{
    "bcoid": "GLY_000041",
    "title": "Glycosylation sites - UniCarbKB [Mouse proteins]",
    "description": "List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if ...",
    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv",
    "filetype": "csv",
    "categories": {
        "status": "Reviewed",
        "molecule": "Proteoform",
        "species": "Mus musculus",
        "tags": "UniCarbKB glycosylation sites",
        "file_type": "csv",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q91ZX7-1...",
                "447..."
            ],
            [
                "Q91ZX7-1...",
                "447..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "glycosylatio..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "glycosylation_site_uniprotkb"
                },
                {
                    "type": "string",
                    "label": "amino_acid"
                },
                {
                    "type": "string",
                    "label": "saccharide"
                },
                {
                    "type": "string",
                    "label": "glycosylation_type"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                },
                {
                    "type": "string",
                    "label": "src_xref_key"
                },
                {
                    "type": "string",
                    "label": "src_xref_id"
                },
                {
                    "type": "string",
                    "label": "start_pos"
                },
                {
                    "type": "string",
                    "label": "end_pos"
                },
                {
                    "type": "string",
                    "label": "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"
                }
            ],
            [
                "Q91ZX7-1",
                "447",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q91ZX7",
                "protein_xref_unicarbkb",
                "Q91ZX7",
                "447",
                "447",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "446",
                "",
                "",
                "",
                "NST",
                "NXT"
            ],
            [
                "Q91ZX7-1",
                "447",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q91ZX7",
                "447",
                "447",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "446",
                "",
                "",
                "",
                "NST",
                "NXT"
            ],
            [
                "Q91ZX7-1",
                "447",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q91ZX7",
                "447",
                "447",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "446",
                "",
                "",
                "",
                "NST",
                "NXT"
            ],
            [
                "Q8BLQ9-1",
                "211",
                "Asn",
                "G12580WI",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q8BLQ9",
                "protein_xref_unicarbkb",
                "Q8BLQ9",
                "211",
                "211",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G12580WI",
                "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "205",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q8BLQ9-1",
                "211",
                "Asn",
                "G12580WI",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q8BLQ9",
                "211",
                "211",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G12580WI",
                "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "205",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q8BLQ9-1",
                "211",
                "Asn",
                "G12580WI",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q8BLQ9",
                "211",
                "211",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G12580WI",
                "HexNAc5Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "205",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G59626AS",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G59626AS",
                "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G59626AS",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G59626AS",
                "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G59626AS",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G59626AS",
                "HexNAc4Hex5dHex0NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "139",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "139",
                "139",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "138",
                "",
                "",
                "",
                "NET",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G72961RM",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G72961RM",
                "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G72961RM",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G72961RM",
                "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G72961RM",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G72961RM",
                "HexNAc6Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G92050GC",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q00493",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G92050GC",
                "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G92050GC",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G92050GC",
                "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q00493-1",
                "390",
                "Asn",
                "G92050GC",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q00493",
                "390",
                "390",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G92050GC",
                "HexNAc2Hex4dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "382",
                "",
                "",
                "",
                "NAT",
                "NXT"
            ],
            [
                "Q9CPW0-1",
                "630",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q9CPW0",
                "protein_xref_unicarbkb",
                "Q9CPW0",
                "630",
                "630",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "627",
                "",
                "",
                "",
                "NMT",
                "NXT"
            ],
            [
                "Q9CPW0-1",
                "630",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q9CPW0",
                "630",
                "630",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "627",
                "",
                "",
                "",
                "NMT",
                "NXT"
            ],
            [
                "Q9CPW0-1",
                "630",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q9CPW0",
                "630",
                "630",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "627",
                "",
                "",
                "",
                "NMT",
                "NXT"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G81572SC",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q640R3",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G81572SC",
                "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G81572SC",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G81572SC",
                "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G81572SC",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G81572SC",
                "HexNAc4Hex4dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q640R3",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "",
                "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "",
                "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "",
                "HexNAc3Hex5dHex1NeuAc2NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G09528DL",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q640R3",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G09528DL",
                "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G09528DL",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G09528DL",
                "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G09528DL",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G09528DL",
                "HexNAc3Hex6dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G67324HN",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q640R3",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G67324HN",
