{
    "bcoid": "GLY_000465",
    "title": "SARS-CoV1 Protein Site Annotation",
    "description": "The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] ...",
    "filename": "sarscov1_protein_site_annotation_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": [
            "SARS coronavirus (SARS-CoV-1)"
        ],
        "molecule": [
            "Protein"
        ],
        "tags": [
            "site annotation"
        ],
        "file_type": [
            "csv"
        ],
        "status": [
            "Reviewed"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "P59596-1...",
                "M..."
            ],
            [
                "P59596-1...",
                "M..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "gene_symbol..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "gene_symbol"
                },
                {
                    "type": "string",
                    "label": "ann_type"
                },
                {
                    "type": "string",
                    "label": "start_pos"
                },
                {
                    "type": "string",
                    "label": "end_pos"
                },
                {
                    "type": "string",
                    "label": "annotation"
                },
                {
                    "type": "string",
                    "label": "ecoid"
                },
                {
                    "type": "string",
                    "label": "ref_aa"
                },
                {
                    "type": "string",
                    "label": "alt_aa"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                }
            ],
            [
                "P59596-1",
                "M",
                "Glycosylation_Annotation",
                "4",
                "4",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000269",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Glycosylation_Annotation",
                "4",
                "4",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000269",
                "N",
                "",
                "protein_xref_pubmed",
                "19534833"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "27",
                "27",
                "In strain: Isolate CUHK-Su10, Isolate TWC2, Isolate TWC3, Isolate TWH, Isolate TWJ, Isolate TWK, Isolate TWS, Isolate TWY, Isolate Taiwan TC1, Isolate Taiwan TC2 and Isolate Taiwan TC3.",
                "",
                "F",
                "C",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "73",
                "73",
                "In strain: Isolate TC3.",
                "",
                "N",
                "T",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "119",
                "119",
                "In strain: Isolate Shanghai QXC1.",
                "",
                "L",
                "P",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "11",
                "11",
                "In strain: Isolate Sin2500.",
                "",
                "E",
                "K",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "154",
                "154",
                "In strain: Isolate Urbani.",
                "",
                "S",
                "P",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "M",
                "Natural_Variant_Annotation",
                "68",
                "68",
                "In strain: Isolate HKU-39849, Isolate FRA and Isolate Frankfurt 1.",
                "",
                "A",
                "V",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "667",
                "668",
                "Cleavage",
                "ECO_0000255",
                "RS",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "667",
                "668",
                "Cleavage",
                "ECO_0000255",
                "RS",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "667",
                "668",
                "Cleavage",
                "ECO_0000269",
                "RS",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "667",
                "668",
                "Cleavage",
                "ECO_0000269",
                "RS",
                "",
                "protein_xref_pubmed",
                "19321428"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "797",
                "798",
                "Cleavage",
                "ECO_0000269",
                "RS",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "797",
                "798",
                "Cleavage",
                "ECO_0000269",
                "RS",
                "",
                "protein_xref_pubmed",
                "19321428"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "797",
                "798",
                "Cleavage",
                "ECO_0000255",
                "RS",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Site_Annotation",
                "797",
                "798",
                "Cleavage",
                "ECO_0000255",
                "RS",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1080",
                "1080",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1080",
                "1080",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "699",
                "699",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "699",
                "699",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1056",
                "1056",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1056",
                "1056",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "158",
                "158",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "158",
                "158",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "783",
                "783",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "783",
                "783",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "602",
                "602",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "602",
                "602",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "269",
                "269",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "269",
                "269",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "318",
                "318",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "318",
                "318",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "118",
                "118",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "118",
                "118",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1116",
                "1116",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1116",
                "1116",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "589",
                "589",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "589",
                "589",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "227",
                "227",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "227",
                "227",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "119",
                "119",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "119",
                "119",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "29",
                "29",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "29",
                "29",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "73",
                "73",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "73",
                "73",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "330",
