{
    "bcoid": "GLY_000774",
    "title": "Yeast Protein Site Annotation",
    "description": "The Yeast Protein Site Annotation (UniProtKB) dataset contains yeast [taxid:559292] site annotations ...",
    "filename": "yeast_protein_site_annotation_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": [
            "Saccharomyces cerevisiae S288C"
        ],
        "molecule": [
            "Protein"
        ],
        "tag": [
            "site annotation"
        ],
        "file_type": [
            "csv"
        ],
        "status": [
            "Reviewed"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "P39979-1...",
                "HPA3..."
            ],
            [
                "P39979-1...",
                "HPA3..."
            ]
        ],
        "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"
                }
            ],
            [
                "P39979-1",
                "HPA3",
                "Site_Annotation",
                "144",
                "144",
                "Important for catalytic activity",
                "ECO_0000250",
                "Y",
                "",
                "protein_xref_uniprotkb",
                "P39979"
            ],
            [
                "P39979-1",
                "HPA3",
                "Site_Annotation",
                "144",
                "144",
                "Important for catalytic activity",
                "ECO_0000250",
                "Y",
                "",
                "protein_xref_pubmed",
                "Q06592"
            ],
            [
                "P39979-1",
                "HPA3",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P39979"
            ],
            [
                "P39979-1",
                "HPA3",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "22814378"
            ],
            [
                "Q07959-1",
                "IZH3",
                "Glycosylation_Annotation",
                "45",
                "45",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q07959"
            ],
            [
                "Q07959-1",
                "IZH3",
                "Glycosylation_Annotation",
                "123",
                "123",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q07959"
            ],
            [
                "Q07959-1",
                "IZH3",
                "Glycosylation_Annotation",
                "256",
                "256",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q07959"
            ],
            [
                "Q07959-1",
                "IZH3",
                "Glycosylation_Annotation",
                "319",
                "319",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q07959"
            ],
            [
                "Q07959-1",
                "IZH3",
                "Glycosylation_Annotation",
                "153",
                "153",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q07959"
            ],
            [
                "P0CX69-1",
                "TY1A-MR2",
                "Site_Annotation",
                "401",
                "402",
                "Cleavage; by Ty1 protease",
                "",
                "HN",
                "",
                "protein_xref_uniprotkb",
                "P0CX69"
            ],
            [
                "P0CX69-1",
                "TY1A-MR2",
                "Modified_Residue_Annotation",
                "416",
                "416",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P0CX69"
            ],
            [
                "P0CX69-1",
                "TY1A-MR2",
                "Modified_Residue_Annotation",
                "416",
                "416",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q12441"
            ],
            [
                "P25379-1",
                "CHA1",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P25379"
            ],
            [
                "P25379-1",
                "CHA1",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "22814378"
            ],
            [
                "P25379-1",
                "CHA1",
                "Modified_Residue_Annotation",
                "37",
                "37",
                "N6-(pyridoxal phosphate)lysine",
                "",
                "K",
                "",
                "protein_xref_uniprotkb",
                "P25379"
            ],
            [
                "P25378-1",
                "RHB1",
                "Modified_Residue_Annotation",
                "206",
                "206",
                "Cysteine methyl ester",
                "",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25378"
            ],
            [
                "P25378-1",
                "RHB1",
                "Modified_Residue_Annotation",
                "1",
                "1",
                "N-acetylmethionine",
                "ECO_0007744",
                "M",
                "",
                "protein_xref_uniprotkb",
                "P25378"
            ],
            [
                "P25378-1",
                "RHB1",
                "Modified_Residue_Annotation",
                "1",
                "1",
                "N-acetylmethionine",
                "ECO_0007744",
                "M",
                "",
                "protein_xref_pubmed",
                "22814378"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "37",
                "37",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17121"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "37",
                "37",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "491",
                "491",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17121"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "491",
                "491",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18407956"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "491",
                "491",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "491",
                "491",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "17330950"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "435",
                "435",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17121"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "435",
                "435",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18407956"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "435",
                "435",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "632",
                "632",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17121"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "632",
                "632",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18407956"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "632",
                "632",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "46",
                "46",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17121"
            ],
            [
                "P17121-1",
                "SAC7",
                "Modified_Residue_Annotation",
                "46",
                "46",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "17330950"
            ],
            [
                "P25374-1",
                "NFS1",
                "Active_Site_Annotation",
                "421",
                "421",
                "Cysteine persulfide intermediate",
                "ECO_0000250",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25374"
            ],
            [
                "P25374-1",
                "NFS1",
                "Active_Site_Annotation",
                "421",
                "421",
                "Cysteine persulfide intermediate",
                "ECO_0000250",
                "C",
                "",
                "protein_xref_pubmed",
                "P0A6B7"
            ],
            [
                "P25374-1",
                "NFS1",
                "Binding_Site_Annotation",
                "421",
                "421",
                "via persulfide group",
                "ECO_0000250",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25374"
