{ "bcoid": "GLY_000494", "title": "HCV1a Protein Site Annotation", "description": "The Hepatitis C virus (genotype 1a, isolate H) Protein Site Annotation (UniProtKB) dataset contains hcv1a ...", "filename": "hcv1a_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Hepatitis c virus (isolate h)" ], "molecule": [ "Protein" ], "tag": [ "site annotation" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P27958-1...", "..." ], [ "P27958-1...", "..." ] ], "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" } ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU01030" ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "H", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "H", "", "protein_xref_pubmed", "16862121" ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "H", "", "protein_xref_pubmed", "8248148" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "C", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "C", "", "protein_xref_pubmed", "8248148" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2 activity; shared with dimeric partner", "ECO_0000269", "C", "", "protein_xref_pubmed", "16862121" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU01030" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000269", "H", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000269", "H", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "H", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "H", "", "protein_xref_pubmed", "8861917" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU01166" ], [ "P27958-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "D", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "D", "", "protein_xref_pubmed", "8861917" ], [ "P27958-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "D", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "D", "", "protein_xref_pubmed", "PRU01166" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000269", "S", "", "protein_xref_pubmed", "8248148" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "S", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000305", "S", "", "protein_xref_pubmed", "8861917" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000269", "S", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "S", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "S", "", "protein_xref_pubmed", "PRU01166" ], [ "P27958-1", "", "Active_Site_Annotation", "972", "972", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "E", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Active_Site_Annotation", "972", "972", "For protease NS2 activity; shared with dimeric partner", "ECO_0000255", "E", "", "protein_xref_pubmed", "PRU01030" ], [ "P27958-1", "", "Site_Annotation", "191", "192", "Cleavage; by host signal peptidase", "ECO_0000250", "AY", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "191", "192", "Cleavage; by host signal peptidase", "ECO_0000250", "AY", "", "protein_xref_pubmed", "P26662" ], [ "P27958-1", "", "Site_Annotation", "1711", "1712", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "1711", "1712", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Site_Annotation", "1026", "1027", "Cleavage; by protease NS2", "ECO_0000255", "LA", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "1026", "1027", "Cleavage; by protease NS2", "ECO_0000255", "LA", "", "protein_xref_pubmed", "PRU01030" ], [ "P27958-1", "", "Site_Annotation", "1972", "1973", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "1972", "1973", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Site_Annotation", "383", "384", "Cleavage; by host signal peptidase", "ECO_0000250", "AE", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "383", "384", "Cleavage; by host signal peptidase", "ECO_0000250", "AE", "", "protein_xref_pubmed", "P26662" ], [ "P27958-1", "", "Site_Annotation", "2420", "2421", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "2420", "2421", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "CS", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Site_Annotation", "177", "178", "Cleavage; by host signal peptide peptidase", "ECO_0000250", "FL", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "177", "178", "Cleavage; by host signal peptide peptidase", "ECO_0000250", "FL", "", "protein_xref_pubmed", "P26662" ], [ "P27958-1", "", "Site_Annotation", "1657", "1658", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "TS", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "1657", "1658", "Cleavage; by serine protease/helicase NS3", "ECO_0000269", "TS", "", "protein_xref_pubmed", "8386278" ], [ "P27958-1", "", "Site_Annotation", "809", "810", "Cleavage; by host signal peptidase", "", "AL", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "746", "747", "Cleavage; by host signal peptidase", "", "AA", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "645", "645", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "645", "645", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "196", "196", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "196", "196", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "10211957" ], [ "P27958-1", "", "Glycosylation_Annotation", "423", "423", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "423", "423", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "305", "305", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "305", "305", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "10211957" ], [ "P27958-1", "", "Glycosylation_Annotation", "623", "623", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "623", "623", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "623", "623", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "24288331" ], [ "P27958-1", "", "Glycosylation_Annotation", "540", "540", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "540", "540", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "476", "476", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "476", "476", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "209", "209", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "209", "209", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "10211957" ], [ "P27958-1", "", "Glycosylation_Annotation", "417", "417", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "417", "417", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "556", "556", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "556", "556", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "556", "556", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "24288331" ], [ "P27958-1", "", "Glycosylation_Annotation", "234", "234", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "234", "234", "N-linked (GlcNAc...) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "10211957" ], [ "P27958-1", "", "Glycosylation_Annotation", "448", "448", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "448", "448", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "430", "430", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "430", "430", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "24288331" ], [ "P27958-1", "", "Glycosylation_Annotation", "430", "430", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "576", "576", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "576", "576", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "532", "532", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Glycosylation_Annotation", "532", "532", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "18187336" ], [ "P27958-1", "", "Glycosylation_Annotation", "532", "532", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "ECO_0000269", "N", "", "protein_xref_pubmed", "24288331" ], [ "P27958-1", "", "Modified_Residue_Annotation", "53", "53", "Phosphoserine; by host", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Modified_Residue_Annotation", "53", "53", "Phosphoserine; by host", "ECO_0000250", "S", "", "protein_xref_pubmed", "Q01403" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2204", "2204", "Phosphoserine; by host; in p58", "ECO_0000250", "S", "", "protein_xref_uniprotkb", "P27958" ] ] }, "readme": "Name\n - HCV1a Protein Site Annotation\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2020-05-07T18:11:47.601071\n\nModified on\n - 2022-09-26T09:05:56.537576\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@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 Hepatitis C virus (genotype 1a, isolate H) Protein Site Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] 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 sequences and extracts as a dataset in a csv format. \n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/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: hcv1a_protein_masterlist.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_masterlist.csv\n Name: uniprot-proteome-hepatitis-c-virus-1a.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-hepatitis-c-virus-1a.nt\n Output Subdomain\n Name: hcv1a_protein_site_annotation_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv\n Name: hcv1a_protein_site_annotation_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1\"\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: \"1\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"6\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"128\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"131\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"33\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"5\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"29\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"23\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"21\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv" }