9Y6C9-1", "E9PIE4-1" ], [ "Q658T7-1", "reviewed", "FAM90A2P", "Q658T7-1", "" ], [ "Q658T7-1", "reviewed", "FAM90A2P", "Q658T7-2", "" ], [ "P30613-1", "reviewed", "PKLR", "P30613-1", "A0A0G2JLC7-1" ], [ "P30613-1", "reviewed", "PKLR", "P30613-2", "F8W6W2-1" ], [ "Q5MIZ7-1", "reviewed", "PPP4R3B", "Q5MIZ7-1", "" ], [ "Q5MIZ7-1", "reviewed", "PPP4R3B", "Q5MIZ7-2", "" ], [ "Q5MIZ7-1", "reviewed", "PPP4R3B", "Q5MIZ7-3", "" ], [ "Q5MIZ7-1", "reviewed", "PPP4R3B", "Q5MIZ7-4", "" ], [ "Q5MIZ7-1", "reviewed", "PPP4R3B", "Q5MIZ7-5", "" ], [ "A0A1W2PQ27-1", "unreviewed", "SSU72P7", "", "A0A1W2PQ27-1" ], [ "P51788-1", "reviewed", "CLCN2", "P51788-1", "A0A1B0GVL9-1" ], [ "P51788-1", "reviewed", "CLCN2", "P51788-2", "A0A1B0GVU4-1" ], [ "P51788-1", "reviewed", "CLCN2", "P51788-3", "A0A1B0GUY6-1" ], [ "P51788-1", "reviewed", "CLCN2", "P51788-4", "H7C0Q8-1" ], [ "P51788-1", "reviewed", "CLCN2", "P51788-5", "A0A1B0GVW7-1" ], [ "P51788-1", "reviewed", "CLCN2", "", "A0A1B0GTY0-1" ], [ "P51788-1", "reviewed", "CLCN2", "", "A0A1B0GTJ3-1" ], [ "P51788-1", "reviewed", "CLCN2", "", "A0A1B0GUZ8-1" ], [ "P51788-1", "reviewed", "CLCN2", "", "A0A1B0GWC8-1" ], [ "P51788-1", "reviewed", "CLCN2", "", "A0A1B0GV52-1" ], [ "P23919-1", "reviewed", "DTYMK", "P23919-2", "H7BZ20-1" ], [ "P23919-1", "reviewed", "DTYMK", "P23919-1", "H7C3A4-1" ], [ "P23919-1", "reviewed", "DTYMK", "", "H7C312-1" ], [ "P23919-1", "reviewed", "DTYMK", "", "G5E9E9-1" ], [ "Q8NHX4-1", "reviewed", "SPATA3", "Q8NHX4-1", "A0A087WU50-1" ], [ "Q8NHX4-1", "reviewed", "SPATA3", "", "H7C3E6-1" ], [ "Q8NHX4-1", "reviewed", "SPATA3", "", "H7C283-1" ], [ "Q8NHX4-1", "reviewed", "SPATA3", "", "F8WDD9-1" ], [ "Q8NHX4-1", "reviewed", "SPATA3", "", "A0A2R8Y5R0-1" ], [ "Q8NHX9-1", "reviewed", "TPCN2", "Q8NHX9-1", "A0A1B0GTM1-1" ], [ "Q8NHX9-1", "reviewed", "TPCN2", "", "A0A1B0GUM5-1" ], [ "Q8NHX9-1", "reviewed", "TPCN2", "", "E7ETX0-1" ], [ "Q9NXR8-1", "reviewed", "ING3", "Q9NXR8-1", "E7ET07-1" ], [ "Q9NXR8-1", "reviewed", "ING3", "Q9NXR8-2", "A0A0C4DG38-1" ], [ "Q9NXR8-1", "reviewed", "ING3", "Q9NXR8-3", "" ], [ "Q9C0H5-1", "reviewed", "ARHGAP39", "Q9C0H5-1", "" ], [ "Q9C0H5-1", "reviewed", "ARHGAP39", "Q9C0H5-2", "" ], [ "Q9C0H9-5", "reviewed", "SRCIN1", "Q9C0H9-2", "" ], [ "Q9C0H9-5", "reviewed", "SRCIN1", "Q9C0H9-4", "" ], [ "Q9C0H9-5", "reviewed", "SRCIN1", "Q9C0H9-5", "" ], [ "Q9NXR1-2", "reviewed", "NDE1", "Q9NXR1-1", "" ], [ "Q9NXR1-2", "reviewed", "NDE1", "Q9NXR1-2", "" ], [ "Q07960-1", "reviewed", "ARHGAP1", "Q07960-1", "H0YE29-1" ], [ "Q07960-1", "reviewed", "ARHGAP1", "", "E9PNR6-1" ], [ "Q9NXR5-1", "reviewed", "ANKRD10", "Q9NXR5-1", "S4R3R2-1" ], [ "Q9NXR5-1", "reviewed", "ANKRD10", "Q9NXR5-2", "Q8IUW1-1" ], [ "Q9NXR7-2", "reviewed", "BABAM2", "Q9NXR7-1", "" ], [ "Q9NXR7-2", "reviewed", "BABAM2", "Q9NXR7-2", "" ], [ "Q9NXR7-2", "reviewed", "BABAM2", "Q9NXR7-3", "" ], [ "Q9NXR7-2", "reviewed", "BABAM2", "Q9NXR7-4", "" ], [ "Q96J66-1", "reviewed", "ABCC11", "Q96J66-1", "H3BRJ2-1" ], [ "Q96J66-1", "reviewed", "ABCC11", "Q96J66-2", "" ], [ "P40424-1", "reviewed", "PBX1", "P40424-2", "H0YLF5-1" ], [ "P40424-1", "reviewed", "PBX1", "P40424-3", "S4R377-1" ], [ "P40424-1", "reviewed", "PBX1", "P40424-1", "H0YLD4-1" ], [ "P40424-1", "reviewed", "PBX1", "", "F8WA05-1" ], [ "P40424-1", "reviewed", "PBX1", "", "A0A0A0MTI0-1" ], [ "P40424-1", "reviewed", "PBX1", "", "H0YKH1-1" ], [ "P40424-1", "reviewed", "PBX1", "", "H0YLM3-1" ], [ "P40424-1", "reviewed", "PBX1", "", "A0A087X0P4-1" ], [ "P40424-1", "reviewed", "PBX1", "", "H0YLT4-1" ], [ "P40424-1", "reviewed", "PBX1", "", "H0YLB0-1" ], [ "P40425-1", "reviewed", "PBX2", "P40425-1", "" ], [ "P40426-1", "reviewed", "PBX3", "P40426-1", "H0Y5D0-1" ], [ "P40426-1", "reviewed", "PBX3", "P40426-2", "U3KQA2-1" ], [ "P40426-1", "reviewed", "PBX3", "P40426-3", "H3BLX0-1" ], [ "P40426-1", "reviewed", "PBX3", "P40426-4", "Q5JS98-1" ], [ "P40426-1", "reviewed", "PBX3", "P40426-5", "" ], [ "Q9H2I8-1", "reviewed", "LRMDA", "Q9H2I8-1", "A0A087WWI0-1" ], [ "Q9H2I8-1", "reviewed", "LRMDA", "", "A0A087WZZ7-1" ], [ "Q9H2I8-1", "reviewed", "LRMDA", "", "M0R2H0-1" ], [ "P08842-1", "reviewed", "STS", "P08842-1", "" ], [ "P03891-1", "reviewed", "MT-ND2", "P03891-1", "" ], [ "Q5VUR7-1", "reviewed", "ANKRD20A3", "Q5VUR7-1", "A0A087WY83-1" ], [ "P03897-1", "reviewed", "MT-ND3", "P03897-1", "" ], [ "P02768-1", "reviewed", "ALB", "P02768-1", "H0YA55-1" ], [ "P02768-1", "reviewed", "ALB", "P02768-2", "H7C013-1" ], [ "P02768-1", "reviewed", "ALB", "P02768-3", "D6RHD5-1" ], [ "P02768-1", "reviewed", "ALB", "", "D6RCE7-1" ], [ "P02768-1", "reviewed", "ALB", "", "A0A087WWT3-1" ], [ "P02768-1", "reviewed", "ALB", "", "B7WNR0-1" ], [ "P02768-1", "reviewed", "ALB", "", "A0A0C4DGB6-1" ], [ "P02768-1", "reviewed", "ALB", "", "C9JKR2-1" ] ] }, "readme": "Name\n - Human Proteome Masterlist (UniProtKB)\n\nVersion\n - 1.7.13\n\nCreated on\n - 2019-01-23T17:21:05.867420\n\nModified on\n - 2020-06-24T16:09:37.059682\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. 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\nDescription Domain\n Keywords\n - canonical accessions\n - gene name\n - protein isoforms\n - complete proteome\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping\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-1.7.13/source/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_protein_masterlist.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_masterlist.csv\n Name: human_protein_masterlist.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_masterlist.stat.csv\n\nFields\n Name: \"status\"\n Description: \"Status of the protein record in UniProtKB database that can be reviewed for UniProtKB/Swiss-Prot entry or unreviewed for UniProtKB/TrEMBL entry\"\n Unique Values: \"2\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"20656\"\n Name: \"unreviewed_isoforms\"\n Description: \"Protein records from UniProtKB/TrEMBL database that have been computationally annotated\"\n Unique Values: \"51536\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"20298\"\n Name: \"reviewed_isoforms\"\n Description: \"\"Protein records from UniProtKB/SwissProt database that have been manually curated and annotated based on experimental results\"\n Unique Values: \"42356\"", "downloadurl": "/ln2data/releases/data/v-1.7.13/reviewed/human_protein_masterlist.csv" }