{ "bcoid": "GLY_000038", "title": "Human Glycosylation Sites (UniProtKB)", "description": "The Human Glycosylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions ...", "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Homo sapiens" ], "molecule": [ "Proteoform" ], "tag": [ "Glycosylation Sites" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "P15848-1...", "426..." ], [ "Q9UIQ6-1...", "525..." ] ], "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" } ], [ "P15848-1", "426", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P15848", "protein_xref_uniprotkb_gly", "P15848", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "426", "426", "Asn", "Asn", "N" ], [ "Q9UIQ6-1", "525", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9UIQ6", "protein_xref_uniprotkb_gly", "Q9UIQ6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "525", "525", "Asn", "Asn", "N" ], [ "Q7L985-1", "188", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7L985", "protein_xref_uniprotkb_gly", "Q7L985", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "188", "188", "Asn", "Asn", "N" ], [ "P98164-1", "3978", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P98164", "protein_xref_uniprotkb_gly", "P98164", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCT", "NXT", "3978", "3978", "Asn", "Asn", "N" ], [ "P04921-1", "9", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P04921", "protein_xref_uniprotkb_gly", "P04921", "O-linked (GalNAc...) serine", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "9", "9", "Ser", "Ser", "S" ], [ "P04921-1", "9", "Ser", "", "O-linked", "protein_xref_pubmed", "7106126", "protein_xref_uniprotkb_gly", "P04921", "O-linked (GalNAc...) serine", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "9", "9", "Ser", "Ser", "S" ], [ "O75094-1", "1025", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O75094", "protein_xref_uniprotkb_gly", "O75094", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "1025", "1025", "Asn", "Asn", "N" ], [ "Q15910-1", "75", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "Q15910", "protein_xref_uniprotkb_gly", "Q15910", "O-linked (GlcNAc) serine", "PubMed", "ECO_0000269", "", "GlcNAc", "O-GlcNAcylation", "", "", "75", "75", "Ser", "Ser", "S" ], [ "Q15910-1", "75", "Ser", "", "O-linked", "protein_xref_pubmed", "24474760", "protein_xref_uniprotkb_gly", "Q15910", "O-linked (GlcNAc) serine", "PubMed", "ECO_0000269", "", "GlcNAc", "O-GlcNAcylation", "", "", "75", "75", "Ser", "Ser", "S" ], [ "Q9UMF0-1", "795", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9UMF0", "protein_xref_uniprotkb_gly", "Q9UMF0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "795", "795", "Asn", "Asn", "N" ], [ "Q9UJW2-1", "360", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9UJW2", "protein_xref_uniprotkb_gly", "Q9UJW2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "360", "360", "Asn", "Asn", "N" ], [ "Q8N1N0-1", "244", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8N1N0", "protein_xref_uniprotkb_gly", "Q8N1N0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "244", "244", "Asn", "Asn", "N" ], [ "Q95460-1", "107", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q95460", "protein_xref_uniprotkb_gly", "Q95460", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NHS", "NXS", "107", "107", "Asn", "Asn", "N" ], [ "Q95460-1", "107", "Asn", "", "N-linked", "protein_xref_pubmed", "12794138", "protein_xref_uniprotkb_gly", "Q95460", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NHS", "NXS", "107", "107", "Asn", "Asn", "N" ], [ "A1E959-1", "244", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "A1E959", "protein_xref_uniprotkb_gly", "A1E959", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "244", "244", "Thr", "Thr", "T" ], [ "P49908-1", "338", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P49908", "protein_xref_uniprotkb_gly", "P49908", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "338", "338", "Asn", "Asn", "N" ], [ "Q9UKJ8-1", "164", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9UKJ8", "protein_xref_uniprotkb_gly", "Q9UKJ8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "164", "164", "Asn", "Asn", "N" ], [ "Q5T6X5-1", "121", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q5T6X5", "protein_xref_uniprotkb_gly", "Q5T6X5", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NCS", "NXS", "121", "121", "Asn", "Asn", "N" ], [ "Q5T6X5-1", "121", "Asn", "", "N-linked", "protein_xref_pubmed", "25617829", "protein_xref_uniprotkb_gly", "Q5T6X5", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NCS", "NXS", "121", "121", "Asn", "Asn", "N" ], [ "Q3KNS1-1", "692", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q3KNS1", "protein_xref_uniprotkb_gly", "Q3KNS1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "692", "692", "Asn", "Asn", "N" ], [ "Q8TC27-1", "598", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8TC27", "protein_xref_uniprotkb_gly", "Q8TC27", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "598", "598", "Asn", "Asn", "N" ], [ "Q695T7-1", "182", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q695T7", "protein_xref_uniprotkb_gly", "Q695T7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "182", "182", "Asn", "Asn", "N" ], [ "Q6V0I7-1", "416", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q6V0I7", "protein_xref_uniprotkb_gly", "Q6V0I7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "416", "416", "Asn", "Asn", "N" ], [ "P35442-1", "1069", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P35442", "protein_xref_uniprotkb_gly", "P35442", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NST", "NXT", "1069", "1069", "Asn", "Asn", "N" ], [ "P35442-1", "1069", "Asn", "", "N-linked", "protein_xref_pubmed", "16186819", "protein_xref_uniprotkb_gly", "P35442", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NST", "NXT", "1069", "1069", "Asn", "Asn", "N" ], [ "O15389-1", "384", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O15389", "protein_xref_uniprotkb_gly", "O15389", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "384", "384", "Asn", "Asn", "N" ], [ "P08648-1", "724", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P08648", "protein_xref_uniprotkb_gly", "P08648", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQS", "NXS", "724", "724", "Asn", "Asn", "N" ], [ "O14522-3", "654", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O14522", "protein_xref_uniprotkb_gly", "O14522", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "654", "654", "Asn", "Asn", "N" ], [ "Q15822-1", "79", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q15822", "protein_xref_uniprotkb_gly", "Q15822", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "79", "79", "Asn", "Asn", "N" ], [ "O00469-1", "209", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O00469", "protein_xref_uniprotkb_gly", "O00469", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NIT", "NXT", "209", "209", "Asn", "Asn", "N" ], [ "O00469-1", "209", "Asn", "", "N-linked", "protein_xref_pubmed", "19159218", "protein_xref_uniprotkb_gly", "O00469", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NIT", "NXT", "209", "209", "Asn", "Asn", "N" ], [ "Q75N90-1", "1658", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q75N90", "protein_xref_uniprotkb_gly", "Q75N90", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "1658", "1658", "Asn", "Asn", "N" ], [ "Q9H293-1", "136", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9H293", "protein_xref_uniprotkb_gly", "Q9H293", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQT", "NXT", "136", "136", "Asn", "Asn", "N" ], [ "P60509-1", "226", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P60509", "protein_xref_uniprotkb_gly", "P60509", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "226", "226", "Asn", "Asn", "N" ], [ "P14780-1", "127", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P14780", "protein_xref_uniprotkb_gly", "P14780", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "127", "127", "Asn", "Asn", "N" ], [ "Q9HC84-1", "5526", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9HC84", "protein_xref_uniprotkb_gly", "Q9HC84", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "5526", "5526", "Asn", "Asn", "N" ], [ "Q7L1S5-1", "243", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7L1S5", "protein_xref_uniprotkb_gly", "Q7L1S5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "243", "243", "Asn", "Asn", "N" ], [ "Q92954-1", "769", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q92954", "protein_xref_uniprotkb_gly", "Q92954", "O-linked (GalNAc...) threonine", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "769", "769", "Thr", "Thr", "T" ], [ "Q92954-1", "769", "Thr", "", "O-linked", "protein_xref_pubmed", "25187573", "protein_xref_uniprotkb_gly", "Q92954", "O-linked (GalNAc...) threonine", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "769", "769", "Thr", "Thr", "T" ], [ "Q9Y4C0-1", "58", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9Y4C0", "protein_xref_uniprotkb_gly", "Q9Y4C0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVS", "NXS", "58", "58", "Asn", "Asn", "N" ], [ "O75976-1", "399", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O75976", "protein_xref_uniprotkb_gly", "O75976", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAT", "NXT", "399", "399", "Asn", "Asn", "N" ], [ "Q99102-1", "1182", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q99102", "protein_xref_uniprotkb_gly", "Q99102", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "1182", "1182", "Thr", "Thr", "T" ], [ "Q9UBS5-1", "409", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9UBS5", "protein_xref_uniprotkb_gly", "Q9UBS5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCT", "NXT", "409", "409", "Asn", "Asn", "N" ], [ "P35916-2", "166", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P35916", "protein_xref_uniprotkb_gly", "P35916", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "166", "166", "Asn", "Asn", "N" ], [ "Q7Z5N4-1", "821", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7Z5N4", "protein_xref_uniprotkb_gly", "Q7Z5N4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "821", "821", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P10253", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_pubmed", "19159218", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_pubmed", "8435067", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_pubmed", "29061980", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P10253", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "5NN3", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "P10253-1", "882", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "5KZW", "protein_xref_uniprotkb_gly", "P10253", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NNT", "NXT", "882", "882", "Asn", "Asn", "N" ], [ "Q9BU40-6", "291", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9BU40", "protein_xref_uniprotkb_gly", "Q9BU40", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "291", "291", "Asn", "Asn", "N" ], [ "P98088-1", "4522", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P98088", "protein_xref_uniprotkb_gly", "P98088", "O-linked (GalNAc) threonine", "PubMed", "ECO_0000269", "", "GalNAc", "O-GalNAcylation", "", "", "4522", "4522", "Thr", "Thr", "T" ], [ "P98088-1", "4522", "Thr", "", "O-linked", "protein_xref_pubmed", "25939779", "protein_xref_uniprotkb_gly", "P98088", "O-linked (GalNAc) threonine", "PubMed", "ECO_0000269", "", "GalNAc", "O-GalNAcylation", "", "", "4522", "4522", "Thr", "Thr", "T" ], [ "P98088-1", "4522", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P98088", "protein_xref_uniprotkb_gly", "P98088", "O-linked (GalNAc) threonine", "PDB", "ECO_0007744", "", "GalNAc", "O-GalNAcylation", "", "", "4522", "4522", "Thr", "Thr", "T" ], [ "P98088-1", "4522", "Thr", "", "O-linked", "protein_xref_pdb4glycosylation", "5AJO", "protein_xref_uniprotkb_gly", "P98088", "O-linked (GalNAc) threonine", "PDB", "ECO_0007744", "", "GalNAc", "O-GalNAcylation", "", "", "4522", "4522", "Thr", "Thr", "T" ], [ "P98088-1", "4522", "Thr", "", "O-linked", "protein_xref_pdb4glycosylation", "5AJP", "protein_xref_uniprotkb_gly", "P98088", "O-linked (GalNAc) threonine", "PDB", "ECO_0007744", "", "GalNAc", "O-GalNAcylation", "", "", "4522", "4522", "Thr", "Thr", "T" ], [ "P06133-1", "315", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P06133", "protein_xref_uniprotkb_gly", "P06133", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NTS", "NXS", "315", "315", "Asn", "Asn", "N" ], [ "P06133-1", "315", "Asn", "", "N-linked", "protein_xref_pubmed", "19159218", "protein_xref_uniprotkb_gly", "P06133", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NTS", "NXS", "315", "315", "Asn", "Asn", "N" ], [ "P08183-1", "99", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P08183", "protein_xref_uniprotkb_gly", "P08183", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDT", "NXT", "99", "99", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P02749", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "19838169", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "19159218", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "14760718", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "16335952", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "6587378", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "16740002", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "19139490", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "P02749-1", "162", "Asn", "", "N-linked", "protein_xref_pubmed", "15084671", "protein_xref_uniprotkb_gly", "P02749", "N-linked (GlcNAc...) (complex) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "Complex", "NNS", "NXS", "162", "162", "Asn", "Asn", "N" ], [ "Q96DR5-1", "132", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q96DR5", "protein_xref_uniprotkb_gly", "Q96DR5", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NVT", "NXT", "132", "132", "Asn", "Asn", "N" ], [ "Q96DR5-1", "132", "Asn", "", "N-linked", "protein_xref_pubmed", "16740002", "protein_xref_uniprotkb_gly", "Q96DR5", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NVT", "NXT", "132", "132", "Asn", "Asn", "N" ], [ "Q6UWL2-1", "112", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q6UWL2", "protein_xref_uniprotkb_gly", "Q6UWL2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NKT", "NXT", "112", "112", "Asn", "Asn", "N" ], [ "P20701-1", "726", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P20701", "protein_xref_uniprotkb_gly", "P20701", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVS", "NXS", "726", "726", "Asn", "Asn", "N" ], [ "P61812-1", "241", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P61812", "protein_xref_uniprotkb_gly", "P61812", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NKS", "NXS", "241", "241", "Asn", "Asn", "N" ], [ "Q86SQ4-1", "258", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q86SQ4", "protein_xref_uniprotkb_gly", "Q86SQ4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "258", "258", "Asn", "Asn", "N" ], [ "P03986-1", "142", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P03986", "protein_xref_uniprotkb_gly", "P03986", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NDT", "NXT", "142", "142", "Asn", "Asn", "N" ], [ "P03986-1", "142", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "P03986", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NDT", "NXT", "142", "142", "Asn", "Asn", "N" ], [ "Q8TE57-1", "310", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8TE57", "protein_xref_uniprotkb_gly", "Q8TE57", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "310", "310", "Asn", "Asn", "N" ], [ "Q14126-1", "182", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q14126", "protein_xref_uniprotkb_gly", "Q14126", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NAT", "NXT", "182", "182", "Asn", "Asn", "N" ], [ "Q14126-1", "182", "Asn", "", "N-linked", "protein_xref_pubmed", "19349973", "protein_xref_uniprotkb_gly", "Q14126", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NAT", "NXT", "182", "182", "Asn", "Asn", "N" ], [ "Q14126-1", "182", "Asn", "", "N-linked", "protein_xref_pubmed", "19159218", "protein_xref_uniprotkb_gly", "Q14126", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NAT", "NXT", "182", "182", "Asn", "Asn", "N" ], [ "Q14126-1", "182", "Asn", "", "N-linked", "protein_xref_pubmed", "16335952", "protein_xref_uniprotkb_gly", "Q14126", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NAT", "NXT", "182", "182", "Asn", "Asn", "N" ], [ "Q9P0T7-1", "38", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9P0T7", "protein_xref_uniprotkb_gly", "Q9P0T7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "38", "38", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Human Glycosylation Sites (UniProtKB)\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2019-01-23T17:21:05.905721\n\nModified on\n - 2024-01-03T19:39:02\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@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 Human Glycosylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Homo sapiens proteome release.\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/glygener/glygen-backend-integration/blob/master/dataset-maker/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: glycosylation_subtype.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/glycosylation_subtype.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2023_10_11/cellosaurus.txt\n Name: uniprot-proteome-homo-sapiens.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv\n Name: human_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"4560\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"2741\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"7\"\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: \"4\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"6\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"5987\"\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: \"4588\"\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: \"81\"\n Name: \"data_source\"\n Description: \"The source database for the data\"\n Unique Values: \"7\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"10\"\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: \"90\"\n Name: \"carb_name\"\n Description: \"carbohydrate name\"\n Unique Values: \"18\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"12\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"68\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"2741\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"2741\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"7\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv" }