{ "bcoid": "GLY_000444", "title": "SARS-CoV2 Protein Site Annotation", "description": "The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 ...", "filename": "sarscov2_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P0DTD1-1...", "rep..." ], [ "P0DTD1-1...", "rep..." ] ], "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" } ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "1674", "1674", "For PL1-PRO activity", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "1674", "1674", "For PL1-PRO activity", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00444" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3408", "3408", "Nucleophile; for 3CL-PRO activity", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3408", "3408", "Nucleophile; for 3CL-PRO activity", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00772" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3408", "3408", "Nucleophile; for 3CL-PRO activity", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3408", "3408", "Nucleophile; for 3CL-PRO activity", "ECO_0000269", "C", "", "protein_xref_pubmed", "32198291" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3304", "3304", "For 3CL-PRO activity", "ECO_0000305", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3304", "3304", "For 3CL-PRO activity", "ECO_0000305", "H", "", "protein_xref_pubmed", "32198291" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3304", "3304", "For 3CL-PRO activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "3304", "3304", "For 3CL-PRO activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00772" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "1835", "1835", "For PL2-PRO activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Active_Site_Annotation", "1835", "1835", "For PL2-PRO activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00444" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4253", "4254", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4253", "4254", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "2763", "2764", "Cleavage; by PL-PRO", "ECO_0000250", "GK", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "2763", "2764", "Cleavage; by PL-PRO", "ECO_0000250", "GK", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3569", "3570", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3569", "3570", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "5324", "5325", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "5324", "5325", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3942", "3943", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3942", "3943", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4392", "4393", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4392", "4393", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "818", "819", "Cleavage; by PL-PRO", "ECO_0000250", "GA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "818", "819", "Cleavage; by PL-PRO", "ECO_0000250", "GA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4140", "4141", "Cleavage; by 3CL-PRO", "ECO_0000250", "QN", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "4140", "4141", "Cleavage; by 3CL-PRO", "ECO_0000250", "QN", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "180", "181", "Cleavage; by PL-PRO", "ECO_0000250", "GA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "180", "181", "Cleavage; by PL-PRO", "ECO_0000250", "GA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "6452", "6453", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "6452", "6453", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "6798", "6799", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "6798", "6799", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3859", "3860", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3859", "3860", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "5925", "5926", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "5925", "5926", "Cleavage; by 3CL-PRO", "ECO_0000250", "QA", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3263", "3264", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Site_Annotation", "3263", "3264", "Cleavage; by 3CL-PRO", "ECO_0000250", "QS", "", "protein_xref_pubmed", "P0C6V3" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4693", "4693", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4693", "4693", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5332", "5332", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5332", "5332", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5357", "5357", "Zinc 4; via pros nitrogen", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5357", "5357", "Zinc 4; via pros nitrogen", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5340", "5340", "Zinc 4", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5340", "5340", "Zinc 4", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5034", "5034", "Zinc 2; structural", "ECO_0000269", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5034", "5034", "Zinc 2; structural", "ECO_0000269", "H", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4879", "4879", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4879", "4879", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5396", "5396", "Zinc 5", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5396", "5396", "Zinc 5", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5353", "5353", "Zinc 4; via tele nitrogen", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5353", "5353", "Zinc 4; via tele nitrogen", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5363", "5363", "Zinc 4", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5363", "5363", "Zinc 4", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4698", "4698", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4698", "4698", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5343", "5343", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5343", "5343", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5374", "5374", "Zinc 5", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5374", "5374", "Zinc 5", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5329", "5329", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5329", "5329", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5399", "5399", "Zinc 5", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5399", "5399", "Zinc 5", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4687", "4687", "Zinc 1; structural", "ECO_0000269", "H", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4687", "4687", "Zinc 1; structural", "ECO_0000269", "H", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5379", "5379", "Zinc 5; via pros nitrogen", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5379", "5379", "Zinc 5; via pros nitrogen", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5037", "5037", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5037", "5037", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4702", "4702", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "4702", "4702", "Zinc 1; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5350", "5350", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5350", "5350", "Zinc 3", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU00986" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5038", "5038", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "Metal_Binding_Annotation", "5038", "5038", "Zinc 2; structural", "ECO_0000269", "C", "", "protein_xref_pubmed", "32358203" ], [ "P0DTD1-1", "rep", "NP_Binding_Annotation", "5606", "5613", "NTP", "ECO_0000255", "GPPGTGKS", "", "protein_xref_uniprotkb", "P0DTD1" ], [ "P0DTD1-1", "rep", "NP_Binding_Annotation", "5606", "5613", "NTP", "ECO_0000255", "GPPGTGKS", "", "protein_xref_pubmed", "PRU00990" ], [ "P0DTC3-1", "", "Site_Annotation", "133", "133", "Involved in polymerization", "ECO_0000250", "C", "", "protein_xref_uniprotkb", "P0DTC3" ], [ "P0DTC3-1", "", "Site_Annotation", "133", "133", "Involved in polymerization", "ECO_0000250", "C", "", "protein_xref_pubmed", "P59632" ] ] }, "readme": "Name\n - SARS-CoV2 Protein Site Annotation\n\nVersion\n - 1.7.13\n\nCreated on\n - 2020-04-03T11:59:02.009860\n\nModified on\n - 2020-04-10T12:29:18.863153\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-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] 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-sars-cov-2.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/uniprot-proteome-sars-cov-2.nt\n Name: sarscov2_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/sarscov2_protein_masterlist.csv\n Output Subdomain\n Name: sarscov2_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv\n Name: sarscov2_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"6\"\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: \"22\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"7\"\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: \"4\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"17\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"75\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"5\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"73\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"30\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"", "downloadurl": "/ln2data/releases/data/v-1.7.13/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv" }