{
    "bcoid": "GLY_000481",
    "title": "Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified]",
    "description": "List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) ...",
    "filename": "human_proteoform_glycosylation_sites_literature_mining.csv",
    "filetype": "csv",
    "categories": {
        "status": [
            "Reviewed"
        ],
        "molecule": [
            "Proteoform"
        ],
        "species": [
            "Homo sapiens"
        ],
        "tag": [
            "glycosylation sites"
        ],
        "file_type": [
            "csv"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "Q11128-1...",
                "105..."
            ],
            [
                "Q11128-1...",
                "105..."
            ]
        ],
        "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": "additional_notes"
                },
                {
                    "type": "string",
                    "label": "n_sequon"
                },
                {
                    "type": "string",
                    "label": "n_sequon_type"
                },
                {
                    "type": "string",
                    "label": "start_pos"
                },
                {
                    "type": "string",
                    "label": "end_pos"
                },
                {
                    "type": "string",
                    "label": "start_aa"
                },
                {
                    "type": "string",
                    "label": "end_aa"
                },
                {
                    "type": "string",
                    "label": "site_seq"
                }
            ],
            [
                "Q11128-1",
                "105",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "11511810",
                "protein_xref_automatic_literature_mining",
                "11511810",
                "source files=glycosylation_sites_legacy",
                "NIT",
                "NXT",
                "105",
                "105",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q11128-1",
                "105",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "11511810",
                "protein_xref_automatic_literature_mining",
                "11511810",
                "source files=glycosylation_sites_legacy",
                "NIT",
                "NXT",
                "105",
                "105",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60911-1",
                "221",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "22967898",
                "protein_xref_automatic_literature_mining",
                "22967898",
                "source files=glycosylation_sites_legacy",
                "NDT",
                "NXT",
                "221",
                "221",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60911-1",
                "221",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "22967898",
                "protein_xref_automatic_literature_mining",
                "22967898",
                "source files=glycosylation_sites_legacy",
                "NDT",
                "NXT",
                "221",
                "221",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P42262-1",
                "413",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "26271046",
                "protein_xref_automatic_literature_mining",
                "26271046",
                "source files=glycosylation_sites_legacy",
                "NKT",
                "NXT",
                "413",
                "413",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P42262-1",
                "413",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "26271046",
                "protein_xref_automatic_literature_mining",
                "26271046",
                "source files=glycosylation_sites_legacy",
                "NKT",
                "NXT",
                "413",
                "413",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P12643-1",
                "135",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "24336949",
                "protein_xref_automatic_literature_mining",
                "24336949",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "135",
                "135",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P12643-1",
                "135",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "24336949",
                "protein_xref_automatic_literature_mining",
                "24336949",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "135",
                "135",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35354-1",
                "130",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "11258925",
                "protein_xref_automatic_literature_mining",
                "11258925",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "130",
                "130",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35354-1",
                "130",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "11258925",
                "protein_xref_automatic_literature_mining",
                "11258925",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "130",
                "130",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P60508-1",
                "133",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "26853155",
                "protein_xref_automatic_literature_mining",
                "26853155",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "133",
                "133",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P60508-1",
                "133",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "26853155",
                "protein_xref_automatic_literature_mining",
                "26853155",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "133",
                "133",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NUM4-1",
                "183",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23742080",
                "protein_xref_automatic_literature_mining",
                "23742080",
                "source files=glycosylation_sites_set_30k",
                "NIT",
                "NXT",
                "183",
                "183",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NUM4-1",
                "183",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23742080",
                "protein_xref_automatic_literature_mining",
                "23742080",
                "source files=glycosylation_sites_set_30k",
                "NIT",
                "NXT",
                "183",
                "183",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P16662-1",
                "315",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "22240840",
                "protein_xref_automatic_literature_mining",
                "22240840",
                "source files=glycosylation_sites_legacy",
