{ "bcoid": "GLY_000039", "title": "Mouse Glycosylation Sites (UniProtKB)", "description": "The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions ...", "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Mus musculus" ], "molecule": [ "Proteoform" ], "tag": [ "Glycosylation Sites" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q8CFG9-1...", "124..." ], [ "P23188-1...", "387..." ] ], "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" } ], [ "Q8CFG9-1", "124", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8CFG9", "protein_xref_uniprotkb_gly", "Q8CFG9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "124", "124", "Asn", "Asn", "N" ], [ "P23188-1", "387", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P23188", "protein_xref_uniprotkb_gly", "P23188", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NLT", "NXT", "387", "387", "Asn", "Asn", "N" ], [ "P23188-1", "387", "Asn", "", "N-linked", "protein_xref_pubmed", "12794637", "protein_xref_uniprotkb_gly", "P23188", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NLT", "NXT", "387", "387", "Asn", "Asn", "N" ], [ "P23188-1", "387", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P23188", "protein_xref_uniprotkb_gly", "P23188", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NLT", "NXT", "387", "387", "Asn", "Asn", "N" ], [ "P23188-1", "387", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "1P8J", "protein_xref_uniprotkb_gly", "P23188", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007744", "", "GlcNAc...", "", "NLT", "NXT", "387", "387", "Asn", "Asn", "N" ], [ "Q9QXX0-1", "1045", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9QXX0", "protein_xref_uniprotkb_gly", "Q9QXX0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "1045", "1045", "Asn", "Asn", "N" ], [ "Q8JZM8-1", "2359", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q8JZM8", "protein_xref_uniprotkb_gly", "Q8JZM8", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "2359", "2359", "Thr", "Thr", "T" ], [ "Q9ES57-1", "29", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9ES57", "protein_xref_uniprotkb_gly", "Q9ES57", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQT", "NXT", "29", "29", "Asn", "Asn", "N" ], [ "Q8R4Y4-1", "416", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8R4Y4", "protein_xref_uniprotkb_gly", "Q8R4Y4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAT", "NXT", "416", "416", "Asn", "Asn", "N" ], [ "B2RPV6-1", "810", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B2RPV6", "protein_xref_uniprotkb_gly", "B2RPV6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NET", "NXT", "810", "810", "Asn", "Asn", "N" ], [ "Q5QD11-1", "34", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q5QD11", "protein_xref_uniprotkb_gly", "Q5QD11", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "34", "34", "Asn", "Asn", "N" ], [ "Q810U4-1", "371", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q810U4", "protein_xref_uniprotkb_gly", "Q810U4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "371", "371", "Asn", "Asn", "N" ], [ "G3XA59-1", "309", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "G3XA59", "protein_xref_uniprotkb_gly", "G3XA59", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "309", "309", "Asn", "Asn", "N" ], [ "Q03391-1", "381", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q03391", "protein_xref_uniprotkb_gly", "Q03391", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NPS", "NXS", "381", "381", "Asn", "Asn", "N" ], [ "Q99K41-1", "767", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q99K41", "protein_xref_uniprotkb_gly", "Q99K41", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "767", "767", "Asn", "Asn", "N" ], [ "Q8JZM8-1", "1604", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q8JZM8", "protein_xref_uniprotkb_gly", "Q8JZM8", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "1604", "1604", "Thr", "Thr", "T" ], [ "Q8BUV8-1", "64", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8BUV8", "protein_xref_uniprotkb_gly", "Q8BUV8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVS", "NXS", "64", "64", "Asn", "Asn", "N" ], [ "Q9ES57-1", "93", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9ES57", "protein_xref_uniprotkb_gly", "Q9ES57", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NET", "NXT", "93", "93", "Asn", "Asn", "N" ], [ "Q9ES57-1", "93", "Asn", "", "N-linked", "protein_xref_pubmed", "23602662", "protein_xref_uniprotkb_gly", "Q9ES57", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NET", "NXT", "93", "93", "Asn", "Asn", "N" ], [ "Q8K596-1", "130", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8K596", "protein_xref_uniprotkb_gly", "Q8K596", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "130", "130", "Asn", "Asn", "N" ], [ "Q9EQ16-1", "24", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9EQ16", "protein_xref_uniprotkb_gly", "Q9EQ16", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "24", "24", "Asn", "Asn", "N" ], [ "Q61200-1", "93", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q61200", "protein_xref_uniprotkb_gly", "Q61200", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "93", "93", "Asn", "Asn", "N" ], [ "P24063-1", "728", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P24063", "protein_xref_uniprotkb_gly", "P24063", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "728", "728", "Asn", "Asn", "N" ], [ "Q06335-1", "570", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "Q06335", "protein_xref_uniprotkb_gly", "Q06335", "O-linked (Xyl...) (chondroitin sulfate) serine", "UniProtKB", "ECO_0000250", "", "Xyl...", "", "", "", "570", "570", "Ser", "Ser", "S" ], [ "P55849-1", "130", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P55849", "protein_xref_uniprotkb_gly", "P55849", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "130", "130", "Asn", "Asn", "N" ], [ "Q8BHY3-1", "806", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8BHY3", "protein_xref_uniprotkb_gly", "Q8BHY3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NHT", "NXT", "806", "806", "Asn", "Asn", "N" ], [ "O88721-1", "185", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O88721", "protein_xref_uniprotkb_gly", "O88721", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "185", "185", "Asn", "Asn", "N" ], [ "Q9JKV7-1", "480", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9JKV7", "protein_xref_uniprotkb_gly", "Q9JKV7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "480", "480", "Asn", "Asn", "N" ], [ "O89090-1", "641", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "O89090", "protein_xref_uniprotkb_gly", "O89090", "O-linked (GlcNAc) threonine; alternate", "", "", "", "GlcNAc", "O-GlcNAcylation", "", "", "641", "641", "Thr", "Thr", "T" ], [ "Q2VWQ2-1", "562", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q2VWQ2", "protein_xref_uniprotkb_gly", "Q2VWQ2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NHS", "NXS", "562", "562", "Asn", "Asn", "N" ], [ "Q05117-1", "149", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q05117", "protein_xref_uniprotkb_gly", "Q05117", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "149", "149", "Asn", "Asn", "N" ], [ "Q8BFR4-1", "441", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8BFR4", "protein_xref_uniprotkb_gly", "Q8BFR4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNT", "NXT", "441", "441", "Asn", "Asn", "N" ], [ "Q60677-1", "314", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q60677", "protein_xref_uniprotkb_gly", "Q60677", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "314", "314", "Asn", "Asn", "N" ], [ "A7XV04-1", "92", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A7XV04", "protein_xref_uniprotkb_gly", "A7XV04", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "92", "92", "Asn", "Asn", "N" ], [ "P28665-1", "871", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P28665", "protein_xref_uniprotkb_gly", "P28665", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NFS", "NXS", "871", "871", "Asn", "Asn", "N" ], [ "P28665-1", "871", "Asn", "", "N-linked", "protein_xref_pubmed", "17330941", "protein_xref_uniprotkb_gly", "P28665", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NFS", "NXS", "871", "871", "Asn", "Asn", "N" ], [ "P55284-1", "523", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P55284", "protein_xref_uniprotkb_gly", "P55284", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFT", "NXT", "523", "523", "Asn", "Asn", "N" ], [ "B1AWN6-1", "285", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B1AWN6", "protein_xref_uniprotkb_gly", "B1AWN6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "285", "285", "Asn", "Asn", "N" ], [ "Q9JHI4-1", "174", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9JHI4", "protein_xref_uniprotkb_gly", "Q9JHI4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "174", "174", "Asn", "Asn", "N" ], [ "Q06806-1", "705", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q06806", "protein_xref_uniprotkb_gly", "Q06806", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "705", "705", "Asn", "Asn", "N" ], [ "Q80WV3-1", "243", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q80WV3", "protein_xref_uniprotkb_gly", "Q80WV3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "243", "243", "Asn", "Asn", "N" ], [ "Q8JZM8-1", "588", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q8JZM8", "protein_xref_uniprotkb_gly", "Q8JZM8", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "588", "588", "Thr", "Thr", "T" ], [ "Q91YK8-1", "178", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91YK8", "protein_xref_uniprotkb_gly", "Q91YK8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "178", "178", "Asn", "Asn", "N" ], [ "Q8BJD1-1", "776", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8BJD1", "protein_xref_uniprotkb_gly", "Q8BJD1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQS", "NXS", "776", "776", "Asn", "Asn", "N" ], [ "P80560-1", "550", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P80560", "protein_xref_uniprotkb_gly", "P80560", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NMT", "NXT", "550", "550", "Asn", "Asn", "N" ], [ "Q2QI47-1", "4756", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q2QI47", "protein_xref_uniprotkb_gly", "Q2QI47", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "4756", "4756", "Asn", "Asn", "N" ], [ "Q9EP78-1", "87", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9EP78", "protein_xref_uniprotkb_gly", "Q9EP78", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "87", "87", "Asn", "Asn", "N" ], [ "Q8CG65-1", "4799", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8CG65", "protein_xref_uniprotkb_gly", "Q8CG65", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NMT", "NXT", "4799", "4799", "Asn", "Asn", "N" ], [ "Q9Z0T6-1", "1607", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9Z0T6", "protein_xref_uniprotkb_gly", "Q9Z0T6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NDS", "NXS", "1607", "1607", "Asn", "Asn", "N" ], [ "O54799-1", "8", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O54799", "protein_xref_uniprotkb_gly", "O54799", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLS", "NXS", "8", "8", "Asn", "Asn", "N" ], [ "A2AJX4-1", "1380", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A2AJX4", "protein_xref_uniprotkb_gly", "A2AJX4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "1380", "1380", "Asn", "Asn", "N" ], [ "P49194-1", "205", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P49194", "protein_xref_uniprotkb_gly", "P49194", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTT", "NXT", "205", "205", "Asn", "Asn", "N" ], [ "Q91ZC4-1", "151", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91ZC4", "protein_xref_uniprotkb_gly", "Q91ZC4", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFS", "NXS", "151", "151", "Asn", "Asn", "N" ], [ "P08071-1", "118", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P08071", "protein_xref_uniprotkb_gly", "P08071", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "118", "118", "Asn", "Asn", "N" ], [ "Q61702-1", "282", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q61702", "protein_xref_uniprotkb_gly", "Q61702", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "282", "282", "Asn", "Asn", "N" ], [ "Q80Z19-1", "4017", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q80Z19", "protein_xref_uniprotkb_gly", "Q80Z19", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "4017", "4017", "Asn", "Asn", "N" ], [ "Q80Z19-1", "4017", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "Q80Z19", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "4017", "4017", "Asn", "Asn", "N" ], [ "Q91XZ0-1", "419", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91XZ0", "protein_xref_uniprotkb_gly", "Q91XZ0", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NIT", "NXT", "419", "419", "Asn", "Asn", "N" ], [ "Q91XZ0-1", "419", "Asn", "", "N-linked", "protein_xref_pdb4glycosylation", "5SZL", "protein_xref_uniprotkb_gly", "Q91XZ0", "N-linked (GlcNAc...) asparagine", "PDB", "ECO_0007829", "", "GlcNAc...", "", "NIT", "NXT", "419", "419", "Asn", "Asn", "N" ], [ "O88839-1", "238", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O88839", "protein_xref_uniprotkb_gly", "O88839", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "238", "238", "Asn", "Asn", "N" ], [ "P32648-1", "133", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P32648", "protein_xref_uniprotkb_gly", "P32648", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "133", "133", "Asn", "Asn", "N" ], [ "Q68SA9-1", "84", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q68SA9", "protein_xref_uniprotkb_gly", "Q68SA9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "84", "84", "Asn", "Asn", "N" ], [ "Q8JZM8-1", "1874", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q8JZM8", "protein_xref_uniprotkb_gly", "Q8JZM8", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "1874", "1874", "Thr", "Thr", "T" ], [ "Q91ZB9-1", "11", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91ZB9", "protein_xref_uniprotkb_gly", "Q91ZB9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNT", "NXT", "11", "11", "Asn", "Asn", "N" ], [ "Q62011-1", "51", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "Q62011", "protein_xref_uniprotkb_gly", "Q62011", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "51", "51", "Thr", "Thr", "T" ], [ "Q9JJ04-1", "335", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9JJ04", "protein_xref_uniprotkb_gly", "Q9JJ04", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "335", "335", "Asn", "Asn", "N" ], [ "Q91ZX7-1", "1196", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91ZX7", "protein_xref_uniprotkb_gly", "Q91ZX7", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCS", "NXS", "1196", "1196", "Asn", "Asn", "N" ], [ "Q61282-1", "1220", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "Q61282", "protein_xref_uniprotkb_gly", "Q61282", "O-linked (Xyl...) (chondroitin sulfate) serine", "UniProtKB", "ECO_0000250", "", "Xyl...", "", "", "", "1220", "1220", "Ser", "Ser", "S" ], [ "Q5DID3-1", "90", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q5DID3", "protein_xref_uniprotkb_gly", "Q5DID3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "90", "90", "Asn", "Asn", "N" ], [ "P06802-1", "567", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P06802", "protein_xref_uniprotkb_gly", "P06802", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NGS", "NXS", "567", "567", "Asn", "Asn", "N" ], [ "P06802-1", "567", "Asn", "", "N-linked", "protein_xref_pubmed", "23027977", "protein_xref_uniprotkb_gly", "P06802", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NGS", "NXS", "567", "567", "Asn", "Asn", "N" ], [ "P06802-1", "567", "Asn", "", "N-linked", "protein_xref_pubmed", "23041369", "protein_xref_uniprotkb_gly", "P06802", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NGS", "NXS", "567", "567", "Asn", "Asn", "N" ], [ "Q9EPT5-1", "134", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9EPT5", "protein_xref_uniprotkb_gly", "Q9EPT5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "134", "134", "Asn", "Asn", "N" ], [ "Q812C9-1", "589", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q812C9", "protein_xref_uniprotkb_gly", "Q812C9", "N-linked (GlcNAc...) (complex) asparagine", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "Complex", "NQT", "NXT", "589", "589", "Asn", "Asn", "N" ], [ "Q91XX7-1", "474", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "Q91XX7", "protein_xref_uniprotkb_gly", "Q91XX7", "O-linked (Man...) serine", "PDB", "ECO_0007829", "", "Man...", "O-mannosylation", "", "", "474", "474", "Ser", "Ser", "S" ], [ "Q91XX7-1", "474", "Ser", "", "O-linked", "protein_xref_pdb4glycosylation", "5SZR", "protein_xref_uniprotkb_gly", "Q91XX7", "O-linked (Man...) serine", "PDB", "ECO_0007829", "", "Man...", "O-mannosylation", "", "", "474", "474", "Ser", "Ser", "S" ], [ "Q07113-1", "2129", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q07113", "protein_xref_uniprotkb_gly", "Q07113", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "2129", "2129", "Asn", "Asn", "N" ], [ "Q9QUN9-1", "204", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9QUN9", "protein_xref_uniprotkb_gly", "Q9QUN9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "204", "204", "Asn", "Asn", "N" ], [ "P52800-1", "39", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P52800", "protein_xref_uniprotkb_gly", "P52800", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NSS", "NXS", "39", "39", "Asn", "Asn", "N" ], [ "P52800-1", "39", "Asn", "", "N-linked", "protein_xref_pubmed", "11703926", "protein_xref_uniprotkb_gly", "P52800", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NSS", "NXS", "39", "39", "Asn", "Asn", "N" ], [ "Q91WW3-1", "159", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q91WW3", "protein_xref_uniprotkb_gly", "Q91WW3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "159", "159", "Asn", "Asn", "N" ], [ "Q01815-1", "328", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F8WJL1", "protein_xref_uniprotkb_gly", "F8WJL1", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGT", "NXT", "328", "328", "Asn", "Asn", "N" ], [ "Q01815-1", "328", "Asn", "", "N-linked", "protein_xref_pirsr", "PIRSR602077-3", "protein_xref_uniprotkb_gly", "F8WJL1", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGT", "NXT", "328", "328", "Asn", "Asn", "N" ], [ "Q8BRG8-1", "57", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8BRG8", "protein_xref_uniprotkb_gly", "Q8BRG8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "57", "57", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Mouse Glycosylation Sites (UniProtKB)\n\nVersion\n - v-2.3.1\n\nCreated on\n - 2019-01-23T17:21:05.906744\n\nModified on\n - 2024-01-03T19:39:57\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 Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Mus musculus 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-mus-musculus.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-mus-musculus.nt\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv\n Name: mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"3845\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"2154\"\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: \"4239\"\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: \"3884\"\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: \"57\"\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: \"12\"\n Name: \"carb_name\"\n Description: \"carbohydrate name\"\n Unique Values: \"14\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"11\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"50\"\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: \"2154\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"2154\"\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/mouse_proteoform_glycosylation_sites_uniprotkb.csv" }