                "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G67324HN",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G67324HN",
                "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q640R3-1",
                "189",
                "Asn",
                "G67324HN",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q640R3",
                "189",
                "189",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G67324HN",
                "HexNAc3Hex5dHex1NeuAc1NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "183",
                "",
                "",
                "",
                "NDS",
                "NXS"
            ],
            [
                "Q05186-1",
                "47",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q05186",
                "protein_xref_unicarbkb",
                "Q05186",
                "47",
                "47",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "32",
                "",
                "",
                "",
                "NQS",
                "NXS"
            ],
            [
                "Q05186-1",
                "47",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q05186",
                "47",
                "47",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "32",
                "",
                "",
                "",
                "NQS",
                "NXS"
            ],
            [
                "Q05186-1",
                "47",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q05186",
                "47",
                "47",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "32",
                "",
                "",
                "",
                "NQS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G31852PQ",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G31852PQ",
                "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G31852PQ",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G31852PQ",
                "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G31852PQ",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G31852PQ",
                "HexNAc2Hex7dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "Q6AXF6-1",
                "83",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q6AXF6",
                "83",
                "83",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "80",
                "",
                "",
                "",
                "NSS",
                "NXS"
            ],
            [
                "P20917-1",
                "99",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "P20917",
                "protein_xref_unicarbkb",
                "P20917",
                "99",
                "99",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NCT",
                "NXT"
            ],
            [
                "P20917-1",
                "99",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "P20917",
                "99",
                "99",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NCT",
                "NXT"
            ],
            [
                "P20917-1",
                "99",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "P20917",
                "99",
                "99",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NCT",
                "NXT"
            ],
            [
                "Q9WTR5-1",
                "598",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q9WTR5",
                "protein_xref_unicarbkb",
                "Q9WTR5",
                "598",
                "598",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NLS",
                "NXS"
            ],
            [
                "Q9WTR5-1",
                "598",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q9WTR5",
                "598",
                "598",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NLS",
                "NXS"
            ],
            [
                "Q9WTR5-1",
                "598",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q9WTR5",
                "598",
                "598",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NLS",
                "NXS"
            ],
            [
                "Q6PHU5-1",
                "404",
                "Asn",
                "G80920RR",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q6PHU5",
                "protein_xref_unicarbkb",
                "Q6PHU5",
                "404",
                "404",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G80920RR",
                "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "391",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q6PHU5-1",
                "404",
                "Asn",
                "G80920RR",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q6PHU5",
                "404",
                "404",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G80920RR",
                "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "391",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q6PHU5-1",
                "404",
                "Asn",
                "G80920RR",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q6PHU5",
                "404",
                "404",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G80920RR",
                "HexNAc2Hex9dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "391",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q9QUR8-1",
                "256",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q9QUR8",
                "protein_xref_unicarbkb",
                "Q9QUR8",
                "256",
                "256",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "244",
                "",
                "",
                "",
                "NVS",
                "NXS"
            ],
            [
                "Q9QUR8-1",
                "256",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q9QUR8",
                "256",
                "256",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "244",
                "",
                "",
                "",
                "NVS",
                "NXS"
            ],
            [
                "Q9QUR8-1",
                "256",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q9QUR8",
                "256",
                "256",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "244",
                "",
                "",
                "",
                "NVS",
                "NXS"
            ],
            [
                "P97952-1",
                "135",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_unicarbkb",
                "P97952",
                "protein_xref_unicarbkb",
                "P97952",
                "135",
                "135",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "126",
                "",
                "",
                "",
                "NTS",
                "NXS"
            ],
            [
                "P97952-1",
                "135",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "P97952",
                "135",
                "135",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "126",
                "",
                "",
                "",
                "NTS",
                "NXS"
            ],
            [
                "P97952-1",
                "135",
                "Asn",
                "G41247ZX",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "P97952",
                "135",
                "135",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G41247ZX",
                "HexNAc2Hex6dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "126",
                "",
                "",
                "",
                "NTS",
                "NXS"
            ],
            [
                "Q7TNR6-1",
                "407",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q7TNR6",
                "protein_xref_unicarbkb",
                "Q7TNR6",
                "407",
                "407",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "402",
                "",
                "",
                "",
                "NGS",
                "NXS"
            ],
            [
                "Q7TNR6-1",
                "407",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q7TNR6",
                "407",
                "407",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "402",
                "",
                "",
                "",
                "NGS",
                "NXS"
            ],
            [
                "Q7TNR6-1",
                "407",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q7TNR6",