                "NMT",
                "NXT",
                "315",
                "315",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P16662-1",
                "315",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "22240840",
                "protein_xref_automatic_literature_mining",
                "22240840",
                "source files=glycosylation_sites_legacy",
                "NMT",
                "NXT",
                "315",
                "315",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O75355-1",
                "81",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "18404400",
                "protein_xref_automatic_literature_mining",
                "18404400",
                "source files=glycosylation_sites_legacy",
                "NNT",
                "NXT",
                "81",
                "81",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O75355-1",
                "81",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "18404400",
                "protein_xref_automatic_literature_mining",
                "18404400",
                "source files=glycosylation_sites_legacy",
                "NNT",
                "NXT",
                "81",
                "81",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "172",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "source files=glycosylation_sites_legacy",
                "NGS",
                "NXS",
                "172",
                "172",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "172",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "source files=glycosylation_sites_legacy",
                "NGS",
                "NXS",
                "172",
                "172",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35052-1",
                "79",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "21932778",
                "protein_xref_automatic_literature_mining",
                "21932778",
                "source files=glycosylation_sites_legacy",
                "NRS",
                "NXS",
                "79",
                "79",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35052-1",
                "79",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "21932778",
                "protein_xref_automatic_literature_mining",
                "21932778",
                "source files=glycosylation_sites_legacy",
                "NRS",
                "NXS",
                "79",
                "79",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01854-2",
                "264",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "26687240",
                "protein_xref_automatic_literature_mining",
                "26687240",
                "source files=glycosylation_sites_set_30k",
                "NHS",
                "NXS",
                "264",
                "264",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01854-2",
                "264",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "26687240",
                "protein_xref_automatic_literature_mining",
                "26687240",
                "source files=glycosylation_sites_set_30k",
                "NHS",
                "NXS",
                "264",
                "264",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9BYF1-1",
                "90",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "32766576",
                "protein_xref_automatic_literature_mining",
                "32766576",
                "source files=glycosylation_sites_set_30k",
                "NLT",
                "NXT",
                "90",
                "90",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9BYF1-1",
                "90",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "32766576",
                "protein_xref_automatic_literature_mining",
                "32766576",
                "source files=glycosylation_sites_set_30k",
                "NLT",
                "NXT",
                "90",
                "90",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P40879-1",
                "165",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "22159084",
                "protein_xref_automatic_literature_mining",
                "22159084",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "165",
                "165",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P40879-1",
                "165",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "22159084",
                "protein_xref_automatic_literature_mining",
                "22159084",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "165",
                "165",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P00738-1",
                "207",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "17803183",
                "protein_xref_automatic_literature_mining",
                "17803183",
                "source files=glycosylation_sites_legacy",
                "NHS",
                "NXS",
                "207",
                "207",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P00738-1",
                "207",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "17803183",
                "protein_xref_automatic_literature_mining",
                "17803183",
                "source files=glycosylation_sites_legacy",
                "NHS",
                "NXS",
                "207",
                "207",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "371",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "371",
                "371",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "371",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "371",
                "371",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9UP52-1",
                "754",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23556518",
                "protein_xref_automatic_literature_mining",
                "23556518",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "754",
                "754",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9UP52-1",
                "754",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23556518",
                "protein_xref_automatic_literature_mining",
                "23556518",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "754",
                "754",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q14542-1",
                "57",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "12590919",
                "protein_xref_automatic_literature_mining",
                "12590919",
                "source files=glycosylation_sites_legacy",
                "NHT",
                "NXT",
                "57",
                "57",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q14542-1",
                "57",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "12590919",
                "protein_xref_automatic_literature_mining",
