{ "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 (genotype 1a, isolate H)", "molecule": "Protein", "tags": "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": "pmid" }, { "type": "string", "label": "ecoid" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" } ], [ "P27958-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "PRU01166", "ECO_0000255", "H", "" ], [ "P27958-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "PRU01166", "ECO_0000255", "S", "" ], [ "P27958-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "PRU01166", "ECO_0000255", "D", "" ], [ "P27958-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2-3 activity; shared with dimeric partner", "", "", "C", "" ], [ "P27958-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2-3 activity; shared with dimeric partner", "", "", "H", "" ], [ "P27958-1", "", "Active_Site_Annotation", "972", "972", "For protease NS2-3 activity; shared with dimeric partner", "", "", "E", "" ], [ "P27958-1", "", "Site_Annotation", "1026", "1027", "Cleavage; by protease NS2-3", "PRU01030", "ECO_0000255", "", "" ], [ "P27958-1", "", "Site_Annotation", "2420", "2421", "Cleavage; by serine protease NS3", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "383", "384", "Cleavage; by host signal peptidase", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "177", "178", "Cleavage; by host signal peptidase", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "809", "810", "Cleavage; by host signal peptidase", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "191", "192", "Cleavage; by host signal peptidase", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "1657", "1658", "Cleavage; by serine protease NS3", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "1972", "1973", "Cleavage; by serine protease NS3", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "1711", "1712", "Cleavage; by serine protease NS3", "", "", "", "" ], [ "P27958-1", "", "Site_Annotation", "746", "747", "Cleavage; by host signal peptidase", "", "", "", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "532", "532", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "556", "556", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "423", "423", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "448", "448", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "576", "576", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "196", "196", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "209", "209", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "623", "623", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "234", "234", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "540", "540", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "645", "645", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "305", "305", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "417", "417", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "476", "476", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Glycosylation_Annotation", "430", "430", "N-linked (GlcNAc...) asparagine; by host", "", "", "N", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "1175", "1175", "Zinc", "PRU01166", "ECO_0000255", "H", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "1171", "1171", "Zinc", "PRU01166", "ECO_0000255", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "1125", "1125", "Zinc", "PRU01166", "ECO_0000255", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "1123", "1123", "Zinc", "PRU01166", "ECO_0000255", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2052", "2052", "Zinc", "", "", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2031", "2031", "Zinc", "", "", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2029", "2029", "Zinc", "", "", "C", "" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2011", "2011", "Zinc", "", "", "C", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2321", "2321", "Phosphoserine; by host", "10488152", "ECO_0000269", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2194", "2194", "Phosphoserine; by host; in p56", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "99", "99", "Phosphoserine; by host", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2201", "2201", "Phosphoserine; by host; in p58", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2197", "2197", "Phosphoserine; by host; in p58", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2204", "2204", "Phosphoserine; by host; in p58", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "116", "116", "Phosphoserine; by host PKA", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "2", "2", "N-acetylserine; by host", "", "", "S", "" ], [ "P27958-1", "", "Modified_Residue_Annotation", "53", "53", "Phosphoserine; by host", "", "", "S", "" ], [ "P27958-1", "", "NP_Binding_Annotation", "1230", "1237", "ATP", "PRU00541", "ECO_0000255", "", "" ], [ "P27958-1", "", "Mutagenesis_Annotation", "781", "781", "Virus can no longer infect chimpanzee.", "14504405", "ECO_0000269", "R", "S" ], [ "P27958-1", "", "Mutagenesis_Annotation", "1972", "1972", "Slight decrease in NS4B palmitoylation.", "16731940", "ECO_0000269", "C", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "1968", "1968", "Strong