{ "bcoid": "GLY_000480", "title": "Human Glycosylation Sites [GPTwiki]", "description": "Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research ...", "filename": "human_proteoform_glycosylation_sites_gptwiki.csv", "filetype": "csv", "categories": { "status": [ "Reviewed" ], "molecule": [ "Proteoform" ], "species": [ "Homo sapiens" ], "tag": [ "glycosylation sites" ], "file_type": [ "csv" ], "scope": [ "internal" ] }, "minitable": { "content": [ [ "O00754-1...", "692..." ], [ "O00754-1...", "930..." ] ], "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": "glycopeptide_id" }, { "type": "string", "label": "composition" }, { "type": "string", "label": "glycan_xref_key" }, { "type": "string", "label": "glycan_xref_id" }, { "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" } ], [ "O00754-1", "692", "Asn", "G28681TP", "N-linked", "protein_xref_gptwiki", "O00754@N692", "protein_xref_gptwiki", "O00754@N692", "PE001986", "HexNAc(2)Hex(3)", "glycan_xref_gptwiki", "G28681TP", "NFS", "NXS", "692", "692", "Asn", "Asn", "N" ], [ "O00754-1", "930", "Asn", "G41247ZX", "N-linked", "protein_xref_gptwiki", "O00754@N930", "protein_xref_gptwiki", "O00754@N930", "PE002013", "HexNAc(2)Hex(6)", "glycan_xref_gptwiki", "G41247ZX", "NLS", "NXS", "930", "930", "Asn", "Asn", "N" ], [ "O14672-1", "278", "Asn", "G80920RR", "N-linked", "protein_xref_gptwiki", "O14672@N278", "protein_xref_gptwiki", "O14672@N278", "PE001964", "HexNAc(2)Hex(9)", "glycan_xref_gptwiki", "G80920RR", "NTT", "NXT", "278", "278", "Asn", "Asn", "N" ], [ "O43405-1", "100", "Asn", "G27126ED", "N-linked", "protein_xref_gptwiki", "O43405@N100", "protein_xref_gptwiki", "O43405@N100", "PE002197", "HexNAc(4)Hex(6)NeuAc(1)", "glycan_xref_gptwiki", "G27126ED", "NYS", "NXS", "100", "100", "Asn", "Asn", "N" ], [ "O43852-1", "131", "Asn", "G25987BV", "N-linked", "protein_xref_gptwiki", "O43852@N131", "protein_xref_gptwiki", "O43852@N131", "PE001250", "HexNAc(4)Hex(3)dHex(1)", "glycan_xref_gptwiki", "G25987BV", "NAT", "NXT", "131", "131", "Asn", "Asn", "N" ], [ "O43852-1", "131", "Asn", "G25987BV", "N-linked", "protein_xref_gptwiki", "O43852@N131", "protein_xref_gptwiki", "O43852@N131", "PE001256", "HexNAc(4)Hex(3)dHex(1)", "glycan_xref_gptwiki", "G25987BV", "NAT", "NXT", "131", "131", "Asn", "Asn", "N" ], [ "O43852-1", "131", "Asn", "G80475RE", "N-linked", "protein_xref_gptwiki", "O43852@N131", "protein_xref_gptwiki", "O43852@N131", "PE001257", "HexNAc(3)Hex(3)dHex(1)", "glycan_xref_gptwiki", "G80475RE", "NAT", "NXT", "131", "131", "Asn", "Asn", "N" ], [ "O43852-1", "131", "Asn", "G88725PI", "N-linked", "protein_xref_gptwiki", "O43852@N131", "protein_xref_gptwiki", "O43852@N131", "PE002179", "HexNAc(5)Hex(3)dHex(1)", "glycan_xref_gptwiki", "G88725PI", "NAT", "NXT", "131", "131", "Asn", "Asn", "N" ], [ "O75636-1", "189", "Asn", "G07799LX", "N-linked", "protein_xref_gptwiki", "O75636@N189", "protein_xref_gptwiki", "O75636@N189", "PE002098", "HexNAc(4)Hex(5)dHex(3)NeuAc(1)", "glycan_xref_gptwiki", "G07799LX", "NRT", "NXT", "189", "189", "Asn", "Asn", "N" ], [ "O75636-1", "189", "Asn", "G08293MJ", "N-linked", "protein_xref_gptwiki", "O75636@N189", "protein_xref_gptwiki", "O75636@N189", "PE000574", "HexNAc(4)Hex(5)dHex(1)NeuAc(1)", "glycan_xref_gptwiki", "G08293MJ", "NRT", "NXT", "189", "189", "Asn", "Asn", "N" ], [ "O75636-1", "189", "Asn", "G88374WZ", "N-linked", "protein_xref_gptwiki", "O75636@N189", "protein_xref_gptwiki", "O75636@N189", "PE000575", "HexNAc(4)Hex(5)dHex(1)NeuAc(2)", "glycan_xref_gptwiki", "G88374WZ", "NRT", "NXT", "189", "189", "Asn", "Asn", "N" ], [ "O75882-1", "325", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "O75882@N325", "protein_xref_gptwiki", "O75882@N325", "PE000022", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NQS", "NXS", "325", "325", "Asn", "Asn", "N" ], [ "O75882-1", "416", "Asn", "G02815KT", "N-linked", "protein_xref_gptwiki", "O75882@N416", "protein_xref_gptwiki", "O75882@N416", "PE001451", "HexNAc(2)Hex(5)", "glycan_xref_gptwiki", "G02815KT", "NVT", "NXT", "416", "416", "Asn", "Asn", "N" ], [ "O75882-1", "428", "Asn", "G01650EU", "N-linked", "protein_xref_gptwiki", "O75882@N428", "protein_xref_gptwiki", "O75882@N428", "PE000850", "HexNAc(3)Hex(6)NeuAc(1)", "glycan_xref_gptwiki", "G01650EU", "NES", "NXS", "428", "428", "Asn", "Asn", "N" ], [ "O75882-1", "428", "Asn", "G02815KT", "N-linked", "protein_xref_gptwiki", "O75882@N428", "protein_xref_gptwiki", "O75882@N428", "PE002063", "HexNAc(2)Hex(5)", "glycan_xref_gptwiki", "G02815KT", "NES", "NXS", "428", "428", "Asn", "Asn", "N" ], [ "O75882-1", "428", "Asn", "G28541PG", "N-linked", "protein_xref_gptwiki", "O75882@N428", "protein_xref_gptwiki", "O75882@N428", "PE001127", "HexNAc(3)Hex(6)", "glycan_xref_gptwiki", "G28541PG", "NES", "NXS", "428", "428", "Asn", "Asn", "N" ], [ "O75882-1", "428", "Asn", "G37399XV", "N-linked", "protein_xref_gptwiki", "O75882@N428", "protein_xref_gptwiki", "O75882@N428", "PE001128", "HexNAc(3)Hex(5)NeuAc(1)", "glycan_xref_gptwiki", "G37399XV", "NES", "NXS", "428", "428", "Asn", "Asn", "N" ], [ "O75882-1", "428", "Asn", "G57776ZU", "N-linked", "protein_xref_gptwiki", "O75882@N428", "protein_xref_gptwiki", "O75882@N428", "PE001131", "HexNAc(3)Hex(4)", "glycan_xref_gptwiki", "G57776ZU", "NES", "NXS", "428", "428", "Asn", "Asn", "N" ], [ "O75882-1", "731", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "O75882@N731", "protein_xref_gptwiki", "O75882@N731", "PE000531", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NHS", "NXS", "731", "731", "Asn", "Asn", "N" ], [ "O75882-1", "731", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "O75882@N731", "protein_xref_gptwiki", "O75882@N731", "PE000907", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NHS", "NXS", "731", "731", "Asn", "Asn", "N" ], [ "O75882-1", "1043", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "O75882@N1043", "protein_xref_gptwiki", "O75882@N1043", "PE000674", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NSS", "NXS", "1043", "1043", "Asn", "Asn", "N" ], [ "O75882-1", "1043", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "O75882@N1043", "protein_xref_gptwiki", "O75882@N1043", "PE002123", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NSS", "NXS", "1043", "1043", "Asn", "Asn", "N" ], [ "O95302-1", "174", "Asn", "G62765YT", "N-linked", "protein_xref_gptwiki", "O95302@N174", "protein_xref_gptwiki", "O95302@N174", "PE001924", "HexNAc(2)Hex(8)", "glycan_xref_gptwiki", "G62765YT", "NGT", "NXT", "174", "174", "Asn", "Asn", "N" ], [ "O95302-1", "286", "Asn", "G25079LO", "N-linked", "protein_xref_gptwiki", "O95302@N286", "protein_xref_gptwiki", "O95302@N286", "PE002051", "HexNAc(6)Hex(4)", "glycan_xref_gptwiki", "G25079LO", "NGT", "NXT", "286", "286", "Asn", "Asn", "N" ], [ "O95302-1", "286", "Asn", "G80920RR", "N-linked", "protein_xref_gptwiki", "O95302@N286", "protein_xref_gptwiki", "O95302@N286", "PE002024", "HexNAc(2)Hex(9)", "glycan_xref_gptwiki", "G80920RR", "NGT", "NXT", "286", "286", "Asn", "Asn", "N" ], [ "O95445-1", "135", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "O95445@N135", "protein_xref_gptwiki", "O95445@N135", "PE001212", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NET", "NXT", "135", "135", "Asn", "Asn", "N" ], [ "O95445-1", "135", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "O95445@N135", "protein_xref_gptwiki", "O95445@N135", "PE002145", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NET", "NXT", "135", "135", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000235", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000263", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000679", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G03596YS", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE002092", "HexNAc(5)Hex(6)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G03596YS", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G05933EN