{
    "bcoid": "GLY_000040",
    "title": "Glycosylation Sites - UniCarbKB [Human proteins]",
    "description": "List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if ...",
    "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv",
    "filetype": "csv",
    "categories": {
        "status": "Reviewed",
        "molecule": "Proteoform",
        "species": "Homo sapiens",
        "tags": "UniCarbKB glycosylation sites",
        "file_type": "csv",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "A1L4H1-1...",
                "1445..."
            ],
            [
                "A1L4H1-1...",
                "1458..."
            ]
        ],
        "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": "evidence"
                },
                {
                    "type": "string",
                    "label": "unicarbkb_id"
                },
                {
                    "type": "string",
                    "label": "glytoucan_ac"
                },
                {
                    "type": "string",
                    "label": "amino_acid"
                },
                {
                    "type": "string",
                    "label": "glycosylation_type"
                },
                {
                    "type": "string",
                    "label": "curation_notes"
                },
                {
                    "type": "string",
                    "label": "additonal_notes"
                },
                {
                    "type": "string",
                    "label": "composition"
                }
            ],
            [
                "A1L4H1-1",
                "1445",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1458",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1462",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1462",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1466",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "758",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1558",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1558",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1558",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc4Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1047",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "1047",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex3dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "157",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "453",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "884",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "581",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "764",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "939",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A1L4H1-1",
                "760",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A5D8T8-1",
                "356",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "A6NFA1-1",
                "395",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "B4DS77-1",
                "66",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "B4DS77-1",
                "66",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "C9JH25-1",
                "78",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00178-1",
                "119",
                "26598643",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00178-1",
                "122",
                "26598643",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00220-1",
                "126",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00339-1",
                "860",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00339-1",
                "866",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00339-1",
                "905",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00391-1",
                "592",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00391-1",
                "593",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00451-1",
                "396",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00451-1",
                "396",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex3dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00451-1",
                "401",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "276",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "276",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "283",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "283",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "222",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "229",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "259",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00461-1",
                "308",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1261",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1258",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1258",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc4Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1258",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc4Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "987",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "985",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc4Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "985",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex3dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "162",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "162",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "994",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "994",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1095",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "1095",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "159",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "167",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "204",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "496",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00468-1",
                "896",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "200",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "200",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "330",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "232",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "232",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "232",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "232",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc3Hex3dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "261",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc2Hex2dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "202",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "202",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "334",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex0dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "334",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "267",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O00592-1",
                "269",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O14498-1",
                "379",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O14498-1",
                "371",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O14594-1",
                "725",
                "30459171",
                "",
                "",
                "Ser",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ],
            [
                "O14594-1",
                "871",
                "30459171",
                "",
                "",
                "Thr",
                "o-linked",
                "",
                "",
                "comp_HexNAc1Hex1dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0"
            ]
        ]
    },
    "readme": "Name\n   - Glycosylation Sites - UniCarbKB [Human proteins]\n\nVersion\n   - 1.4.5\n\nCreated on\n  - 2019-01-23T17:21:05.907769\n\nModified on\n   - 2019-09-12T12:45:24.988433\n\nCreated by\n   - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu], Xavier Holmes [xavierh@gwu.edu]\n\nAuthors\n   - Matthew Campbell  [m.campbell2@griffith.edu.au], Nathan Edwards [Georgetown University]\n\nChecksum\n   - \n\nUsability Domain\n   - List of human [taxid:9606] 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/GLYDS000001).\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 (human_18072019_2019_07_18_10_45_16.csv ;for script:human_glycosylation_current.csv) 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 script additionally implements 10 QC checks. Any row that falls 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: human_18072019_2019_07_18_10_45_16.csv\n      URI: https://data.glygen.org/ln2wwwdata/source/human_18072019_2019_07_18_10_45_16.csv\n      Name: human_protein_idmapping.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv\n      Name: classification.tsv\n      URI: https://data.glygen.org/ln2wwwdata/source/classification.tsv\n      Name: glycan_properties.tsv\n      URI: https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv\n      Name: human_protein_allsequences.fasta\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta\n      Name: aadict.csv\n      URI: https://data.glygen.org/ln2wwwdata/source/aadict.csv\n   Output Subdomain\n      Name: human_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.1.log\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.2.log\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.stats.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n      Unique Values: \"1081\"\n      Name: \"unicarbkb_id\"\n     Description: \"\"\n      Unique Values: \"755\"\n      Name: \"glycosylation_site_uniprotkb\"\n     Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n      Unique Values: \"1312\"\n      Name: \"glycosylation_type\"\n     Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n      Unique Values: \"2\"\n      Name: \"amino_acid\"\n     Description: \"Three letter abbreviation code of the amino acid\"\n      Unique Values: \"4\"\n      Name: \"evidence\"\n     Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n      Unique Values: \"165\"\n      Name: \"additonal_notes\"\n     Description: \"\"\n      Unique Values: \"19\"\n      Name: \"composition\"\n     Description: \"Composition of glycan\"\n      Unique Values: \"196\"\n      Name: \"glytoucan_ac\"\n     Description: \"\"\n      Unique Values: \"582\"\n      Name: \"curation_notes\"\n     Description: \"\"\n      Unique Values: \"150\"",
    "downloadurl": "/ln2data/releases/data/v-1.4.5/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"
}
