{
    "bcoid": "GLY_000582",
    "title": "Human glycosylation sites [Automatic literature Mining] [Manually 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_manually_verified.csv",
    "filetype": "csv",
    "categories": {
        "status": [
            "Reviewed"
        ],
        "molecule": [
            "Proteoform"
        ],
        "species": [
            "Homo sapiens"
        ],
        "tag": [
            "glycosylation sites"
        ],
        "file_type": [
            "csv"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "O00555-8...",
                "283..."
            ],
            [
                "O00555-8...",
                "283..."
            ]
        ],
        "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": "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"
                }
            ],
            [
                "O00555-8",
                "283",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "29470411",
                "protein_xref_automatic_literature_mining",
                "29470411",
                "NGT",
                "NXT",
                "283",
                "283",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O00555-8",
                "283",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "29470411",
                "protein_xref_automatic_literature_mining",
                "29470411",
                "NGT",
                "NXT",
                "283",
                "283",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O00622-1",
                "242",
                "Thr",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "26424659",
                "protein_xref_automatic_literature_mining",
                "26424659",
                "",
                "",
                "242",
                "242",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "O00622-1",
                "242",
                "Thr",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "26424659",
                "protein_xref_automatic_literature_mining",
                "26424659",
                "",
                "",
                "242",
                "242",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "O14672-1",
                "267",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "18381078",
                "protein_xref_automatic_literature_mining",
                "18381078",
                "NIS",
                "NXS",
                "267",
                "267",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O14672-1",
                "267",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "18381078",
                "protein_xref_automatic_literature_mining",
                "18381078",
                "NIS",
                "NXS",
                "267",
                "267",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O43490-1",
                "548",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "26029999",
                "protein_xref_automatic_literature_mining",
                "26029999",
                "NKS",
                "NXS",
                "548",
                "548",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O43490-1",
                "548",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "26029999",
                "protein_xref_automatic_literature_mining",
                "26029999",
                "NKS",
                "NXS",
                "548",
                "548",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60779-1",
                "314",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "NYT",
                "NXT",
                "314",
                "314",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60779-1",
                "314",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "12065289",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "NYT",
                "NXT",
                "314",
                "314",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60779-1",
                "63",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "NLT",
                "NXT",
                "63",
                "63",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O60779-1",
                "63",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "12065289",
                "protein_xref_automatic_literature_mining",
                "12065289",
                "NLT",
                "NXT",
                "63",
                "63",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O75355-1",
                "149",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "28956227",
                "protein_xref_automatic_literature_mining",
                "28956227",
                "NET",
                "NXT",
                "149",
                "149",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O75355-1",
                "149",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "28956227",
                "protein_xref_automatic_literature_mining",
                "28956227",
                "NET",
                "NXT",
                "149",
                "149",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O94856-1",
                "467",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "24497634",
                "protein_xref_automatic_literature_mining",
                "24497634",
                "NGQ",
                "other",
                "467",
                "467",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O94856-1",
                "467",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "24497634",
                "protein_xref_automatic_literature_mining",
                "24497634",
                "NGQ",
                "other",
                "467",
                "467",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95180-1",
                "1466",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "NIS",
                "NXS",
                "1466",
                "1466",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95180-1",
                "1466",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23503728",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "NIS",
                "NXS",
                "1466",
                "1466",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95180-1",
                "192",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "NVS",
                "NXS",
                "192",
                "192",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95180-1",
                "192",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "23503728",
                "protein_xref_automatic_literature_mining",
                "23503728",
                "NVS",
                "NXS",
                "192",
                "192",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95832-1",
                "192",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "192",
                "192",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "192",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "192",
                "192",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "205",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "205",
                "205",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "205",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "205",
                "205",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "206",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "206",
                "206",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "206",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "206",
                "206",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "O95832-1",
                "191",
                "Thr",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "191",
                "191",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "O95832-1",
                "191",
                "Thr",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "21569618",
                "protein_xref_automatic_literature_mining",
                "21569618",
                "",
                "",
                "191",
                "191",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "O95980-1",
                "200",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NYT",
                "NXT",
                "200",
                "200",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95980-1",
                "200",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NYT",
                "NXT",
                "200",
                "200",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95980-1",
                "297",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NTS",
                "NXS",
                "297",
                "297",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95980-1",
                "297",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NTS",
                "NXS",
                "297",
                "297",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95980-1",
                "86",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NSS",
                "NXS",
                "86",
                "86",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "O95980-1",
                "86",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "16103099",
                "protein_xref_automatic_literature_mining",
                "16103099",
                "NSS",
                "NXS",
                "86",
                "86",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01042-1",