decrease in NS4B palmitoylation.", "16731940", "ECO_0000269", "C", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "952", "952", "Complete loss of NS2-NS3 cleavage.", "16862121", "ECO_0000269", "H", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "952", "952", "Complete loss of NS2-NS3 cleavage.", "8248148", "ECO_0000269", "H", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "720", "720", "Increases processing between E2 and p7.", "15722527", "ECO_0000269", "V", "L" ], [ "P27958-1", "", "Mutagenesis_Annotation", "1165", "1165", "Complete loss of NS3-NS4A, NS4A-NS4B, NS4B-NS5A and NS5A-NS5B cleavages.", "8248148", "ECO_0000269", "S", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "779", "779", "Virus can no longer infect chimpanzee.", "14504405", "ECO_0000269", "K", "I" ], [ "P27958-1", "", "Mutagenesis_Annotation", "2321", "2321", "Loss of phosphorylation.", "10488152", "ECO_0000269", "S", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "993", "993", "Complete loss of NS2-NS3 cleavage.", "16862121", "ECO_0000269", "C", "A" ], [ "P27958-1", "", "Mutagenesis_Annotation", "993", "993", "Complete loss of NS2-NS3 cleavage.", "8248148", "ECO_0000269", "C", "A" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2425", "2425", "In strain: Isolate H77.", "", "", "S", "T" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1121", "1121", "In strain: Isolate H77.", "", "", "T", "A" ], [ "P27958-1", "", "Natural_Variant_Annotation", "877", "877", "In strain: Isolate H77.", "", "", "T", "M" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2755", "2755", "In strain: Isolate H77.", "", "", "S", "N" ], [ "P27958-1", "", "Natural_Variant_Annotation", "457", "457", "In strain: Isolate H77.", "", "", "A", "T" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2043", "2043", "In strain: Isolate H77.", "", "", "T", "A" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1839", "1840", "In strain: Isolate H77.", "", "", "", "" ], [ "P27958-1", "", "Natural_Variant_Annotation", "948", "948", "In strain: Isolate H77.", "", "", "C", "Y" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1173", "1173", "In strain: Isolate H77.", "", "", "T", "A" ], [ "P27958-1", "", "Natural_Variant_Annotation", "650", "650", "In strain: Isolate H77.", "", "", "E", "G" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2341", "2341", "In strain: Isolate H77.", "", "", "P", "S" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2053", "2053", "In strain: Isolate H77.", "", "", "K", "R" ], [ "P27958-1", "", "Natural_Variant_Annotation", "297", "297", "In strain: Isolate H77.", "", "", "H", "R" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2185", "2185", "In strain: Isolate H77.", "", "", "A", "E" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2715", "2715", "In strain: Isolate H77.", "", "", "R", "C" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2061", "2061", "In strain: Isolate H77.", "", "", "F", "L" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1100", "1100", "In strain: Isolate H77.", "", "", "T", "M" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1214", "1214", "In strain: Isolate H77.", "", "", "S", "P" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1608", "1608", "In strain: Isolate H77.", "", "", "R", "W" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1026", "1026", "In strain: Isolate H77.", "", "", "L", "Q" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1049", "1049", "In strain: Isolate H77.", "", "", "G", "S" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2960", "2960", "In strain: Isolate H77.", "", "", "T", "A" ], [ "P27958-1", "", "Natural_Variant_Annotation", "1327", "1327", "In strain: Isolate H77.", "", "", "S", "L" ], [ "P27958-1", "", "Natural_Variant_Annotation", "2283", "2283", "In strain: Isolate H77.", "", "", "P", "R" ] ] }, "readme": "Name\n - HCV1a Protein Site Annotation\n\nVersion\n - 1.5.27\n\nCreated on\n - 2020-05-07T18:11:47.601071\n\nModified on\n - 2020-05-07T18:12:20.019621\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 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 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-hepatitis-c-virus-1a.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt\n Name: hcv1a_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/hcv1a_protein_masterlist.csv\n Output Subdomain\n Name: hcv1a_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv\n Name: hcv1a_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n Unique Values: \"1\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"8\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"20\"\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: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"19\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"114\"\n Name: \"ecoid\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"3\"\n Name: \"pmid\"\n Description: \"NCBI PubMed database Identifier\"\n Unique Values: \"10\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"116\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"21\"", "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv" }