{ "bcoid": "GLY_000367", "title": "HCV1b Protein Site Annotation", "description": "The Hepatitis C virus (genotype 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset ...", "filename": "hcv1b_protein_site_annotation_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Hepatitis C virus (genotype 1b, isolate Japanese)", "molecule": "Protein", "tags": "site annotation", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P26662-1...", "..." ], [ "P26662-1...", "..." ] ], "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" } ], [ "P26662-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "952", "952", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU01030" ], [ "P26662-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "1165", "1165", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "S", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "993", "993", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU01030" ], [ "P26662-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "D", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "1107", "1107", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "D", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "1083", "1083", "Charge relay system; for serine protease NS3 activity", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Active_Site_Annotation", "972", "972", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "E", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Active_Site_Annotation", "972", "972", "For protease NS2-3 activity; shared with dimeric partner", "ECO_0000255", "E", "", "protein_xref_pubmed", "PRU01030" ], [ "P26662-1", "", "Site_Annotation", "1026", "1027", "Cleavage; by protease NS2-3", "ECO_0000255", "LA", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "1026", "1027", "Cleavage; by protease NS2-3", "ECO_0000255", "LA", "", "protein_xref_pubmed", "PRU01030" ], [ "P26662-1", "", "Site_Annotation", "746", "747", "Cleavage; by host signal peptidase", "", "AT", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "383", "384", "Cleavage; by host signal peptidase", "", "GH", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "1657", "1658", "Cleavage; by serine protease NS3", "", "TS", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "1972", "1973", "Cleavage; by serine protease NS3", "", "CS", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "1711", "1712", "Cleavage; by serine protease NS3", "", "CA", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "809", "810", "Cleavage; by host signal peptidase", "", "AM", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "177", "178", "Cleavage; by host signal peptidase", "", "FL", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "191", "192", "Cleavage; by host signal peptidase", "", "AY", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Site_Annotation", "2419", "2420", "Cleavage; by serine protease NS3", "", "CS", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "401", "401", "O-linked (Hex...) serine; by host", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "401", "401", "O-linked (Hex...) serine; by host", "ECO_0000269", "S", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "385", "385", "O-linked (Hex...) threonine; by host", "ECO_0000305", "T", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "385", "385", "O-linked (Hex...) threonine; by host", "ECO_0000305", "T", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "473", "473", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "473", "473", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "404", "404", "O-linked (Hex...) serine; by host", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "404", "404", "O-linked (Hex...) serine; by host", "ECO_0000269", "S", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "518", "518", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "518", "518", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "396", "396", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "396", "396", "O-linked (Hex...) threonine; by host", "ECO_0000269", "T", "", "protein_xref_pubmed", "23242014" ], [ "P26662-1", "", "Glycosylation_Annotation", "430", "430", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "250", "250", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "576", "576", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "305", "305", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "423", "423", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "645", "645", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "417", "417", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "234", "234", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "448", "448", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "556", "556", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "209", "209", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "532", "532", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "196", "196", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Glycosylation_Annotation", "623", "623", "N-linked (GlcNAc...) asparagine; by host", "", "N", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1171", "1171", "Zinc", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1171", "1171", "Zinc", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1175", "1175", "Zinc", "ECO_0000255", "H", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1175", "1175", "Zinc", "ECO_0000255", "H", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1123", "1123", "Zinc", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1123", "1123", "Zinc", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1125", "1125", "Zinc", "ECO_0000255", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "1125", "1125", "Zinc", "ECO_0000255", "C", "", "protein_xref_pubmed", "PRU01166" ], [ "P26662-1", "", "Metal_Binding_Annotation", "2029", "2029", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "2011", "2011", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "2031", "2031", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Metal_Binding_Annotation", "2052", "2052", "Zinc", "", "C", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2194", "2194", "Phosphoserine; by host; in p56", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2194", "2194", "Phosphoserine; by host; in p56", "ECO_0000269", "S", "", "protein_xref_pubmed", "7769656" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2201", "2201", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2201", "2201", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_pubmed", "7769656" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2197", "2197", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2197", "2197", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_pubmed", "7769656" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2204", "2204", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2204", "2204", "Phosphoserine; by host; in p58", "ECO_0000269", "S", "", "protein_xref_pubmed", "7769656" ], [ "P26662-1", "", "Modified_Residue_Annotation", "53", "53", "Phosphoserine; by host", "", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "99", "99", "Phosphoserine; by host", "", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "116", "116", "Phosphoserine; by host PKA", "", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Modified_Residue_Annotation", "2", "2", "N-acetylserine; by host", "", "S", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "NP_Binding_Annotation", "1230", "1237", "ATP", "ECO_0000255", "APTGSGKS", "", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "NP_Binding_Annotation", "1230", "1237", "ATP", "ECO_0000255", "APTGSGKS", "", "protein_xref_pubmed", "PRU00541" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1107", "1107", "Complete loss of serine protease NS3 activity.", "ECO_0000269", "D", "A", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1107", "1107", "Complete loss of serine protease NS3 activity.", "ECO_0000269", "D", "A", "protein_xref_pubmed", "8392606" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1107", "1107", "Complete loss of serine protease NS3 activity.", "ECO_0000269", "D", "A", "protein_xref_pubmed", "8389908" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1229", "1229", "No effect on polyprotein processing. No effect on zinc-binding by serine protease NS3.", "ECO_0000269", "H", "A", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1229", "1229", "No effect on polyprotein processing. No effect on zinc-binding by serine protease NS3.", "ECO_0000269", "H", "A", "protein_xref_pubmed", "9060645" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1229", "1229", "No effect on polyprotein processing. No effect on zinc-binding by serine protease NS3.", "ECO_0000269", "H", "A", "protein_xref_pubmed", "8392606" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1058", "1058", "No effect on polyprotein processing.", "ECO_0000269", "E", "Q", "protein_xref_uniprotkb", "P26662" ], [ "P26662-1", "", "Mutagenesis_Annotation", "1058", "1058", "No effect on polyprotein processing.", "ECO_0000269", "E", "Q", "protein_xref_pubmed", "8392606" ], [ "P26662-1", "", "Mutagenesis_Annotation", "922", "922", "No effect on polyprotein processing.", "ECO_0000269", "C", "A", "protein_xref_uniprotkb", "P26662" ] ] }, "readme": "Name\n - HCV1b Protein Site Annotation\n\nVersion\n - 1.7.10\n\nCreated on\n - 2020-03-14T17:19:20.779869\n\nModified on\n - 2020-04-09T18:07:37.578247\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 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] 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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.10/reviewed/uniprot-proteome-homo-sapiens.nt\n Name: hcv1b_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.7.10/reviewed/hcv1b_protein_masterlist.csv\n Output Subdomain\n Name: hcv1b_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.10/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv\n Name: hcv1b_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.7.10/reviewed/hcv1b_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"ann_type\"\n Description: \"Annotation Type\"\n Unique Values: \"7\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"10\"\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: \"1\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"21\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"82\"\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: \"82\"\n Name: \"annotation\"\n Description: \"Function annotation from UniProtKB|RefSeq database\"\n Unique Values: \"36\"\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/hcv1b_protein_site_annotation_uniprotkb.csv" }