                "12590919",
                "source files=glycosylation_sites_legacy",
                "NHT",
                "NXT",
                "57",
                "57",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35354-1",
                "580",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9126611",
                "protein_xref_automatic_literature_mining",
                "9126611",
                "source files=glycosylation_sites_legacy",
                "NAS",
                "NXS",
                "580",
                "580",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35354-1",
                "580",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9126611",
                "protein_xref_automatic_literature_mining",
                "9126611",
                "source files=glycosylation_sites_legacy",
                "NAS",
                "NXS",
                "580",
                "580",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O15431-1",
                "15",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "17525160",
                "protein_xref_automatic_literature_mining",
                "17525160",
                "source files=glycosylation_sites_legacy",
                "NST",
                "NXT",
                "15",
                "15",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O15431-1",
                "15",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "17525160",
                "protein_xref_automatic_literature_mining",
                "17525160",
                "source files=glycosylation_sites_legacy",
                "NST",
                "NXT",
                "15",
                "15",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NPF0-1",
                "195",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23603833",
                "protein_xref_automatic_literature_mining",
                "23603833",
                "source files=glycosylation_sites_legacy",
                "NAT",
                "NXT",
                "195",
                "195",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NPF0-1",
                "195",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23603833",
                "protein_xref_automatic_literature_mining",
                "23603833",
                "source files=glycosylation_sites_legacy",
                "NAT",
                "NXT",
                "195",
                "195",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q6ZPD9-1",
                "319",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "29405629",
                "protein_xref_automatic_literature_mining",
                "29405629",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "319",
                "319",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q6ZPD9-1",
                "319",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "29405629",
                "protein_xref_automatic_literature_mining",
                "29405629",
                "source files=glycosylation_sites_legacy",
                "NLS",
                "NXS",
                "319",
                "319",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P02730-1",
                "642",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10364201",
                "protein_xref_automatic_literature_mining",
                "10364201",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "642",
                "642",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P02730-1",
                "642",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10364201",
                "protein_xref_automatic_literature_mining",
                "10364201",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "642",
                "642",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q8NHS3-1",
                "376",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "20406422",
                "protein_xref_automatic_literature_mining",
                "20406422",
                "source files=glycosylation_sites_legacy",
                "NTT",
                "NXT",
                "376",
                "376",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q8NHS3-1",
                "376",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "20406422",
                "protein_xref_automatic_literature_mining",
                "20406422",
                "source files=glycosylation_sites_legacy",
                "NTT",
                "NXT",
                "376",
                "376",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NZC2-1",
                "20",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "36095053",
                "protein_xref_automatic_literature_mining",
                "36095053",
                "source files=glycosylation_sites_set_30k",
                "NTT",
                "NXT",
                "20",
                "20",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9NZC2-1",
                "20",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "36095053",
                "protein_xref_automatic_literature_mining",
                "36095053",
                "source files=glycosylation_sites_set_30k",
                "NTT",
                "NXT",
                "20",
                "20",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9Y6Y9-1",
                "26",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "11544325",
                "protein_xref_automatic_literature_mining",
                "11544325",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "26",
                "26",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9Y6Y9-1",
                "26",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "11544325",
                "protein_xref_automatic_literature_mining",
                "11544325",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "26",
                "26",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P08473-1",
                "628",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "22766194",
                "protein_xref_automatic_literature_mining",
                "22766194",
                "source files=glycosylation_sites_legacy",
                "NFS",
                "NXS",
                "628",
                "628",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P08473-1",
                "628",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "22766194",
                "protein_xref_automatic_literature_mining",
                "22766194",
                "source files=glycosylation_sites_legacy",
                "NFS",
                "NXS",
                "628",
                "628",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P00450-1",
                "397",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "29427759",
                "protein_xref_automatic_literature_mining",
