{ "bcoid": "GLY_000383", "title": "HCV1b Glycosylation Sites (UniProtKB)", "description": "The Hepatitis C virus (genotype 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains ...", "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": "Hepatitis C virus (genotype 1b, isolate Japanese)", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P26662-1...", "518..." ], [ "P26662-1...", "518..." ] ], "headers": [ "uniprotkb_ca...", "glycosylatio..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "glycosylation_site_uniprotkb" }, { "type": "string", "label": "amino_acid" }, { "type": "string", "label": "saccharide" }, { "type": "string", "label": "glycosylation_type" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "src_xref_key" }, { "type": "string", "label": "src_xref_id" }, { "type": "string", "label": "uniprotkb_glycosylation_annotation_comment" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "eco_id" }, { "type": "string", "label": "uniprotkb_ftid" }, { "type": "string", "label": "carb_name" }, { "type": "string", "label": "glycosylation_subtype" }, { "type": "string", "label": "n_sequon" }, { "type": "string", "label": "n_sequon_type" }, { "type": "string", "label": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "start_aa" }, { "type": "string", "label": "end_aa" }, { "type": "string", "label": "site_seq" } ], [ "P26662-1", "518", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "518", "518", "Thr", "Thr", "T" ], [ "P26662-1", "518", "Thr", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "518", "518", "Thr", "Thr", "T" ], [ "P26662-1", "404", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) serine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "404", "404", "Ser", "Ser", "S" ], [ "P26662-1", "404", "Ser", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) serine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "404", "404", "Ser", "Ser", "S" ], [ "P26662-1", "396", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "396", "396", "Thr", "Thr", "T" ], [ "P26662-1", "396", "Thr", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "396", "396", "Thr", "Thr", "T" ], [ "P26662-1", "234", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NFS", "NXS", "234", "234", "Asn", "Asn", "N" ], [ "P26662-1", "209", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NSS", "NXS", "209", "209", "Asn", "Asn", "N" ], [ "P26662-1", "430", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NDS", "NXS", "430", "430", "Asn", "Asn", "N" ], [ "P26662-1", "623", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NFT", "NXT", "623", "623", "Asn", "Asn", "N" ], [ "P26662-1", "305", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NCS", "NXS", "305", "305", "Asn", "Asn", "N" ], [ "P26662-1", "417", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NGS", "NXS", "417", "417", "Asn", "Asn", "N" ], [ "P26662-1", "645", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NWT", "NXT", "645", "645", "Asn", "Asn", "N" ], [ "P26662-1", "532", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NET", "NXT", "532", "532", "Asn", "Asn", "N" ], [ "P26662-1", "385", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000305", "", "Hex...", "Other", "", "", "385", "385", "Thr", "Thr", "T" ], [ "P26662-1", "385", "Thr", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000305", "", "Hex...", "Other", "", "", "385", "385", "Thr", "Thr", "T" ], [ "P26662-1", "196", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NVS", "NXS", "196", "196", "Asn", "Asn", "N" ], [ "P26662-1", "423", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NRT", "NXT", "423", "423", "Asn", "Asn", "N" ], [ "P26662-1", "576", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NNT", "NXT", "576", "576", "Asn", "Asn", "N" ], [ "P26662-1", "401", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) serine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "401", "401", "Ser", "Ser", "S" ], [ "P26662-1", "401", "Ser", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) serine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "401", "401", "Ser", "Ser", "S" ], [ "P26662-1", "556", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NST", "NXT", "556", "556", "Asn", "Asn", "N" ], [ "P26662-1", "473", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "473", "473", "Thr", "Thr", "T" ], [ "P26662-1", "473", "Thr", "", "O-linked", "protein_xref_pubmed", "23242014", "protein_xref_uniprotkb_gly", "P26662", "O-linked (Hex...) threonine; by host", "PubMed", "ECO_0000269", "", "Hex...", "Other", "", "", "473", "473", "Thr", "Thr", "T" ], [ "P26662-1", "448", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P26662", "protein_xref_uniprotkb_gly", "P26662", "N-linked (GlcNAc...) (high mannose) asparagine; by host", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "High mannose", "NAS", "NXS", "448", "448", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - HCV1b Glycosylation Sites (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T12:27:03.522584\n\nModified on\n - 2020-04-09T18:12:53.311327\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@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 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n Keywords\n - glycosylation\n - reported glycosylation\n - predicted glycosylation\n - UniProtKB\n - PubMed\n - Evidence and conclusion Ontology\n\n Pipeline Steps\n - Step-1: The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-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-1b.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2021_04/uniprot-proteome-hepatitis-c-virus-1b.nt\n Name: glycosylation_subtype.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/glycosylation_subtype.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Output Subdomain\n Name: hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n Name: hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"19\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"3\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"1\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\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: \"2\"\n Name: \"src_xref_key\"\n Description: \"Source Xref key\"\n Unique Values: \"1\"\n Name: \"src_xref_id\"\n Description: \"Source X-ref ID\"\n Unique Values: \"1\"\n Name: \"uniprotkb_glycosylation_annotation_comment\"\n Description: \"The glycosylation annotation in UniProtKB that provides more context and description about the glycosylation event on a proein\"\n Unique Values: \"4\"\n Name: \"data_source\"\n Description: \"The source database for the data\"\n Unique Values: \"2\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"3\"\n Name: \"uniprotkb_ftid\"\n Description: \"A stable feature identifier that allows to construct links directly from position-specific annotation to specialized protein-related databases. (In the dataset the FTID is for glycosylation for residues attached to an oligosaccharide structure annotated in the UniCarbKB database)\"\n Unique Values: \"1\"\n Name: \"carb_name\"\n Description: \"carbohydrate name\"\n Unique Values: \"2\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"14\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"19\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"19\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"3\"", "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv" }