{ "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": "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", "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", "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", "", "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", "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", "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", "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", "16862121" ], [ "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", "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_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_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", "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", "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", "", "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", "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", "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", "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", "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", "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", "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", "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", "746", "747", "Cleavage; by host signal peptidase", "", "AA", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Site_Annotation", "809", "810", "Cleavage; by host signal peptidase", "", "AL", "", "protein_xref_uniprotkb", "P27958" ], [ "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", "", "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", "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", "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", "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", "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", "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", "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", "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", "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", "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", "24288331" ], [ "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", "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", "", "Metal_Binding_Annotation", "2640", "2640", "Magnesium; catalytic; for RNA-directed RNA polymerase activity", "ECO_0000250", "D", "", "protein_xref_uniprotkb", "P27958" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2640", "2640", "Magnesium; catalytic; for RNA-directed RNA polymerase activity", "ECO_0000250", "D", "", "protein_xref_pubmed", "P26663" ], [ "P27958-1", "", "Metal_Binding_Annotation", "2031", "2031", "Zinc; structural", "ECO_0000250", "C", "", "protein_xref_uniprotkb", "P27958" ] ] }, "readme": "Name\n - HCV1a Protein Site Annotation\n\nVersion\n - 1.8.25\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/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt\n Name: hcv1a_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv\n Output Subdomain\n Name: hcv1a_protein_site_annotation_uniprotkb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv\n Name: hcv1a_protein_site_annotation_uniprotkb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"119\"\n Name: \"title\"\n Description: \"Title of the published article in the journal\"\n Unique Values: \"119\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"120\"\n Name: \"journal_name\"\n Description: \"The name of the journal in which the article is published\"\n Unique Values: \"49\"\n Name: \"authors\"\n Description: \"NA\"\n Unique Values: \"118\"\n Name: \"publication_date\"\n Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n Unique Values: \"117\"\n Name: \"glytoucan_ac\"\n Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n Unique Values: \"115\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv" }