{ "bcoid": "GLY_000465", "title": "SARS-CoV1 Protein Site Annotation", "description": "The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] ...", "filename": "sarscov1_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "SARS coronavirus (SARS-CoV-1)", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P59596-1...", "M..." ], [ "P59596-1...", "M..." ] ], "headers": [ "uniprotkb_ca...", "gene_symbol..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "gene_symbol" }, { "type": "string", "label": "ann_type" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "annotation" }, { "type": "string", "label": "ecoid" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" } ], [ "P59596-1", "M", "Natural_Variant_Annotation", "27", "27", "In strain: Isolate CUHK-Su10, Isolate TWC2, Isolate TWC3, Isolate TWH, Isolate TWJ, Isolate TWK, Isolate TWS, Isolate TWY, Isolate Taiwan TC1, Isolate Taiwan TC2 and Isolate Taiwan TC3.", "", "F", "C", "protein_xref_uniprotkb", "P59596" ], [ "P59596-1", "M", "Natural_Variant_Annotation", "68", "68", "In strain: Isolate HKU-39849, Isolate FRA and Isolate Frankfurt 1.", "", "A", "V", "protein_xref_uniprotkb", "P59596" ], [ "P59596-1", "M", "Natural_Variant_Annotation", "73", "73", "In strain: Isolate TC3.", "", "N", "T", "protein_xref_uniprotkb", "P59596" ], [ "P59596-1", "M", "Natural_Variant_Annotation", "119", "119", "In strain: Isolate Shanghai QXC1.", "", "L", "P", "protein_xref_uniprotkb", "P59596" ], [ "P59596-1", "M", "Natural_Variant_Annotation", "11", "11", "In strain: Isolate Sin2500.", "", "E", "K", "protein_xref_uniprotkb", "P59596" ], [ "P59596-1", "M", "Natural_Variant_Annotation", "154", "154", "In strain: Isolate Urbani.", "", "S", "P", "protein_xref_uniprotkb", "P59596" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "1651", "1651", "For PL-PRO activity", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "1651", "1651", "For PL-PRO activity", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00444" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "1812", "1812", "For PL-PRO activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "1812", "1812", "For PL-PRO activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00444" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "3385", "3385", "For 3CL-PRO activity", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "3385", "3385", "For 3CL-PRO activity", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00772" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "3281", "3281", "For 3CL-PRO activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Active_Site_Annotation", "3281", "3281", "For 3CL-PRO activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00772" ], [ "P0C6U8-1", "", "Site_Annotation", "2740", "2741", "Cleavage; by PL-PRO", "", "GK", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "4230", "4231", "Cleavage; by 3CL-PRO", "", "QA", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "3240", "3241", "Cleavage; by 3CL-PRO", "", "QS", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "818", "819", "Cleavage; by PL-PRO", "", "GA", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "180", "181", "Cleavage", "", "GA", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "3919", "3920", "Cleavage; by 3CL-PRO", "", "QA", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "4369", "4370", "Cleavage; by 3CL-PRO", "", "QS", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "3546", "3547", "Cleavage; by 3CL-PRO", "", "QG", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "3836", "3837", "Cleavage; by 3CL-PRO", "", "QS", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Site_Annotation", "4117", "4118", "Cleavage; by 3CL-PRO", "", "QN", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4307", "4307", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4358", "4358", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4320", "4320", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4350", "4350", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4347", "4347", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4304", "4304", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Metal_Binding_Annotation", "4313", "4313", "Zinc", "", "H", "", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1776", "1777", "In strain: Isolate BJ03.", "", "QQ", "PP", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1136", "1136", "In strain: Isolate SZ3 and Isolate SZ16.", "", "P", "L", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1023", "1023", "In strain: Isolate Shanghai QXC1.", "", "I", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1790", "1790", "In strain: Isolate Shanghai QXC1.", "", "E", "G", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "138", "138", "In strain: Isolate SZ16.", "", "I", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3717", "3717", "In strain: Isolate Shanghai QXC1.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2770", "2770", "In strain: Isolate BJ01 and Isolate BJ02.", "", "V", "L", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2944", "2944", "In strain: Isolate SIN2500, Isolate GD01 and Isolate GZ50.", "", "T", "I", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3488", "3488", "In strain: Isolate BJ04.", "", "D", "E", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4003", "4003", "In strain: Isolate Shanghai LY.", "", "T", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "852", "852", "In strain: Isolate SZ16.", "", "K", "R", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1538", "1538", "In strain: Isolate GD01.", "", "S", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2480", "2480", "In strain: Isolate Shanghai QXC1.", "", "L", "P", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4085", "4085", "In strain: Isolate ZJ01.", "", "I", "H", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "549", "549", "In strain: Isolate SZ3.", "", "A", "S", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4240", "4240", "In strain: Isolate ZJ01.", "", "N", "H", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1004", "1004", "In strain: Isolate BJ03.", "", "N", "H", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1563", "1563", "In strain: Isolate BJ02.", "", "M", "K", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4296", "4296", "In strain: Isolate Shanghai QXC1.", "", "E", "G", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1361", "1361", "In strain: Isolate Shanghai QXC1.", "", "T", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "130", "130", "In strain: Isolate GD01.", "", "G", "R", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1962", "1962", "In strain: Isolate BJ04.", "", "L", "I", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3072", "3072", "In strain: Isolate CUHK-W1, Isolate SZ3, Isolate SZ16 and Isolate GD01.