                "407",
                "407",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "402",
                "",
                "",
                "",
                "NGS",
                "NXS"
            ],
            [
                "Q9WV91-1",
                "300",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q9WV91",
                "protein_xref_unicarbkb",
                "Q9WV91",
                "300",
                "300",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "294",
                "",
                "",
                "",
                "NIT",
                "NXT"
            ],
            [
                "Q9WV91-1",
                "300",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q9WV91",
                "300",
                "300",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "294",
                "",
                "",
                "",
                "NIT",
                "NXT"
            ],
            [
                "Q9WV91-1",
                "300",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q9WV91",
                "300",
                "300",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "294",
                "",
                "",
                "",
                "NIT",
                "NXT"
            ],
            [
                "Q80ZF8-1",
                "625",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_unicarbkb",
                "Q80ZF8",
                "protein_xref_unicarbkb",
                "Q80ZF8",
                "625",
                "625",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q80ZF8-1",
                "625",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_pubmed",
                "34106099",
                "protein_xref_unicarbkb",
                "Q80ZF8",
                "625",
                "625",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q80ZF8-1",
                "625",
                "Asn",
                "G02815KT",
                "N-linked",
                "protein_xref_doi",
                "10.1039/D0MO00044B",
                "protein_xref_unicarbkb",
                "Q80ZF8",
                "625",
                "625",
                "N",
                "known_site",
                "known_34106099_glygen",
                "G02815KT",
                "HexNAc2Hex5dHex0NeuAc0NeuGc0Pent0S0P0KDN0HexA0",
                "",
                "",
                "",
                "",
                "",
                "NVT",
                "NXT"
            ],
            [
                "Q09163-1",
                "94",
                "ser",
                "G01614ZM",
                "Ser",
                "protein_xref_unicarbkb",
                "Q09163",
                "protein_xref_unicarbkb",
                "Q09163",
                "94",
                "94",
                "S",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "96",
                "",
                "GlycoSuiteDB  curation notes. Reported structure can be attached to the following: S-94, N-100, N-165, N-174, S-216, T-224, T-258, T-267, T-271",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "Q09163-1",
                "94",
                "ser",
                "G01614ZM",
                "Ser",
                "protein_xref_pubmed",
                "9118998",
                "protein_xref_unicarbkb",
                "Q09163",
                "94",
                "94",
                "S",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "96",
                "",
                "GlycoSuiteDB  curation notes. Reported structure can be attached to the following: S-94, N-100, N-165, N-174, S-216, T-224, T-258, T-267, T-271",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "P04925-1",
                "196",
                "asn",
                "",
                "Asn",
                "protein_xref_unicarbkb",
                "P04925",
                "protein_xref_unicarbkb",
                "P04925",
                "196",
                "196",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7455",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "P04925-1",
                "196",
                "asn",
                "",
                "Asn",
                "protein_xref_pubmed",
                "10200178",
                "protein_xref_unicarbkb",
                "P04925",
                "196",
                "196",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7455",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "P04925-1",
                "180",
                "asn",
                "G92129PT",
                "Asn",
                "protein_xref_unicarbkb",
                "P04925",
                "protein_xref_unicarbkb",
                "P04925",
                "180",
                "180",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7641",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "P04925-1",
                "180",
                "asn",
                "G92129PT",
                "Asn",
                "protein_xref_pubmed",
                "10200178",
                "protein_xref_unicarbkb",
                "P04925",
                "180",
                "180",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7641",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "O09164-1",
                "121",
                "asn",
                "G25067TK",
                "Asn",
                "protein_xref_unicarbkb",
                "O09164",
                "protein_xref_unicarbkb",
                "O09164",
                "121",
                "121",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7511",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "O09164-1",
                "121",
                "asn",
                "G25067TK",
                "Asn",
                "protein_xref_pubmed",
                "21573946",
                "protein_xref_unicarbkb",
                "O09164",
                "121",
                "121",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7511",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ],
            [
                "P04925-1",
                "196",
                "asn",
                "",
                "Asn",
                "protein_xref_unicarbkb",
                "P04925",
                "protein_xref_unicarbkb",
                "P04925",
                "196",
                "196",
                "N",
                "known_site",
                "known_legacy_human_mouse_rat_glygen",
                "7580",
                "",
                "",
                "",
                "",
                "",
                "",
                "",
                ""
            ]
        ]
    },
    "readme": "Name\n   - Glycosylation sites - UniCarbKB [Mouse proteins]\n\nVersion\n   - 1.11.2\n\nCreated on\n  - 2019-01-23T17:21:05.908793\n\nModified on\n   - 2020-05-01T15:21:10.499362\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 mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007).\n\nDescription Domain\n   Keywords\n   - proteins\n   - canonical\n   - glycosylation sites\n   - glycan\n   - UniCarbKB\n   - GlyTouCan\n\n   Pipeline Steps\n   - Step-1: The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid.\n\nExecution Domain\n   Scripts   - https://github.com/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: merge_human_rat_mouse_gps_06022020_130220.csv\n      URI: https://data.glygen.org//ln2downloads/unicarbkb/06_24_2021/merge_human_rat_mouse_gps_06022020_130220.csv\n      Name: glycan_properties.tsv\n      URI: https://data.glygen.org//ln2downloads/glytoucan/gtc_06_30_2021/export/glycan_properties.tsv\n      Name: glycan_xref_unicarbkb.csv\n      URI: https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/glycan_xref_unicarbkb.csv\n      Name: mouse_protein_allsequences.fasta\n      URI: https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_allsequences.fasta\n      Name: aadict.csv\n      URI: https://data.glygen.org//ln2data/releases/data/v-1.11.2/misc/aadict.csv\n      Name: classification.tsv\n      URI: https://data.glygen.org//ln2downloads/glytoucan/gtc_06_30_2021/export/classification.tsv\n      Name: mouse_protein_masterlist.csv\n      URI: https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_masterlist.csv\n   Output Subdomain\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.1.log\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.2.log\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.stats.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv",
    "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"
}