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE002096", "HexNAc(4)Hex(5)dHex(4)", "glycan_xref_gptwiki", "G05933EN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G05933EN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE002124", "HexNAc(4)Hex(5)dHex(4)", "glycan_xref_gptwiki", "G05933EN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G06247RL", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000567", "HexNAc(5)Hex(6)NeuAc(3)", "glycan_xref_gptwiki", "G06247RL", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G07799LX", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001856", "HexNAc(4)Hex(5)dHex(3)NeuAc(1)", "glycan_xref_gptwiki", "G07799LX", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G07799LX", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE002097", "HexNAc(4)Hex(5)dHex(3)NeuAc(1)", "glycan_xref_gptwiki", "G07799LX", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G10486CT", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000278", "HexNAc(4)Hex(5)", "glycan_xref_gptwiki", "G10486CT", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G27947YN", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000857", "HexNAc(5)Hex(6)NeuAc(2)", "glycan_xref_gptwiki", "G27947YN", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G40926MX", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001299", "HexNAc(5)Hex(6)NeuAc(1)", "glycan_xref_gptwiki", "G40926MX", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G41044JW", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001300", "HexNAc(6)Hex(7)dHex(1)NeuAc(3)", "glycan_xref_gptwiki", "G41044JW", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G43669FQ", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE002140", "HexNAc(6)Hex(7)", "glycan_xref_gptwiki", "G43669FQ", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001301", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001873", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G59626AS", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000478", "HexNAc(4)Hex(5)NeuAc(1)", "glycan_xref_gptwiki", "G59626AS", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G83555HU", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000086", "HexNAc(4)Hex(5)dHex(1)", "glycan_xref_gptwiki", "G83555HU", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G85144OK", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000858", "HexNAc(5)Hex(6)dHex(1)NeuAc(2)", "glycan_xref_gptwiki", "G85144OK", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G86752LQ", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE001135", "HexNAc(5)Hex(6)dHex(1)NeuAc(1)", "glycan_xref_gptwiki", "G86752LQ", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G88374WZ", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000479", "HexNAc(4)Hex(5)dHex(1)NeuAc(2)", "glycan_xref_gptwiki", "G88374WZ", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "138", "Asn", "G94917XT", "N-linked", "protein_xref_gptwiki", "P00450@N138", "protein_xref_gptwiki", "P00450@N138", "PE000568", "HexNAc(5)Hex(6)dHex(1)NeuAc(3)", "glycan_xref_gptwiki", "G94917XT", "NTT", "NXT", "138", "138", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE000007", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G06247RL", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE001799", "HexNAc(5)Hex(6)NeuAc(3)", "glycan_xref_gptwiki", "G06247RL", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G10486CT", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE000106", "HexNAc(4)Hex(5)", "glycan_xref_gptwiki", "G10486CT", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G44211QA", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE000354", "HexNAc(5)Hex(6)dHex(1)", "glycan_xref_gptwiki", "G44211QA", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE001466", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "358", "Asn", "G83555HU", "N-linked", "protein_xref_gptwiki", "P00450@N358", "protein_xref_gptwiki", "P00