                "29427759",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "397",
                "397",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P00450-1",
                "397",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "29427759",
                "protein_xref_automatic_literature_mining",
                "29427759",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "397",
                "397",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q10471-1",
                "25",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "29097258",
                "protein_xref_automatic_literature_mining",
                "29097258",
                "source files=glycosylation_sites_legacy",
                "",
                "",
                "25",
                "25",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "Q10471-1",
                "25",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "29097258",
                "protein_xref_automatic_literature_mining",
                "29097258",
                "source files=glycosylation_sites_legacy",
                "",
                "",
                "25",
                "25",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P25116-1",
                "250",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "21550978",
                "protein_xref_automatic_literature_mining",
                "21550978",
                "source files=glycosylation_sites_legacy",
                "NIT",
                "NXT",
                "250",
                "250",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P25116-1",
                "250",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "21550978",
                "protein_xref_automatic_literature_mining",
                "21550978",
                "source files=glycosylation_sites_legacy",
                "NIT",
                "NXT",
                "250",
                "250",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35575-1",
                "276",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9705299",
                "protein_xref_automatic_literature_mining",
                "9705299",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "276",
                "276",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P35575-1",
                "276",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9705299",
                "protein_xref_automatic_literature_mining",
                "9705299",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "276",
                "276",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P02730-1",
                "642",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "11876646",
                "protein_xref_automatic_literature_mining",
                "11876646",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "642",
                "642",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P02730-1",
                "642",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "11876646",
                "protein_xref_automatic_literature_mining",
                "11876646",
                "source files=glycosylation_sites_legacy",
                "NSS",
                "NXS",
                "642",
                "642",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P19634-1",
                "410",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "8068684",
                "protein_xref_automatic_literature_mining",
                "8068684",
                "source files=glycosylation_sites_legacy",
                "NWT",
                "NXT",
                "410",
                "410",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P19634-1",
                "410",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "8068684",
                "protein_xref_automatic_literature_mining",
                "8068684",
                "source files=glycosylation_sites_legacy",
                "NWT",
                "NXT",
                "410",
                "410",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9Y5Q5-1",
                "1022",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "25451932",
                "protein_xref_automatic_literature_mining",
                "25451932",
                "source files=glycosylation_sites_set_30k;glycosylation_sites_legacy",
                "NVS",
                "NXS",
                "1022",
                "1022",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q9Y5Q5-1",
                "1022",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "25451932",
                "protein_xref_automatic_literature_mining",
                "25451932",
                "source files=glycosylation_sites_set_30k;glycosylation_sites_legacy",
                "NVS",
                "NXS",
                "1022",
                "1022",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P08842-1",
                "259",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "18180093",
                "protein_xref_automatic_literature_mining",
                "18180093",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "259",
                "259",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P08842-1",
                "259",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "18180093",
                "protein_xref_automatic_literature_mining",
                "18180093",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "259",
                "259",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q2MKA7-1",
                "137",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "27314333",
                "protein_xref_automatic_literature_mining",
                "27314333",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "137",
                "137",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q2MKA7-1",
                "137",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "27314333",
                "protein_xref_automatic_literature_mining",
                "27314333",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "137",
                "137",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q14624-1",
                "81",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "24884609",
                "protein_xref_automatic_literature_mining",
                "24884609",
                "source files=glycosylation_sites_legacy",
                "NFS",
                "NXS",
                "81",
                "81",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q14624-1",
                "81",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "24884609",
                "protein_xref_automatic_literature_mining",
                "24884609",
                "source files=glycosylation_sites_legacy",
                "NFS",
                "NXS",
                "81",
                "81",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q7Z2H8-1",