                "180",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "14977046",
                "protein_xref_automatic_literature_mining",
                "14977046",
                "NEV",
                "NXV",
                "180",
                "180",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01042-1",
                "180",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "14977046",
                "protein_xref_automatic_literature_mining",
                "14977046",
                "NEV",
                "NXV",
                "180",
                "180",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P01876-2",
                "225",
                "Thr",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "9442070",
                "protein_xref_automatic_literature_mining",
                "9442070",
                "",
                "",
                "225",
                "225",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "P01876-2",
                "225",
                "Thr",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "9442070",
                "protein_xref_automatic_literature_mining",
                "9442070",
                "",
                "",
                "225",
                "225",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "15009203",
                "protein_xref_automatic_literature_mining",
                "15009203",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "15009203",
                "protein_xref_automatic_literature_mining",
                "15009203",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "1576999",
                "protein_xref_automatic_literature_mining",
                "1576999",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "1576999",
                "protein_xref_automatic_literature_mining",
                "1576999",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "27638310",
                "protein_xref_automatic_literature_mining",
                "27638310",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P04141-1",
                "5",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "27638310",
                "protein_xref_automatic_literature_mining",
                "27638310",
                "",
                "",
                "5",
                "5",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P05186-1",
                "271",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "26797772",
                "protein_xref_automatic_literature_mining",
                "26797772",
                "NRT",
                "NXT",
                "271",
                "271",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P05186-1",
                "271",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "26797772",
                "protein_xref_automatic_literature_mining",
                "26797772",
                "NRT",
                "NXT",
                "271",
                "271",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P05231-1",
                "89",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "19690161",
                "protein_xref_automatic_literature_mining",
                "19690161",
                "NLN",
                "other",
                "89",
                "89",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P05231-1",
                "89",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "19690161",
                "protein_xref_automatic_literature_mining",
                "19690161",
                "NLN",
                "other",
                "89",
                "89",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P07204-1",
                "382",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "NQT",
                "NXT",
                "382",
                "382",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P07204-1",
                "382",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "1314561",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "NQT",
                "NXT",
                "382",
                "382",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P07204-1",
                "409",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "NQT",
                "NXT",
                "409",
                "409",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P07204-1",
                "409",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "1314561",
                "protein_xref_automatic_literature_mining",
                "1314561",
                "NQT",
                "NXT",
                "409",
                "409",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P17342-1",
                "349",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "7727388",
                "protein_xref_automatic_literature_mining",
                "7727388",
                "NME",
                "other",
                "349",
                "349",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P17342-1",
                "349",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "7727388",
                "protein_xref_automatic_literature_mining",
                "7727388",
                "NME",
                "other",
                "349",
                "349",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P13473-1",
                "181",
                "Thr",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "8323299",
                "protein_xref_automatic_literature_mining",
                "8323299",
                "",
                "",
                "181",
                "181",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "P13473-1",
                "181",
                "Thr",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "8323299",
                "protein_xref_automatic_literature_mining",
                "8323299",
                "",
                "",
                "181",
                "181",
                "Thr",
                "Thr",
                "T"
            ],
            [
                "P07196-1",
                "34",
                "Ser",
                "",
                "O-linked",
                "protein_xref_automatic_literature_mining",
                "8702840",
                "protein_xref_automatic_literature_mining",
                "8702840",
                "",
                "",
                "34",
                "34",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P07196-1",
                "34",
                "Ser",
                "",
                "O-linked",
                "protein_xref_pubmed",
                "8702840",
                "protein_xref_automatic_literature_mining",
                "8702840",
                "",
                "",
                "34",
                "34",
                "Ser",
                "Ser",
                "S"
            ],
            [
                "P61073-1",
                "176",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9151832",
                "protein_xref_automatic_literature_mining",
                "9151832",
                "NVS",
                "NXS",
                "176",
                "176",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P61073-1",
                "176",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9151832",
                "protein_xref_automatic_literature_mining",
                "9151832",
                "NVS",
                "NXS",
                "176",
                "176",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "16",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "NIT",
                "NXT",
                "16",
                "16",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "16",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9587408",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "NIT",
                "NXT",
                "16",
                "16",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "4",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "NGS",
                "NXS",
                "4",
                "4",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "4",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9587408",
                "protein_xref_automatic_literature_mining",
                "9587408",
                "NGS",
                "NXS",
                "4",
                "4",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "16",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "9694965",
                "protein_xref_automatic_literature_mining",
                "9694965",
                "NIT",
                "NXT",
                "16",
                "16",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P21731-3",
                "16",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "9694965",
                "protein_xref_automatic_literature_mining",
                "9694965",
                "NIT",
                "NXT",
                "16",
                "16",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P12259-1",
                "2181",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10471296",
                "protein_xref_automatic_literature_mining",
                "10471296",
                "NTN",
                "other",
                "2181",
                "2181",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P12259-1",
                "2181",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10471296",
                "protein_xref_automatic_literature_mining",
                "10471296",
                "NTN",
                "other",
                "2181",
