{ "bcoid": "GLY_000221", "title": "Glycosylation sites - UniCarbKB [Rat proteins]", "description": "List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if ...", "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv", "filetype": "csv", "categories": { "status": "Reviewed", "molecule": "Proteoform", "species": "Rattus norvegicus", "tags": "UniCarbKB glycosylation sites", "file_type": "csv", "scope": "internal" }, "minitable": { "content": [ [ "P01830-1...", "42..." ], [ "P01830-1...", "42..." ] ], "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": "n_sequon" }, { "type": "string", "label": "n_sequon_type" } ], [ "P01830-1", "42", "Asn", "G31852PQ", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G31852PQ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G31852PQ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G31852PQ", "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G41247ZX", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G41247ZX", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G41247ZX", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41247ZX", "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G02815KT", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G02815KT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G02815KT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G02815KT", "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G92050GC", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G92050GC", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "42", "Asn", "G92050GC", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "42", "42", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G92050GC", "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "40", "", "", "", "NNT", "NXT" ], [ "P01830-1", "93", "Asn", "G79941IJ", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G79941IJ", "HexNAc6Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G79941IJ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G79941IJ", "HexNAc6Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G79941IJ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G79941IJ", "HexNAc6Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G12580WI", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G12580WI", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G12580WI", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G12580WI", "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G44953PJ", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G44953PJ", "HexNAc5Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G44953PJ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G44953PJ", "HexNAc5Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G44953PJ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G44953PJ", "HexNAc5Hex4dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G60923RB", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G60923RB", "HexNAc4Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G60923RB", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G60923RB", "HexNAc4Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G60923RB", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G60923RB", "HexNAc4Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G68318VE", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G68318VE", "HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G68318VE", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G68318VE", "HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G68318VE", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G68318VE", "HexNAc5Hex4dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G83555HU", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G83555HU", "HexNAc4Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G83555HU", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G83555HU", "HexNAc4Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G83555HU", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G83555HU", "HexNAc4Hex5dHex1NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G27622TD", "N-linked", "protein_xref_unicarbkb", "P01830", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27622TD", "HexNAc3Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G27622TD", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27622TD", "HexNAc3Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P01830-1", "93", "Asn", "G27622TD", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P01830", "93", "93", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27622TD", "HexNAc3Hex5dHex2NeuAc0NeuGc0Pent0S0P0KDN0HexA0", "", "88", "", "", "", "NFT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "194", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "194", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "194", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G95678HJ", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G95678HJ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G95678HJ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G11115RO", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G11115RO", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G11115RO", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G41044JW", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G99679NM", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G99679NM", "HexNAc6Hex7dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G99679NM", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G99679NM", "HexNAc6Hex7dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G99679NM", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G99679NM", "HexNAc6Hex7dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G32926LW", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G32926LW", "HexNAc6Hex7dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G32926LW", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G32926LW", "HexNAc6Hex7dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G32926LW", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G32926LW", "HexNAc6Hex7dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G94917XT", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G94917XT", "HexNAc5Hex6dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G94917XT", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G94917XT", "HexNAc5Hex6dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G94917XT", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G94917XT", "HexNAc5Hex6dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G37818NZ", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G37818NZ", "HexNAc6Hex7dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G37818NZ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G37818NZ", "HexNAc6Hex7dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G37818NZ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G37818NZ", "HexNAc6Hex7dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G06247RL", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G06247RL", "HexNAc5Hex6dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G06247RL", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G06247RL", "HexNAc5Hex6dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G06247RL", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G06247RL", "HexNAc5Hex6dHex0NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G85144OK", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G85144OK", "HexNAc5Hex6dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G85144OK", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G85144OK", "HexNAc5Hex6dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G85144OK", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G85144OK", "HexNAc5Hex6dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G09406IK", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09406IK", "HexNAc6Hex5dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G09406IK", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09406IK", "HexNAc6Hex5dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G09406IK", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G09406IK", "HexNAc6Hex5dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G27947YN", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27947YN", "HexNAc5Hex6dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G27947YN", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27947YN", "HexNAc5Hex6dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G27947YN", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G27947YN", "HexNAc5Hex6dHex0NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G36670VW", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G36670VW", "HexNAc5Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G36670VW", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G36670VW", "HexNAc5Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G36670VW", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G36670VW", "HexNAc5Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G88374WZ", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G88374WZ", "HexNAc4Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G88374WZ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G88374WZ", "HexNAc4Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "205", "Asn", "G88374WZ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "205", "205", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G88374WZ", "HexNAc4Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0", "", "195", "", "", "", "NTT", "NXT" ], [ "P31596-1", "215", "Asn", "G95678HJ", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G95678HJ", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G95678HJ", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G95678HJ", "HexNAc6Hex7dHex1NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G11115RO", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G11115RO", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G11115RO", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G11115RO", "HexNAc6Hex7dHex0NeuAc4NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G41044JW", "N-linked", "protein_xref_unicarbkb", "P31596", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G41044JW", "N-linked", "protein_xref_pubmed", "34106099", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ], [ "P31596-1", "215", "Asn", "G41044JW", "N-linked", "protein_xref_doi", "10.1039/D0MO00044B", "protein_xref_unicarbkb", "P31596", "215", "215", "Asn", "Asn", "N", "known_site", "known_34106099_glygen", "G41044JW", "HexNAc6Hex7dHex1NeuAc3NeuGc0Pent0S0P0KDN0HexA0", "", "209", "", "", "", "NET", "NXT" ] ] }, "readme": "Name\n - Glycosylation sites - UniCarbKB [Rat proteins]\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-09-05T14:34:59.005886\n\nModified on\n - 2022-01-19T11:26:15.573991\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@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 rat [taxid:10116] 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/GLYDS000244).