                "174",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "19409386",
                "protein_xref_automatic_literature_mining",
                "19409386",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "174",
                "174",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q7Z2H8-1",
                "174",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "19409386",
                "protein_xref_automatic_literature_mining",
                "19409386",
                "source files=glycosylation_sites_legacy",
                "NGT",
                "NXT",
                "174",
                "174",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21217-1",
                "154",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10988254",
                "protein_xref_automatic_literature_mining",
                "10988254",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "154",
                "154",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21217-1",
                "154",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10988254",
                "protein_xref_automatic_literature_mining",
                "10988254",
                "source files=glycosylation_sites_legacy",
                "NLT",
                "NXT",
                "154",
                "154",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q16552-1",
                "68",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23069765",
                "protein_xref_automatic_literature_mining",
                "23069765",
                "source files=glycosylation_sites_legacy",
                "NRS",
                "NXS",
                "68",
                "68",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "Q16552-1",
                "68",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23069765",
                "protein_xref_automatic_literature_mining",
                "23069765",
                "source files=glycosylation_sites_legacy",
                "NRS",
                "NXS",
                "68",
                "68",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P37288-1",
                "27",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "11415438",
                "protein_xref_automatic_literature_mining",
                "11415438",
                "source files=glycosylation_sites_legacy",
                "NTS",
                "NXS",
                "27",
                "27",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P37288-1",
                "27",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "11415438",
                "protein_xref_automatic_literature_mining",
                "11415438",
                "source files=glycosylation_sites_legacy",
                "NTS",
                "NXS",
                "27",
                "27",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01023-1",
                "1089",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "12218066",
                "protein_xref_automatic_literature_mining",
                "12218066",
                "source files=glycosylation_sites_legacy",
                "NAI",
                "other",
                "1089",
                "1089",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01023-1",
                "1089",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "12218066",
                "protein_xref_automatic_literature_mining",
                "12218066",
                "source files=glycosylation_sites_legacy",
                "NAI",
                "other",
                "1089",
                "1089",
                "Asn",
                "Asn",
                "N"
            ]
        ]
    },
    "readme": "Name\n   - Human Glycosylation Sites [Automatic Literature Mining] [Automatically verified]\n\nVersion\n   - v-2.4.1\n\nCreated on\n  - 2020-04-20T16:47:37.482643\n\nModified on\n   - 2022-09-26T09:05:56.438739\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n   - Vijay Shanker [vijay@udel.edu], Karen Ross [ker25@georgetown.edu]\n\nChecksum\n   - \n\nUsability Domain\n   - List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). 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   - GlyTouCan\n   - Automatic Literature Mining\n\n   Pipeline Steps\n   - Step-1: The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. \n\nExecution Domain\n   Scripts   - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py\n\n\n   Software Prerequisites\n      Name: Python\n      Version: 2.7.5\n      URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n   Input Subdomain\n      Name: n_sequon_info.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/n_sequon_info.csv\n      Name: sample_mapping.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/misc/sample_mapping.csv\n      Name: cellosaurus.txt\n      URI: https:/data.glygen.org/ln2downloads/cellosaurus/2024_01_31/cellosaurus.txt\n      Name: glycosylation_sites_legacy.csv\n      URI: https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/glycosylation_sites_legacy.csv\n      Name: glycosylation_sites_set_30k.csv\n      URI: https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/glycosylation_sites_set_30k.csv\n   Output Subdomain\n      Name: human_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"244\"\n      Name: \"glycosylation_site_uniprotkb\"\n     Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n      Unique Values: \"338\"\n      Name: \"amino_acid\"\n     Description: \"Three letter abbreviation code of the amino acid\"\n      Unique Values: \"5\"\n      Name: \"saccharide\"\n     Description: \"Sugar\"\n      Unique Values: \"1\"\n      Name: \"glycosylation_type\"\n     Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n      Unique Values: \"3\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"2\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"299\"\n      Name: \"src_xref_key\"\n     Description: \"Source Xref  key\"\n      Unique Values: \"1\"\n      Name: \"src_xref_id\"\n     Description: \"Source X-ref ID\"\n      Unique Values: \"299\"\n      Name: \"additional_notes\"\n     Description: \"\"\n      Unique Values: \"3\"\n      Name: \"n_sequon\"\n     Description: \"\"\n      Unique Values: \"66\"\n      Name: \"n_sequon_type\"\n     Description: \"\"\n      Unique Values: \"7\"\n      Name: \"start_pos\"\n     Description: \"Start position of the gene on the chromosome\"\n      Unique Values: \"338\"\n      Name: \"end_pos\"\n     Description: \"End position of the gene on the chromosome\"\n      Unique Values: \"338\"\n      Name: \"start_aa\"\n     Description: \"\"\n      Unique Values: \"5\"\n      Name: \"end_aa\"\n     Description: \"\"\n      Unique Values: \"5\"\n      Name: \"site_seq\"\n     Description: \"\"\n      Unique Values: \"5\"",
    "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"
}
