{ "bcoid": "GLY_000495", "title": "SARS-CoV1 Glycosylation Sites (UniProtKB)", "description": "The SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] ...", "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": "SARS coronavirus (SARS-CoV-1)", "molecule": "Proteoform", "tags": "Glycosylation Sites", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P59594-1...", "1080..." ], [ "P59594-1...", "1080..." ] ], "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" } ], [ "P59594-1", "1080", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NGT", "NXT" ], [ "P59594-1", "1080", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NGT", "NXT" ], [ "P59632-1", "34", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P59632", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) threonine; by host", "", "", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59594-1", "783", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS" ], [ "P59594-1", "783", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS" ], [ "P59594-1", "118", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNS", "NXS" ], [ "P59594-1", "118", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNS", "NXS" ], [ "P59594-1", "269", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NGT", "NXT" ], [ "P59594-1", "269", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NGT", "NXT" ], [ "P59594-1", "691", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT" ], [ "P59594-1", "691", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT" ], [ "P59632-1", "27", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P59632", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) serine; by host", "", "", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59594-1", "602", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NCT", "NXT" ], [ "P59594-1", "602", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NCT", "NXT" ], [ "P59632-1", "28", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P59632", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) threonine; by host", "PubMed", "ECO_0000305", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59632-1", "28", "Thr", "", "O-linked", "protein_xref_pubmed", "16474139", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) threonine; by host", "PubMed", "ECO_0000305", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59594-1", "119", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NST", "NXT" ], [ "P59594-1", "119", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NST", "NXT" ], [ "P59594-1", "73", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT" ], [ "P59594-1", "73", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT" ], [ "P59594-1", "65", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NVT", "NXT" ], [ "P59594-1", "65", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NVT", "NXT" ], [ "P59594-1", "699", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS" ], [ "P59594-1", "699", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFS", "NXS" ], [ "P59594-1", "330", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAT", "NXT" ], [ "P59594-1", "330", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAT", "NXT" ], [ "P59594-1", "1176", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NES", "NXS" ], [ "P59594-1", "1176", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NES", "NXS" ], [ "P59594-1", "1056", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFT", "NXT" ], [ "P59594-1", "1056", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NFT", "NXT" ], [ "P59594-1", "29", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NYT", "NXT" ], [ "P59594-1", "29", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NYT", "NXT" ], [ "P59594-1", "1155", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAS", "NXS" ], [ "P59594-1", "1155", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAS", "NXS" ], [ "P59594-1", "227", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT" ], [ "P59594-1", "227", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT" ], [ "P59594-1", "1140", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT" ], [ "P59594-1", "1140", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NHT", "NXT" ], [ "P59632-1", "32", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P59632", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) threonine; by host", "PubMed", "ECO_0000305", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59632-1", "32", "Thr", "", "O-linked", "protein_xref_pubmed", "16474139", "protein_xref_uniprotkb_gly", "P59632", "O-linked (GalNAc...) threonine; by host", "PubMed", "ECO_0000305", "", "GalNAc...", "O-GalNAcylation", "", "" ], [ "P59594-1", "158", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NCT", "NXT" ], [ "P59594-1", "158", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NCT", "NXT" ], [ "P59594-1", "1116", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT" ], [ "P59594-1", "1116", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT" ], [ "P59594-1", "318", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT" ], [ "P59594-1", "318", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT" ], [ "P59594-1", "357", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NST", "NXT" ], [ "P59594-1", "357", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NST", "NXT" ], [ "P59594-1", "109", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NKS", "NXS" ], [ "P59594-1", "109", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NKS", "NXS" ], [ "P59594-1", "589", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P59594", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAS", "NXS" ], [ "P59594-1", "589", "Asn", "", "N-linked", "protein_xref_hamap-rule", "MF_04099", "protein_xref_uniprotkb_gly", "P59594", "N-linked (GlcNAc...) asparagine; by host", "hamap-rule", "ECO_0000255", "", "GlcNAc...", "", "NAS", "NXS" ] ] }, "readme": "Name\n - SARS-CoV1 Glycosylation Sites (UniProtKB)\n\nVersion\n - 1.8.24\n\nCreated on\n - 2020-05-07T18:18:49.168950\n\nModified on\n - 2020-05-07T18:19:55.454009\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 SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 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-human-sars-coronavirus.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/source/uniprot-proteome-human-sars-coronavirus.nt\n Name: sarscov1_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/sarscov1_protein_masterlist.csv\n Output Subdomain\n Name: sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n URI: http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n Name: sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_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-1.8.24/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv" }