{ "bcoid": "GLY_000041", "title": "Glycosylation sites - UniCarbKB [Mouse proteins]", "description": "List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if ...", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filetype": "csv", "categories": { "status": [ "Reviewed" ], "molecule": [ "Proteoform" ], "species": [ "Mus musculus" ], "tags": [ "UniCarbKB glycosylation sites" ], "file_type": [ "csv" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "Q91ZX7-1...", "447..." ], [ "Q91ZX7-1...", "447..." ] ], "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": "start_pos" }, { "type": "string", "label": "end_pos" }, { "type": "string", "label": "start_aa" }, { "type": "string", "label": "end_aa" }, { "type": "string", "label": "site_seq" }, { "type": "string", "label": "site_type" }, { "type": "string", "label": "src_file_name" }, { "type": "string", "label": "uckb_id" }, { "type": "string", "label": "composition" }, { "type": "string", "label": "curation_notes" }, { "type": "string", "label": "additional_notes" }, { "type": "string", "label": "pdb" }, { "type": "string", "label": "swiss_model" }, { "type": "string", "label": "abundance" }, { "type": "string", "label": "source_tissue_id" }, { "type": "string", "label": "source_tissue_name" }, { "type": "string", "label": "source_cell_line_cellosaurus_id" }, { "type": "string", "label": "source_cell_line_cellosaurus_name" }, { "type": "string", "label": "n_sequon" }, { "type": "string", "label": "n_sequon_type" } ], [ "Q91ZX7-1", "447", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q91ZX7", "protein_xref_unicarbkb", "Q91ZX7", "447", "447", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "446", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NST", "NXT" ], [ "Q91ZX7-1", "447", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q91ZX7", "447", "447", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "446", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NST", "NXT" ], [ "Q91ZX7-1", "447", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q91ZX7", "447", "447", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "446", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NST", "NXT" ], [ "Q8BLQ9-1", "211", "Asn", "G12580WI", "N-linked", "protein_xref_unicarbkb", "Q8BLQ9", "protein_xref_unicarbkb", "Q8BLQ9", "211", "211", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "205", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q8BLQ9-1", "211", "Asn", "G12580WI", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q8BLQ9", "211", "211", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "205", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q8BLQ9-1", "211", "Asn", "G12580WI", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q8BLQ9", "211", "211", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "205", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "139", "Asn", "G59626AS", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G59626AS", "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G59626AS", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G59626AS", "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G59626AS", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G59626AS", "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G41247ZX", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G41247ZX", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G41247ZX", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "139", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "139", "139", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "138", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NET", "NXT" ], [ "Q00493-1", "390", "Asn", "G72961RM", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G72961RM", "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G72961RM", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G72961RM", "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G72961RM", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G72961RM", "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G41247ZX", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G41247ZX", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G41247ZX", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G92050GC", "N-linked", "protein_xref_unicarbkb", "Q00493", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G92050GC", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q00493-1", "390", "Asn", "G92050GC", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q00493", "390", "390", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "382", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NAT", "NXT" ], [ "Q9CPW0-1", "630", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q9CPW0", "protein_xref_unicarbkb", "Q9CPW0", "630", "630", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "627", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NMT", "NXT" ], [ "Q9CPW0-1", "630", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q9CPW0", "630", "630", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "627", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NMT", "NXT" ], [ "Q9CPW0-1", "630", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q9CPW0", "630", "630", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "627", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NMT", "NXT" ], [ "Q640R3-1", "189", "Asn", "G81572SC", "N-linked", "protein_xref_unicarbkb", "Q640R3", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G81572SC", "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G81572SC", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G81572SC", "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G81572SC", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G81572SC", "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "", "N-linked", "protein_xref_unicarbkb", "Q640R3", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "", "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "", "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "", "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G09528DL", "N-linked", "protein_xref_unicarbkb", "Q640R3", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09528DL", "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G09528DL", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09528DL", "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G09528DL", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09528DL", "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G67324HN", "N-linked", "protein_xref_unicarbkb", "Q640R3", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G67324HN", "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G67324HN", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G67324HN", "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q640R3-1", "189", "Asn", "G67324HN", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q640R3", "189", "189", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G67324HN", "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "183", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NDS", "NXS" ], [ "Q05186-1", "47", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q05186", "protein_xref_unicarbkb", "Q05186", "47", "47", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "32", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NQS", "NXS" ], [ "Q05186-1", "47", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q05186", "47", "47", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "32", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NQS", "NXS" ], [ "Q05186-1", "47", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q05186", "47", "47", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "32", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NQS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G31852PQ", "N-linked", "protein_xref_unicarbkb", "Q6AXF6", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G31852PQ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G31852PQ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q6AXF6", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "Q6AXF6-1", "83", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q6AXF6", "83", "83", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "80", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NSS", "NXS" ], [ "P20917-1", "99", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "P20917", "protein_xref_unicarbkb", "P20917", "99", "99", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NCT", "NXT" ], [ "P20917-1", "99", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P20917", "99", "99", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NCT", "NXT" ], [ "P20917-1", "99", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P20917", "99", "99", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NCT", "NXT" ], [ "Q9WTR5-1", "598", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q9WTR5", "protein_xref_unicarbkb", "Q9WTR5", "598", "598", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NLS", "NXS" ], [ "Q9WTR5-1", "598", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q9WTR5", "598", "598", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NLS", "NXS" ], [ "Q9WTR5-1", "598", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q9WTR5", "598", "598", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NLS", "NXS" ], [ "Q6PHU5-1", "404", "Asn", "G80920RR", "N-linked", "protein_xref_unicarbkb", "Q6PHU5", "protein_xref_unicarbkb", "Q6PHU5", "404", "404", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G80920RR", "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "391", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q6PHU5-1", "404", "Asn", "G80920RR", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q6PHU5", "404", "404", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G80920RR", "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "391", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q6PHU5-1", "404", "Asn", "G80920RR", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q6PHU5", "404", "404", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G80920RR", "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "391", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q9QUR8-1", "256", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q9QUR8", "protein_xref_unicarbkb", "Q9QUR8", "256", "256", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "244", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVS", "NXS" ], [ "Q9QUR8-1", "256", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q9QUR8", "256", "256", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "244", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVS", "NXS" ], [ "Q9QUR8-1", "256", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q9QUR8", "256", "256", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "244", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVS", "NXS" ], [ "P97952-1", "135", "Asn", "G41247ZX", "N-linked", "protein_xref_unicarbkb", "P97952", "protein_xref_unicarbkb", "P97952", "135", "135", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "126", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NTS", "NXS" ], [ "P97952-1", "135", "Asn", "G41247ZX", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P97952", "135", "135", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "126", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NTS", "NXS" ], [ "P97952-1", "135", "Asn", "G41247ZX", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P97952", "135", "135", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "126", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NTS", "NXS" ], [ "Q7TNR6-1", "407", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q7TNR6", "protein_xref_unicarbkb", "Q7TNR6", "407", "407", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "402", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NGS", "NXS" ], [ "Q7TNR6-1", "407", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q7TNR6", "407", "407", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "402", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NGS", "NXS" ], [ "Q7TNR6-1", "407", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q7TNR6", "407", "407", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "402", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NGS", "NXS" ], [ "Q9WV91-1", "300", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q9WV91", "protein_xref_unicarbkb", "Q9WV91", "300", "300", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "294", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NIT", "NXT" ], [ "Q9WV91-1", "300", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q9WV91", "300", "300", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "294", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NIT", "NXT" ], [ "Q9WV91-1", "300", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q9WV91", "300", "300", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "294", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NIT", "NXT" ], [ "Q80ZF8-1", "625", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "Q80ZF8", "protein_xref_unicarbkb", "Q80ZF8", "625", "625", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q80ZF8-1", "625", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "Q80ZF8", "625", "625", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q80ZF8-1", "625", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "Q80ZF8", "625", "625", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "", "", "", "", "OMIT:0014437", "Synaptosomes", "", "", "NVT", "NXT" ], [ "Q09163-1", "94", "Ser", "G01614ZM", "O-linked", "protein_xref_unicarbkb", "Q09163", "protein_xref_unicarbkb", "Q09163", "94", "94", "Ser", "Ser", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "96", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-94, N-100, N-165, N-174, S-216, T-224, T-258, T-267, T-271", "", "", "", "", "", "", "", "", "", "" ], [ "Q09163-1", "94", "Ser", "G01614ZM", "O-linked", "protein_xref_pubmed", "9118998", "protein_xref_unicarbkb", "Q09163", "94", "94", "Ser", "Ser", "S", "known_site", "known_legacy_human_mouse_rat_glygen", "96", "", "GlycoSuiteDB curation notes. Reported structure can be attached to the following: S-94, N-100, N-165, N-174, S-216, T-224, T-258, T-267, T-271", "", "", "", "", "", "", "", "", "", "" ], [ "P04925-1", "196", "Asn", "", "N-linked", "protein_xref_unicarbkb", "P04925", "protein_xref_unicarbkb", "P04925", "196", "196", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7455", "", "", "", "", "", "", "", "", "", "", "NFT", "NXT" ], [ "P04925-1", "196", "Asn", "", "N-linked", "protein_xref_pubmed", "10200178", "protein_xref_unicarbkb", "P04925", "196", "196", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7455", "", "", "", "", "", "", "", "", "", "", "NFT", "NXT" ], [ "P04925-1", "180", "Asn", "G92129PT", "N-linked", "protein_xref_unicarbkb", "P04925", "protein_xref_unicarbkb", "P04925", "180", "180", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7641", "", "", "", "", "", "", "", "", "", "", "NIT", "NXT" ], [ "P04925-1", "180", "Asn", "G92129PT", "N-linked", "protein_xref_pubmed", "10200178", "protein_xref_unicarbkb", "P04925", "180", "180", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7641", "", "", "", "", "", "", "", "", "", "", "NIT", "NXT" ], [ "O09164-1", "121", "Asn", "G25067TK", "N-linked", "protein_xref_unicarbkb", "O09164", "protein_xref_unicarbkb", "O09164", "121", "121", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7511", "", "", "", "", "", "", "", "", "", "", "NAS", "NXS" ], [ "O09164-1", "121", "Asn", "G25067TK", "N-linked", "protein_xref_pubmed", "21573946", "protein_xref_unicarbkb", "O09164", "121", "121", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7511", "", "", "", "", "", "", "", "", "", "", "NAS", "NXS" ], [ "P04925-1", "196", "Asn", "", "N-linked", "protein_xref_unicarbkb", "P04925", "protein_xref_unicarbkb", "P04925", "196", "196", "Asn", "Asn", "N", "known_site", "known_legacy_human_mouse_rat_glygen", "7580", "", "", "", "", "", "", "", "", "", "", "NFT", "NXT" ] ] }, "readme": "Name\n - Glycosylation sites - UniCarbKB [Mouse proteins]\n\nVersion\n - v-2.1.1\n\nCreated on\n - 2019-01-23T17:21:05.908793\n\nModified on\n - 2022-09-26T08:48:18.860178\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Matthew Campbell [m.campbell2@griffith.edu.au], Robel Kahsay [rykahsay@email.gwu.edu], Nathan Edwards [Georgetown University]\n\nChecksum\n - \n\nUsability Domain\n - List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007).\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - glycan\n - UniCarbKB\n - GlyTouCan\n\n Pipeline Steps\n - Step-1: The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid.\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: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: /data/shared/glyds/downloads/cellosaurus/2023-03-21/cellosaurus.txt\n Name: fuzzy_legacy_cph_start_end_positions.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n Name: fuzzy_legacy_qin_oglanac.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n Name: fuzzy_simplecell_all_glygen_qc.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n Name: known_33064451_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n Name: known_33167210_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n Name: known_33806155_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n Name: known_34004174_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n Name: known_34106099_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n Name: known_legacy_cph_single_positions.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n Name: known_legacy_dbogap_dbogap2_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n Name: known_legacy_human_mouse_rat_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n Name: known_legacy_larsson_xyl.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n Name: known_legacy_reis_gastric_ags.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n Name: known_legacy_sarscov2_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n Name: known_unicarbkb_glycomics_study.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n Name: mixed_34089345_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n Name: unknown_20131323_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n Name: unknown_33993882_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n Name: unknown_34083726_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n Name: unknown_34191522_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n Name: unknown_34327564_glygen.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n URI: /data/shared/glyds/downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n Output Subdomain\n Name: mouse_proteoform_glycosylation_sites_unicarbkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n Name: mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"36\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"55\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"3\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"79\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"2\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"3\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"46\"\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: \"36\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"55\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"55\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"3\"\n Name: \"site_type\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"src_file_name\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"uckb_id\"\n Description: \"\"\n Unique Values: \"93\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"25\"\n Name: \"curation_notes\"\n Description: \"GlycoSuiteDB curation notes\"\n Unique Values: \"8\"\n Name: \"additional_notes\"\n Description: \"\"\n Unique Values: \"14\"\n Name: \"pdb\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"swiss_model\"\n Description: \"SWISS-MODEL ID.\"\n Unique Values: \"1\"\n Name: \"abundance\"\n Description: \" Abundance ratio of the glycan.\"\n Unique Values: \"1\"\n Name: \"source_tissue_id\"\n Description: \"Tissue ID from GlyConnect\"\n Unique Values: \"2\"\n Name: \"source_tissue_name\"\n Description: \"Tissue NAME from GlyConnect\"\n Unique Values: \"2\"\n Name: \"source_cell_line_cellosaurus_id\"\n Description: \"cellosaurus ID of the cell line\"\n Unique Values: \"1\"\n Name: \"source_cell_line_cellosaurus_name\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"28\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"4\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv" }