450@N358", "PE000297", "HexNAc(4)Hex(5)dHex(1)", "glycan_xref_gptwiki", "G83555HU", "NKS", "NXS", "358", "358", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000589", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G06247RL", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000590", "HexNAc(5)Hex(6)NeuAc(3)", "glycan_xref_gptwiki", "G06247RL", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G10486CT", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000287", "HexNAc(4)Hex(5)", "glycan_xref_gptwiki", "G10486CT", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G15038BD", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000896", "HexNAc(4)Hex(6)dHex(1)NeuAc(1)", "glycan_xref_gptwiki", "G15038BD", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000867", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G59626AS", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000485", "HexNAc(4)Hex(5)NeuAc(1)", "glycan_xref_gptwiki", "G59626AS", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G88374WZ", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000591", "HexNAc(4)Hex(5)dHex(1)NeuAc(2)", "glycan_xref_gptwiki", "G88374WZ", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "397", "Asn", "G94917XT", "N-linked", "protein_xref_gptwiki", "P00450@N397", "protein_xref_gptwiki", "P00450@N397", "PE000592", "HexNAc(5)Hex(6)dHex(1)NeuAc(3)", "glycan_xref_gptwiki", "G94917XT", "NLT", "NXT", "397", "397", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000480", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G00912UN", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000665", "HexNAc(4)Hex(5)NeuAc(2)", "glycan_xref_gptwiki", "G00912UN", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G05933EN", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE002102", "HexNAc(4)Hex(5)dHex(4)", "glycan_xref_gptwiki", "G05933EN", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G06247RL", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000481", "HexNAc(5)Hex(6)NeuAc(3)", "glycan_xref_gptwiki", "G06247RL", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G06247RL", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000639", "HexNAc(5)Hex(6)NeuAc(3)", "glycan_xref_gptwiki", "G06247RL", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G07799LX", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001322", "HexNAc(4)Hex(5)dHex(3)NeuAc(1)", "glycan_xref_gptwiki", "G07799LX", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G10486CT", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000282", "HexNAc(4)Hex(5)", "glycan_xref_gptwiki", "G10486CT", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G12341GU", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001194", "HexNAc(7)Hex(8)NeuAc(1)", "glycan_xref_gptwiki", "G12341GU", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G12341GU", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001206", "HexNAc(7)Hex(8)NeuAc(1)", "glycan_xref_gptwiki", "G12341GU", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G27947YN", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000859", "HexNAc(5)Hex(6)NeuAc(2)", "glycan_xref_gptwiki", "G27947YN", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G27947YN", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000862", "HexNAc(5)Hex(6)NeuAc(2)", "glycan_xref_gptwiki", "G27947YN", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G40926MX", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000860", "HexNAc(5)Hex(6)NeuAc(1)", "glycan_xref_gptwiki", "G40926MX", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G40926MX", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000863", "HexNAc(5)Hex(6)NeuAc(1)", "glycan_xref_gptwiki", "G40926MX", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G44211QA", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000352", "HexNAc(5)Hex(6)dHex(1)", "glycan_xref_gptwiki", "G44211QA", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