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1762", "1762", "In strain: Isolate BJ03.", "", "I", "L", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1319", "1319", "In strain: Isolate GD01.", "", "K", "R", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4114", "4114", "In strain: Isolate Shanghai QXC1.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2222", "2222", "In strain: Isolate GD01, Isolate SZ3 and Isolate SZ16.", "", "C", "Y", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1385", "1385", "In strain: Isolate Shanghai QXC1.", "", "I", "V", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2269", "2269", "In strain: Isolate SZ3 and Isolate SZ16.", "", "L", "S", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2556", "2556", "In strain: Isolate HKU-39849.", "", "D", "N", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2746", "2746", "In strain: Isolate SZ3 and Isolate SZ16.", "", "C", "W", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "306", "306", "In strain: Isolate BJ04.", "", "V", "F", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3818", "3818", "In strain: Isolate BJ04.", "", "N", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1329", "1329", "In strain: Isolate GD01.", "", "F", "S", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2718", "2718", "In strain: Isolate HKU-39849.", "", "R", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3903", "3903", "In strain: Isolate BJ03.", "", "D", "N", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3904", "3904", "In strain: Isolate BJ02.", "", "I", "F", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3047", "3047", "In strain: Isolate CUHK-W1, Isolate GD01, Isolate SZ3, Isolate SZ16, Isolate BJ01, Isolate BJ02, Isolate BJ03 and Isolate Shanghai QXC1.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2326", "2326", "In strain: Isolate Shanghai QXC1.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3020", "3020", "In strain: Isolate Shanghai QXC1.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3197", "3197", "In strain: Isolate BJ01, Isolate BJ02, Isolate BJ03, Isolate BJ04 and Isolate Shanghai QXC1.", "", "A", "V", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1021", "1021", "In strain: Isolate SZ3 and Isolate SZ16.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1257", "1257", "In strain: Isolate Shanghai QXC1.", "", "K", "E", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "249", "249", "In strain: Isolate Shanghai LY.", "", "Y", "C", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "1663", "1663", "In strain: Isolate SZ3 and Isolate SZ16.", "", "L", "I", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2116", "2116", "In strain: Isolate GD01, Isolate SZ3 and Isolate SZ16.", "", "L", "F", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "82", "82", "In strain: Isolate GD01.", "", "G", "C", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2971", "2971", "In strain: Isolate GD01 and Isolate SZ16.", "", "V", "A", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "4001", "4001", "In strain: Isolate Shanghai LY.", "", "K", "Q", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "181", "181", "In strain: Isolate Shanghai LY.", "", "A", "V", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2708", "2708", "In strain: Isolate HKU-39849.", "", "S", "T", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "3429", "3429", "In strain: Isolate BJ02.", "", "Q", "P", "protein_xref_uniprotkb", "P0C6U8" ], [ "P0C6U8-1", "", "Natural_Variant_Annotation", "2552", "2552", "In strain: Isolate Urbani and Isolate Taiwan TC2.", "", "A", "V", "protein_xref_uniprotkb", "P0C6U8" ] ] }, "readme": "Name\n - SARS-CoV1 Protein Site Annotation\n\nVersion\n - 1.7.10\n\nCreated on\n - 2020-04-09T13:22:15.821413\n\nModified on\n - 2020-04-09T18:54:45.572843\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 SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - site annotation\n - amino acid range\n - UniProtKB\n\n Pipeline Steps\n - Step-1: The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format\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-human-sars-coronavirus.nt\n URI: https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-human-sars-coronavirus.nt\n Name: sarscov1_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv\n Output Subdomain\n Name: sarscov1_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv\n Name: sarscov1_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"12\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"8\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"28\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"30\"\n Name: \"gene_symbol\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\"\n Unique Values: \"6\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"37\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"234\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"4\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"237\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"84\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.7.10/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv" }