                "330",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "330",
                "330",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1176",
                "1176",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1176",
                "1176",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "109",
                "109",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "109",
                "109",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "357",
                "357",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "357",
                "357",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "691",
                "691",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "691",
                "691",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1155",
                "1155",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1155",
                "1155",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1140",
                "1140",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "1140",
                "1140",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "65",
                "65",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Glycosylation_Annotation",
                "65",
                "65",
                "N-linked (GlcNAc...) asparagine; by host",
                "ECO_0000255",
                "N",
                "",
                "protein_xref_pubmed",
                "MF_04099"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "467",
                "467",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "467",
                "467",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "454",
                "454",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "454",
                "454",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "797",
                "797",
                "Complete loss of trypsin-induced membrane fusion.",
                "ECO_0000269",
                "R",
                "N",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "797",
                "797",
                "Complete loss of trypsin-induced membrane fusion.",
                "ECO_0000269",
                "R",
                "N",
                "protein_xref_pubmed",
                "19321428"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "1253",
                "1253",
                "Decrease in Golgi localization, and complete loss of COPI binding; when associated with A-1251.",
                "ECO_0000269",
                "H",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "1253",
                "1253",
                "Decrease in Golgi localization, and complete loss of COPI binding; when associated with A-1251.",
                "ECO_0000269",
                "H",
                "A",
                "protein_xref_pubmed",
                "17166901"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "463",
                "463",
                "Partial loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "463",
                "463",
                "Partial loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "480",
                "480",
                "No effect on human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "480",
                "480",
                "No effect on human ACE2 binding in vitro.",
                "ECO_0000269",
                "D",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "474",
                "474",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "474",
                "474",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "672",
                "672",
                "No effect on cell-cell fusion.",
                "ECO_0000269",
                "K",
                "S",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "672",
                "672",
                "No effect on cell-cell fusion.",
                "ECO_0000269",
                "K",
                "S",
                "protein_xref_pubmed",
                "16519916"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "348",
                "348",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "348",
                "348",
                "Complete loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "1251",
                "1251",
                "Decrease in Golgi localization, and complete loss of COPI binding; when associated with A-1253.",
                "ECO_0000269",
                "K",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "1251",
                "1251",
                "Decrease in Golgi localization, and complete loss of COPI binding; when associated with A-1253.",
                "ECO_0000269",
                "K",
                "A",
                "protein_xref_pubmed",
                "17166901"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "452",
                "452",
                "90% loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "E",
                "A",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "S",
                "Mutagenesis_Annotation",
                "452",
                "452",
                "90% loss of human ACE2 binding in vitro.",
                "ECO_0000269",
                "E",
                "A",
                "protein_xref_pubmed",
                "14670965"
            ]
        ]
    },
    "readme": "Name\n   - SARS-CoV1 Protein Site Annotation\n\nVersion\n   - v-2.1.1\n\nCreated on\n  - 2020-04-09T13:22:15.821413\n\nModified on\n   - 2022-09-26T09:05:56.467926\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen\n\nDescription Domain\n   Keywords\n   - site annotation\n   - amino acid range\n   - UniProtKB\n\n   Pipeline Steps\n   - Step-1: The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequences and extracts as a dataset in a csv format. \n\nExecution Domain\n   Scripts   - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-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: sarscov1_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_masterlist.csv\n      Name: uniprot-proteome-sars-coronavirus.nt\n      URI: /data/shared/glyds/downloads/ebi/2023_02/uniprot-proteome-sars-coronavirus.nt\n   Output Subdomain\n      Name: sarscov1_protein_site_annotation_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv\n      Name: sarscov1_protein_site_annotation_uniprotkb.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"12\"\n      Name: \"gene_symbol\"\n     Description: \"\"Official gene name/symbol assigned to the gene. Human gene names/symbols are approved by the HUGO Gene Nomenclature Committee (HGNC)\"\n      Unique Values: \"6\"\n      Name: \"ann_type\"\n     Description: \"Annotation Type\"\n      Unique Values: \"6\"\n      Name: \"start_pos\"\n     Description: \"Start position of the gene on the chromosome\"\n      Unique Values: \"239\"\n      Name: \"end_pos\"\n     Description: \"End position of the gene on the chromosome\"\n      Unique Values: \"242\"\n      Name: \"annotation\"\n     Description: \"Function annotation from UniProtKB|RefSeq database\"\n      Unique Values: \"96\"\n      Name: \"ecoid\"\n     Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n      Unique Values: \"4\"\n      Name: \"ref_aa\"\n     Description: \"Reference amino acid residue\"\n      Unique Values: \"44\"\n      Name: \"alt_aa\"\n     Description: \"Altered amino acid residue\"\n      Unique Values: \"34\"\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: \"39\"",
    "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv"
}
