{ "bcoid": "GLY_000896", "title": "Pig Glycosylation Sites (UniProtKB)", "description": "The Pig Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:9823] UniProtKB canonical accessions ...", "filename": "pig_proteoform_glycosylation_sites_uniprotkb.csv", "filetype": "csv", "categories": { "species": [ "Sus scrofa" ], "molecule": [ "Proteoform" ], "tag": [ "Glycosylation Sites" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q8MIB3-1...", "597..." ], [ "P02475-1...", "162..." ] ], "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" } ], [ "Q8MIB3-1", "597", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8MIB3", "protein_xref_uniprotkb_gly", "Q8MIB3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "597", "597", "Asn", "Asn", "N" ], [ "P02475-1", "162", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P02475", "protein_xref_uniprotkb_gly", "P02475", "O-linked (GlcNAc) serine", "", "", "", "GlcNAc", "O-GlcNAcylation", "", "", "162", "162", "Ser", "Ser", "S" ], [ "P00671-1", "21", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P00671", "protein_xref_uniprotkb_gly", "P00671", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "21", "21", "Asn", "Asn", "N" ], [ "Q2QDF0-1", "272", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q2QDF0", "protein_xref_uniprotkb_gly", "Q2QDF0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "272", "272", "Asn", "Asn", "N" ], [ "A0A1S6M251-1", "90", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A0A1S6M251", "protein_xref_uniprotkb_gly", "A0A1S6M251", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NHS", "NXS", "90", "90", "Asn", "Asn", "N" ], [ "F1RMN7-1", "188", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A0A5G2QGR8", "protein_xref_uniprotkb_gly", "A0A5G2QGR8", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NCS", "NXS", "188", "188", "Asn", "Asn", "N" ], [ "F1RMN7-1", "188", "Asn", "", "N-linked", "protein_xref_pirsr", "PIRSR002551-3", "protein_xref_uniprotkb_gly", "A0A5G2QGR8", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NCS", "NXS", "188", "188", "Asn", "Asn", "N" ], [ "B2ZHY2-1", "192", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B2ZHY2", "protein_xref_uniprotkb_gly", "B2ZHY2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "192", "192", "Asn", "Asn", "N" ], [ "Q29053-1", "96", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q29053", "protein_xref_uniprotkb_gly", "Q29053", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "96", "96", "Asn", "Asn", "N" ], [ "F1SHP1-1", "760", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1SHP1", "protein_xref_uniprotkb_gly", "F1SHP1", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGS", "NXS", "760", "760", "Asn", "Asn", "N" ], [ "F1SHP1-1", "760", "Asn", "", "N-linked", "protein_xref_pirsr", "PIRSR613274-4", "protein_xref_uniprotkb_gly", "F1SHP1", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGS", "NXS", "760", "760", "Asn", "Asn", "N" ], [ "Q95252-1", "26", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q95252", "protein_xref_uniprotkb_gly", "Q95252", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NTS", "NXS", "26", "26", "Asn", "Asn", "N" ], [ "Q29243-1", "623", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q29243", "protein_xref_uniprotkb_gly", "Q29243", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NCS", "NXS", "623", "623", "Asn", "Asn", "N" ], [ "P12021-1", "66", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "P12021", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) threonine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "66", "66", "Thr", "Thr", "T" ], [ "P12021-1", "66", "Thr", "", "O-linked", "protein_xref_pubmed", "9092502", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) threonine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "66", "66", "Thr", "Thr", "T" ], [ "Q29010-1", "62", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q29010", "protein_xref_uniprotkb_gly", "Q29010", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "62", "62", "Asn", "Asn", "N" ], [ "Q95242-1", "320", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q95242", "protein_xref_uniprotkb_gly", "Q95242", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "320", "320", "Asn", "Asn", "N" ], [ "A0A8W4F7T5-1", "285", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A0A287A2T8", "protein_xref_uniprotkb_gly", "A0A287A2T8", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGT", "NXT", "285", "285", "Asn", "Asn", "N" ], [ "A0A8W4F7T5-1", "285", "Asn", "", "N-linked", "protein_xref_pirsr", "PIRSR602077-3", "protein_xref_uniprotkb_gly", "A0A287A2T8", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NGT", "NXT", "285", "285", "Asn", "Asn", "N" ], [ "O02671-1", "276", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O02671", "protein_xref_uniprotkb_gly", "O02671", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NST", "NXT", "276", "276", "Asn", "Asn", "N" ], [ "B2ZI34-1", "16", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "B2ZI34", "protein_xref_uniprotkb_gly", "B2ZI34", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NQS", "NXS", "16", "16", "Asn", "Asn", "N" ], [ "P12021-1", "91", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P12021", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "91", "91", "Ser", "Ser", "S" ], [ "P12021-1", "91", "Ser", "", "O-linked", "protein_xref_pubmed", "9092502", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "91", "91", "Ser", "Ser", "S" ], [ "O02839-1", "304", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "O02839", "protein_xref_uniprotkb_gly", "O02839", "O-linked (GalNAc...) threonine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "304", "304", "Thr", "Thr", "T" ], [ "P12021-1", "76", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P12021", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "76", "76", "Ser", "Ser", "S" ], [ "P12021-1", "76", "Ser", "", "O-linked", "protein_xref_pubmed", "9092502", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "76", "76", "Ser", "Ser", "S" ], [ "A0A8W4FCN0-1", "193", "Thr", "", "O-linked", "protein_xref_uniprotkb_gly", "A0A8W4FCN0", "protein_xref_uniprotkb_gly", "A0A8W4FCN0", "O-linked (GlcNAc) threonine", "pirsr", "ECO_0000256", "", "GlcNAc", "O-GlcNAcylation", "", "", "193", "193", "Thr", "Thr", "T" ], [ "A0A8W4FCN0-1", "193", "Thr", "", "O-linked", "protein_xref_pirsr", "PIRSR628391-4", "protein_xref_uniprotkb_gly", "A0A8W4FCN0", "O-linked (GlcNAc) threonine", "pirsr", "ECO_0000256", "", "GlcNAc", "O-GlcNAcylation", "", "", "193", "193", "Thr", "Thr", "T" ], [ "F1RWC3-1", "2583", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1RWC3", "protein_xref_uniprotkb_gly", "F1RWC3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFT", "NXT", "2583", "2583", "Asn", "Asn", "N" ], [ "P00690-1", "427", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P00690", "protein_xref_uniprotkb_gly", "P00690", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "427", "427", "Asn", "Asn", "N" ], [ "Q863T6-1", "71", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q863T6", "protein_xref_uniprotkb_gly", "Q863T6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "71", "71", "Asn", "Asn", "N" ], [ "F1RRW5-1", "78", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1RRW5", "protein_xref_uniprotkb_gly", "F1RRW5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "78", "78", "Asn", "Asn", "N" ], [ "Q95N02-1", "6", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q95N02", "protein_xref_uniprotkb_gly", "Q95N02", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "6", "6", "Asn", "Asn", "N" ], [ "P32306-1", "26", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P32306", "protein_xref_uniprotkb_gly", "P32306", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "26", "26", "Asn", "Asn", "N" ], [ "P24786-1", "232", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P24786", "protein_xref_uniprotkb_gly", "P24786", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "232", "232", "Asn", "Asn", "N" ], [ "Q863Z5-1", "170", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q863Z5", "protein_xref_uniprotkb_gly", "Q863Z5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "170", "170", "Asn", "Asn", "N" ], [ "O02839-1", "314", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "O02839", "protein_xref_uniprotkb_gly", "O02839", "O-linked (GalNAc...) serine", "", "", "", "GalNAc...", "O-GalNAcylation", "", "", "314", "314", "Ser", "Ser", "S" ], [ "P22411-1", "150", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P22411", "protein_xref_uniprotkb_gly", "P22411", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "150", "150", "Asn", "Asn", "N" ], [ "P22411-1", "150", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "P22411", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "150", "150", "Asn", "Asn", "N" ], [ "C0HL13-1", "2778", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "C0HL13", "protein_xref_uniprotkb_gly", "C0HL13", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT", "2778", "2778", "Asn", "Asn", "N" ], [ "C0HL13-1", "2778", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "C0HL13", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NIT", "NXT", "2778", "2778", "Asn", "Asn", "N" ], [ "Q9GLP1-1", "782", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9GLP1", "protein_xref_uniprotkb_gly", "Q9GLP1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "782", "782", "Asn", "Asn", "N" ], [ "A0A287A2K5-1", "7", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A0A287A2K5", "protein_xref_uniprotkb_gly", "A0A287A2K5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "7", "7", "Asn", "Asn", "N" ], [ "A5PF10-1", "344", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "A5PF10", "protein_xref_uniprotkb_gly", "A5PF10", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "344", "344", "Asn", "Asn", "N" ], [ "Q9GLX8-1", "14", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9GLX8", "protein_xref_uniprotkb_gly", "Q9GLX8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGT", "NXT", "14", "14", "Asn", "Asn", "N" ], [ "Q2TLZ2-1", "452", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q2TLZ2", "protein_xref_uniprotkb_gly", "Q2TLZ2", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIS", "NXS", "452", "452", "Asn", "Asn", "N" ], [ "Q9GLP1-1", "1048", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9GLP1", "protein_xref_uniprotkb_gly", "Q9GLP1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NHS", "NXS", "1048", "1048", "Asn", "Asn", "N" ], [ "Q1RPR6-1", "48", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q1RPR6", "protein_xref_uniprotkb_gly", "Q1RPR6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFT", "NXT", "48", "48", "Asn", "Asn", "N" ], [ "O18766-1", "15", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O18766", "protein_xref_uniprotkb_gly", "O18766", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NKT", "NXT", "15", "15", "Asn", "Asn", "N" ], [ "O02840-1", "58", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "O02840", "protein_xref_uniprotkb_gly", "O02840", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NGS", "NXS", "58", "58", "Asn", "Asn", "N" ], [ "Q8SPS7-1", "125", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8SPS7", "protein_xref_uniprotkb_gly", "Q8SPS7", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NLT", "NXT", "125", "125", "Asn", "Asn", "N" ], [ "Q8SPS7-1", "125", "Asn", "", "N-linked", "protein_xref_pubmed", "22922649", "protein_xref_uniprotkb_gly", "Q8SPS7", "N-linked (GlcNAc...) asparagine", "PubMed", "ECO_0000269", "", "GlcNAc...", "", "NLT", "NXT", "125", "125", "Asn", "Asn", "N" ], [ "P35054-1", "529", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P35054", "protein_xref_uniprotkb_gly", "P35054", "O-linked (Xyl...) (glycosaminoglycan) serine", "", "", "", "Xyl...", "", "", "", "529", "529", "Ser", "Ser", "S" ], [ "Q28920-1", "36", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q28920", "protein_xref_uniprotkb_gly", "Q28920", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYS", "NXS", "36", "36", "Asn", "Asn", "N" ], [ "C0HL13-1", "341", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "C0HL13", "protein_xref_uniprotkb_gly", "C0HL13", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "341", "341", "Asn", "Asn", "N" ], [ "C0HL13-1", "341", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "C0HL13", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NNT", "NXT", "341", "341", "Asn", "Asn", "N" ], [ "F1SFA2-1", "269", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1SFA2", "protein_xref_uniprotkb_gly", "F1SFA2", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NIS", "NXS", "269", "269", "Asn", "Asn", "N" ], [ "F1SFA2-1", "269", "Asn", "", "N-linked", "protein_xref_pirsr", "PIRSR602640-4", "protein_xref_uniprotkb_gly", "F1SFA2", "N-linked (GlcNAc...) asparagine", "pirsr", "ECO_0000256", "", "GlcNAc...", "", "NIS", "NXS", "269", "269", "Asn", "Asn", "N" ], [ "Q9GLF5-1", "113", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9GLF5", "protein_xref_uniprotkb_gly", "Q9GLF5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "113", "113", "Asn", "Asn", "N" ], [ "P30555-1", "4", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P30555", "protein_xref_uniprotkb_gly", "P30555", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "4", "4", "Asn", "Asn", "N" ], [ "P12021-1", "87", "Ser", "", "O-linked", "protein_xref_uniprotkb_gly", "P12021", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "87", "87", "Ser", "Ser", "S" ], [ "P12021-1", "87", "Ser", "", "O-linked", "protein_xref_pubmed", "9092502", "protein_xref_uniprotkb_gly", "P12021", "O-linked (GalNAc...) serine; partial", "PubMed", "ECO_0000269", "", "GalNAc...", "O-GalNAcylation", "", "", "87", "87", "Ser", "Ser", "S" ], [ "Q75ZH0-1", "3", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q75ZH0", "protein_xref_uniprotkb_gly", "Q75ZH0", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "3", "3", "Asn", "Asn", "N" ], [ "P21692-1", "120", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P21692", "protein_xref_uniprotkb_gly", "P21692", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NYT", "NXT", "120", "120", "Asn", "Asn", "N" ], [ "P98074-1", "403", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P98074", "protein_xref_uniprotkb_gly", "P98074", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NAS", "NXS", "403", "403", "Asn", "Asn", "N" ], [ "P42098-1", "179", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P42098", "protein_xref_uniprotkb_gly", "P42098", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NWS", "NXS", "179", "179", "Asn", "Asn", "N" ], [ "P15145-1", "569", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P15145", "protein_xref_uniprotkb_gly", "P15145", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "569", "569", "Asn", "Asn", "N" ], [ "Q9GKE8-1", "23", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9GKE8", "protein_xref_uniprotkb_gly", "Q9GKE8", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NIT", "NXT", "23", "23", "Asn", "Asn", "N" ], [ "Q9TTB4-1", "40", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q9TTB4", "protein_xref_uniprotkb_gly", "Q9TTB4", "N-linked (GlcNAc...) (keratan sulfate) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "40", "40", "Asn", "Asn", "N" ], [ "F1RRW5-1", "42", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1RRW5", "protein_xref_uniprotkb_gly", "F1RRW5", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NFT", "NXT", "42", "42", "Asn", "Asn", "N" ], [ "Q8SPP9-1", "302", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8SPP9", "protein_xref_uniprotkb_gly", "Q8SPP9", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NES", "NXS", "302", "302", "Asn", "Asn", "N" ], [ "Q7M329-1", "43", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q7M329", "protein_xref_uniprotkb_gly", "Q7M329", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRS", "NXS", "43", "43", "Asn", "Asn", "N" ], [ "P98074-1", "721", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P98074", "protein_xref_uniprotkb_gly", "P98074", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NWT", "NXT", "721", "721", "Asn", "Asn", "N" ], [ "Q8SQC1-1", "212", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q8SQC1", "protein_xref_uniprotkb_gly", "Q8SQC1", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NNS", "NXS", "212", "212", "Asn", "Asn", "N" ], [ "F1RRV3-1", "546", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1RRV3", "protein_xref_uniprotkb_gly", "F1RRV3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NKT", "NXT", "546", "546", "Asn", "Asn", "N" ], [ "F1RRV3-1", "546", "Asn", "", "N-linked", "protein_xref_prosite-prorule", "PRU00498", "protein_xref_uniprotkb_gly", "F1RRV3", "N-linked (GlcNAc...) asparagine", "prosite-prorule", "ECO_0000255", "", "GlcNAc...", "", "NKT", "NXT", "546", "546", "Asn", "Asn", "N" ], [ "F1RWC3-1", "1170", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "F1RWC3", "protein_xref_uniprotkb_gly", "F1RWC3", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NLT", "NXT", "1170", "1170", "Asn", "Asn", "N" ], [ "Q864U6-1", "198", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q864U6", "protein_xref_uniprotkb_gly", "Q864U6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NHS", "NXS", "198", "198", "Asn", "Asn", "N" ], [ "Q58D68-1", "100", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q58D68", "protein_xref_uniprotkb_gly", "Q58D68", "N-linked (GlcNAc...) asparagine", "UniProtKB", "ECO_0000250", "", "GlcNAc...", "", "NKS", "NXS", "100", "100", "Asn", "Asn", "N" ], [ "Q9TUQ3-1", "509", "Trp", "", "C-linked", "protein_xref_uniprotkb_gly", "Q9TUQ3", "protein_xref_uniprotkb_gly", "Q9TUQ3", "C-linked (Man) tryptophan", "UniProtKB", "ECO_0000250", "", "Man", "C-mannosylation", "", "", "509", "509", "Trp", "Trp", "W" ], [ "P25117-1", "74", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "P25117", "protein_xref_uniprotkb_gly", "P25117", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NRT", "NXT", "74", "74", "Asn", "Asn", "N" ], [ "Q866X6-1", "118", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q866X6", "protein_xref_uniprotkb_gly", "Q866X6", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVS", "NXS", "118", "118", "Asn", "Asn", "N" ], [ "Q68Y56-1", "238", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q68Y56", "protein_xref_uniprotkb_gly", "Q68Y56", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NSS", "NXS", "238", "238", "Asn", "Asn", "N" ], [ "Q95334-1", "114", "Asn", "", "N-linked", "protein_xref_uniprotkb_gly", "Q95334", "protein_xref_uniprotkb_gly", "Q95334", "N-linked (GlcNAc...) asparagine", "", "", "", "GlcNAc...", "", "NVT", "NXT", "114", "114", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Pig Glycosylation Sites (UniProtKB)\n\nVersion\n - v-2.4.1\n\nCreated on\n - \n\nModified on\n - 2024-02-27T14:49:50\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], 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 Pig Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:9823] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from the UniProtKB Sus scrofa proteome release.\n\nDescription Domain\n\n Pipeline Steps\n - Step-1: The script loads the glycosylation information from the triplestore containing 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-2.4.1/misc/glycosylation_subtype.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt\n Name: uniprot-proteome-sus_scrofa.nt\n URI: https:/data.glygen.org/ln2downloads/ebi/2024_02_19/uniprot-proteome-sus_scrofa.nt\n Output Subdomain\n Name: pig_proteoform_glycosylation_sites_uniprotkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.csv\n Name: pig_proteoform_glycosylation_sites_uniprotkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"452\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"721\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"6\"\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: \"5\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"537\"\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: \"479\"\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: \"27\"\n Name: \"data_source\"\n Description: \"The source database for the data\"\n Unique Values: \"6\"\n Name: \"eco_id\"\n Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n Unique Values: \"7\"\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: \"9\"\n Name: \"carb_name\"\n Description: \"carbohydrate name\"\n Unique Values: \"10\"\n Name: \"glycosylation_subtype\"\n Description: \"\"\n Unique Values: \"9\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"41\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"4\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"721\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"721\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"6\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"6\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"6\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.csv" }