\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - glycan\n - UniCarbKB\n - GlyTouCan\n\n Pipeline Steps\n - Step-0: 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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt\n Name: known_legacy_dbogap_dbogap2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n Name: known_34106099_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n Name: known_unicarbkb_glycomics_study.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n Name: fuzzy_legacy_cph_start_end_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n Name: known_legacy_cph_single_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n Name: known_legacy_human_mouse_rat_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n Name: known_34004174_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n Name: known_33806155_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n Name: known_33167210_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n Name: known_legacy_reis_gastric_ags.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n Name: known_legacy_sarscov2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n Name: unknown_20131323_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n Name: fuzzy_simplecell_all_glygen_qc.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n Name: mixed_34089345_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n Name: known_33064451_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n Name: unknown_33993882_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n Name: unknown_34083726_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n Name: known_legacy_larsson_xyl.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n Name: unknown_34327564_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n Name: fuzzy_legacy_qin_oglanac.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n Name: unknown_34191522_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt\n Name: known_legacy_dbogap_dbogap2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n Name: known_34106099_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n Name: known_unicarbkb_glycomics_study.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n Name: fuzzy_legacy_cph_start_end_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n Name: known_legacy_cph_single_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n Name: known_legacy_human_mouse_rat_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n Name: known_34004174_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n Name: known_33806155_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n Name: known_33167210_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n Name: known_legacy_reis_gastric_ags.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n Name: known_legacy_sarscov2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n Name: unknown_20131323_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n Name: fuzzy_simplecell_all_glygen_qc.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n Name: mixed_34089345_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n Name: known_33064451_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n Name: unknown_33993882_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n Name: unknown_34083726_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n Name: known_legacy_larsson_xyl.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n Name: unknown_34327564_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n Name: fuzzy_legacy_qin_oglanac.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n Name: unknown_34191522_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt\n Name: known_legacy_dbogap_dbogap2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n Name: known_34106099_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n Name: known_unicarbkb_glycomics_study.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n Name: fuzzy_legacy_cph_start_end_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n Name: known_legacy_cph_single_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n Name: known_legacy_human_mouse_rat_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n Name: known_34004174_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n Name: known_33806155_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n Name: known_33167210_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n Name: known_legacy_reis_gastric_ags.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n Name: known_legacy_sarscov2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n Name: unknown_20131323_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n Name: fuzzy_simplecell_all_glygen_qc.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n Name: mixed_34089345_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n Name: known_33064451_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n Name: unknown_33993882_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n Name: unknown_34083726_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n Name: known_legacy_larsson_xyl.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n Name: unknown_34327564_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n Name: fuzzy_legacy_qin_oglanac.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n Name: unknown_34191522_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2020-09-15/cellosaurus.txt\n Name: known_legacy_dbogap_dbogap2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_dbogap_dbogap2_glygen.csv\n Name: known_34106099_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34106099_glygen.csv\n Name: known_unicarbkb_glycomics_study.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_unicarbkb_glycomics_study.csv\n Name: fuzzy_legacy_cph_start_end_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_cph_start_end_positions.csv\n Name: known_legacy_cph_single_positions.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_cph_single_positions.csv\n Name: unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_legacy_human_proteoform_glycosylation_sites_unicarbkb_ogalnac_data.csv\n Name: known_legacy_human_mouse_rat_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_human_mouse_rat_glygen.csv\n Name: known_34004174_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_34004174_glygen.csv\n Name: known_33806155_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33806155_glygen.csv\n Name: known_33167210_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33167210_glygen.csv\n Name: known_legacy_reis_gastric_ags.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_reis_gastric_ags.csv\n Name: known_legacy_sarscov2_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_sarscov2_glygen.csv\n Name: unknown_20131323_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_20131323_glygen.csv\n Name: fuzzy_simplecell_all_glygen_qc.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_simplecell_all_glygen_qc.csv\n Name: mixed_34089345_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/mixed_34089345_glygen.csv\n Name: known_33064451_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_33064451_glygen.csv\n Name: unknown_33993882_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_33993882_glygen.csv\n Name: fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_human_proteoform_glycosylation_sites_unicarbkb_qin_isoforms.csv\n Name: unknown_34083726_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34083726_glygen.csv\n Name: known_legacy_larsson_xyl.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/known_legacy_larsson_xyl.csv\n Name: unknown_34327564_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34327564_glygen.csv\n Name: fuzzy_legacy_qin_oglanac.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/fuzzy_legacy_qin_oglanac.csv\n Name: unknown_34191522_glygen.csv\n URI: https:/data.glygen.org/ln2downloads/unicarbkb/01_11_2022/unknown_34191522_glygen.csv\n Name: n_sequon_info.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/misc/n_sequon_info.csv\n Output Subdomain\n Name: rat_proteoform_glycosylation_sites_unicarbkb.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n Name: rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"160\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"240\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"2\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"179\"\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: \"169\"\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: \"160\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"240\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"240\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"2\"\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: \"116\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"124\"\n Name: \"curation_notes\"\n Description: \"GlycoSuiteDB curation notes\"\n Unique Values: \"262\"\n Name: \"additional_notes\"\n Description: \"\"\n Unique Values: \"63\"\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: \"n_sequon\"\n Description: \"\"\n Unique Values: \"39\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"4\"", "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv" }