001195", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G47737VJ", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001220", "HexNAc(4)Hex(5)dHex(2)NeuAc(1)", "glycan_xref_gptwiki", "G47737VJ", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G59626AS", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000482", "HexNAc(4)Hex(5)NeuAc(1)", "glycan_xref_gptwiki", "G59626AS", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G59626AS", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000483", "HexNAc(4)Hex(5)NeuAc(1)", "glycan_xref_gptwiki", "G59626AS", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G60033FS", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000290", "HexNAc(5)Hex(6)", "glycan_xref_gptwiki", "G60033FS", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G66933CM", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE001047", "HexNAc(5)Hex(6)dHex(2)", "glycan_xref_gptwiki", "G66933CM", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ], [ "P00450-1", "762", "Asn", "G83555HU", "N-linked", "protein_xref_gptwiki", "P00450@N762", "protein_xref_gptwiki", "P00450@N762", "PE000286", "HexNAc(4)Hex(5)dHex(1)", "glycan_xref_gptwiki", "G83555HU", "NVS", "NXS", "762", "762", "Asn", "Asn", "N" ] ] }, "readme": "Name\n - Human Glycosylation Sites [GPTwiki]\n\nVersion\n - v-2.2.1\n\nCreated on\n - 2020-04-20T16:33:02.961632\n\nModified on\n - 2022-09-26T09:05:56.429819\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n - Nathan Edwards [Georgetown University], Radoslav Goldman [rg26@georgetown.edu]\n\nChecksum\n - \n\nUsability Domain\n - Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)\n\nDescription Domain\n Keywords\n - proteins\n - canonical\n - glycosylation sites\n - glycan\n - GPTwiki\n - GlyTouCan\n\n Pipeline Steps\n - Step-1: The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\"\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-2.2.1/misc/n_sequon_info.csv\n Name: sample_mapping.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/sample_mapping.csv\n Name: cellosaurus.txt\n URI: https:/data.glygen.org/ln2downloads/cellosaurus/2023_07_13/cellosaurus.txt\n Name: glycosites.csv\n URI: https:/data.glygen.org/ln2downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv\n Output Subdomain\n Name: human_proteoform_glycosylation_sites_gptwiki.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv\n Name: human_proteoform_glycosylation_sites_gptwiki.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"141\"\n Name: \"glycosylation_site_uniprotkb\"\n Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n Unique Values: \"218\"\n Name: \"amino_acid\"\n Description: \"Three letter abbreviation code of the amino acid\"\n Unique Values: \"1\"\n Name: \"saccharide\"\n Description: \"Sugar\"\n Unique Values: \"101\"\n Name: \"glycosylation_type\"\n Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n Unique Values: \"1\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"282\"\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: \"282\"\n Name: \"glycopeptide_id\"\n Description: \"Glycopeptide Id from GPTwiki database. \"\n Unique Values: \"1708\"\n Name: \"composition\"\n Description: \"Composition of glycan\"\n Unique Values: \"101\"\n Name: \"glycan_xref_key\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"glycan_xref_id\"\n Description: \"\"\n Unique Values: \"101\"\n Name: \"n_sequon\"\n Description: \"\"\n Unique Values: \"38\"\n Name: \"n_sequon_type\"\n Description: \"\"\n Unique Values: \"2\"\n Name: \"start_pos\"\n Description: \"Start position of the gene on the chromosome\"\n Unique Values: \"218\"\n Name: \"end_pos\"\n Description: \"End position of the gene on the chromosome\"\n Unique Values: \"218\"\n Name: \"start_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"end_aa\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"site_seq\"\n Description: \"\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv" }