                "2181",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P61073-1",
                "176",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10486146",
                "protein_xref_automatic_literature_mining",
                "10486146",
                "NVS",
                "NXS",
                "176",
                "176",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P61073-1",
                "176",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10486146",
                "protein_xref_automatic_literature_mining",
                "10486146",
                "NVS",
                "NXS",
                "176",
                "176",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P47872-1",
                "72",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10537138",
                "protein_xref_automatic_literature_mining",
                "10537138",
                "NIS",
                "NXS",
                "72",
                "72",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P47872-1",
                "72",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10537138",
                "protein_xref_automatic_literature_mining",
                "10537138",
                "NIS",
                "NXS",
                "72",
                "72",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "371",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "NGT",
                "NXT",
                "371",
                "371",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "371",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "NGT",
                "NXT",
                "371",
                "371",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "86",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "NRT",
                "NXT",
                "86",
                "86",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P14679-1",
                "86",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10713140",
                "protein_xref_automatic_literature_mining",
                "10713140",
                "NRT",
                "NXT",
                "86",
                "86",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P11678-1",
                "327",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10864452",
                "protein_xref_automatic_literature_mining",
                "10864452",
                "NRT",
                "NXT",
                "327",
                "327",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P11678-1",
                "327",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10864452",
                "protein_xref_automatic_literature_mining",
                "10864452",
                "NRT",
                "NXT",
                "327",
                "327",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "153",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NVT",
                "NXT",
                "153",
                "153",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "153",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NVT",
                "NXT",
                "153",
                "153",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "172",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NGS",
                "NXS",
                "172",
                "172",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "172",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NGS",
                "NXS",
                "172",
                "172",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "223",
                "Asn",
                "",
                "N-linked",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NQS",
                "NXS",
                "223",
                "223",
                "Asn",
                "Asn",
                "N"
            ],
            [
                "P56817-1",
                "223",
                "Asn",
                "",
                "N-linked",
                "protein_xref_pubmed",
                "10887202",
                "protein_xref_automatic_literature_mining",
                "10887202",
                "NQS",
                "NXS",
                "223",
                "223",
                "Asn",
                "Asn",
                "N"
            ]
        ]
    },
    "readme": "Name\n   - Human glycosylation sites [Automatic literature Mining] [Manually verified]\n\nVersion\n   - v-2.3.1\n\nCreated on\n  - 2021-08-02T15:33:34.395747\n\nModified on\n   - 2022-09-26T09:08:12.559953\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@email.gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n   - 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). This file contains rows that are detected from automatic literature mining and which failed the automatic QC where the annotation (protein+site) didn't already exist in GlyGen. such rows are then manually verified by curators. 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   - Manual QC\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 wether the annotion (protein +site) is already present in GlyGen or not. Only those rows where extracted where the rows failed the annotation QC i.e where the annotation didn't already exist in GlyGen. Such rows where manually verified by the curators and again only those rows that passed where added to the 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: proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/compiled/proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: fruitfly_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv\n      Name: fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      Name: fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      Name: fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: hcv1a_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv\n      Name: hcv1a_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: human_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv\n      Name: human_proteoform_glycosylation_sites_gptwiki.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv\n      Name: human_proteoform_glycosylation_sites_harvard.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv\n      Name: human_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: human_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      Name: human_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      Name: human_proteoform_glycosylation_sites_o_gluc.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv\n      Name: human_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv\n      Name: human_proteoform_glycosylation_sites_tyr_o_linked.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      Name: human_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: mouse_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv\n      Name: mouse_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv\n      Name: mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      Name: mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      Name: mouse_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: rat_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv\n      Name: rat_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv\n      Name: rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: rat_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      Name: rat_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      Name: rat_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv\n      Name: rat_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      Name: rat_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: sarscov1_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv\n      Name: sarscov1_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: sarscov2_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv\n      Name: sarscov2_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: sarscov2_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: yeast_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.csv\n      Name: yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv\n      Name: yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv\n      Name: yeast_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: n_sequon_info.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/n_sequon_info.csv\n      Name: sample_mapping.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/sample_mapping.csv\n      Name: cellosaurus.txt\n      URI: https:/data.glygen.org/ln2downloads/cellosaurus/2023_10_11/cellosaurus.txt\n   Output Subdomain\n      Name: human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"94\"\n      Name: \"glycosylation_site_uniprotkb\"\n     Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n      Unique Values: \"133\"\n      Name: \"amino_acid\"\n     Description: \"Three letter abbreviation code of the amino acid\"\n      Unique Values: \"4\"\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: \"105\"\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: \"105\"\n      Name: \"n_sequon\"\n     Description: \"\"\n      Unique Values: \"45\"\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: \"133\"\n      Name: \"end_pos\"\n     Description: \"End position of the gene on the chromosome\"\n      Unique Values: \"133\"\n      Name: \"start_aa\"\n     Description: \"\"\n      Unique Values: \"4\"\n      Name: \"end_aa\"\n     Description: \"\"\n      Unique Values: \"4\"\n      Name: \"site_seq\"\n     Description: \"\"\n      Unique Values: \"4\"",
    "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
}