            ],
            [
                "P25374-1",
                "NFS1",
                "Binding_Site_Annotation",
                "421",
                "421",
                "via persulfide group",
                "ECO_0000250",
                "C",
                "",
                "protein_xref_pubmed",
                "O29689"
            ],
            [
                "P25374-1",
                "NFS1",
                "Modified_Residue_Annotation",
                "299",
                "299",
                "N6-(pyridoxal phosphate)lysine",
                "ECO_0000250",
                "K",
                "",
                "protein_xref_uniprotkb",
                "P25374"
            ],
            [
                "P25374-1",
                "NFS1",
                "Modified_Residue_Annotation",
                "299",
                "299",
                "N6-(pyridoxal phosphate)lysine",
                "ECO_0000250",
                "K",
                "",
                "protein_xref_pubmed",
                "P0A6B9"
            ],
            [
                "P25374-1",
                "NFS1",
                "Mutagenesis_Annotation",
                "191",
                "191",
                "Disrupts iron-sulfur (Fe-S) cluster assembly and decreases cytosolic tRNA thiolation. Exhibits constitutive up-regulation of the genes of the cellular iron uptake system.",
                "ECO_0000269",
                "I",
                "S",
                "protein_xref_uniprotkb",
                "P25374"
            ],
            [
                "P25374-1",
                "NFS1",
                "Mutagenesis_Annotation",
                "191",
                "191",
                "Disrupts iron-sulfur (Fe-S) cluster assembly and decreases cytosolic tRNA thiolation. Exhibits constitutive up-regulation of the genes of the cellular iron uptake system.",
                "ECO_0000269",
                "I",
                "S",
                "protein_xref_pubmed",
                "10551871"
            ],
            [
                "P25374-1",
                "NFS1",
                "Mutagenesis_Annotation",
                "191",
                "191",
                "Disrupts iron-sulfur (Fe-S) cluster assembly and decreases cytosolic tRNA thiolation. Exhibits constitutive up-regulation of the genes of the cellular iron uptake system.",
                "ECO_0000269",
                "I",
                "S",
                "protein_xref_pubmed",
                "31040179"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17123"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "22814378"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "118",
                "118",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17123"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "118",
                "118",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "125",
                "125",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P17123"
            ],
            [
                "P17123-1",
                "SPO12",
                "Modified_Residue_Annotation",
                "125",
                "125",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P25371-1",
                "ADP1",
                "Glycosylation_Annotation",
                "221",
                "221",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Glycosylation_Annotation",
                "935",
                "935",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Glycosylation_Annotation",
                "50",
                "50",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Glycosylation_Annotation",
                "165",
                "165",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Glycosylation_Annotation",
                "114",
                "114",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "659",
                "659",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "659",
                "659",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18407956"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "659",
                "659",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "702",
                "702",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P25371"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "702",
                "702",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18407956"
            ],
            [
                "P25371-1",
                "ADP1",
                "Modified_Residue_Annotation",
                "702",
                "702",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19779198"
            ],
            [
                "P25373-1",
                "GRX1",
                "Disulfide_Bond_Annotation",
                "27",
                "27",
                "Redox-active; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25373"
            ],
            [
                "P25373-1",
                "GRX1",
                "Disulfide_Bond_Annotation",
                "27",
                "27",
                "Redox-active; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_pubmed",
                "18473363"
            ],
            [
                "P25373-1",
                "GRX1",
                "Disulfide_Bond_Annotation",
                "30",
                "30",
                "Redox-active; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25373"
            ],
            [
                "P25373-1",
                "GRX1",
                "Disulfide_Bond_Annotation",
                "30",
                "30",
                "Redox-active; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_pubmed",
                "18473363"
            ],
            [
                "P25373-1",
                "GRX1",
                "Modified_Residue_Annotation",
                "27",
                "27",
                "S-glutathionyl cysteine; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25373"
            ],
            [
                "P25373-1",
                "GRX1",
                "Modified_Residue_Annotation",
                "27",
                "27",
                "S-glutathionyl cysteine; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_pubmed",
                "18473363"
            ],
            [
                "P25373-1",
                "GRX1",
                "Modified_Residue_Annotation",
                "27",
                "27",
                "S-glutathionyl cysteine; alternate",
                "ECO_0000269",
                "C",
                "",
                "protein_xref_pubmed",
                "17327665"
            ],
            [
                "P25373-1",
                "GRX1",
                "Mutagenesis_Annotation",
                "30",
                "30",
                "Leads to increased oxidoreductase activity.",
                "ECO_0000269",
                "C",
                "S",
                "protein_xref_uniprotkb",
                "P25373"
            ],
            [
                "P25373-1",
                "GRX1",
                "Mutagenesis_Annotation",
                "30",
                "30",
                "Leads to increased oxidoreductase activity.",
                "ECO_0000269",
                "C",
                "S",
                "protein_xref_pubmed",
                "18992757"
            ],
            [
                "P25373-1",
                "GRX1",
                "Mutagenesis_Annotation",
                "89",
                "89",
                "Leads to increased oxidoreductase activity.",
                "ECO_0000269",
                "D",
                "S",
                "protein_xref_uniprotkb",
                "P25373"
            ],
            [
                "P25373-1",
                "GRX1",
                "Mutagenesis_Annotation",
                "89",
                "89",
                "Leads to increased oxidoreductase activity.",
                "ECO_0000269",
                "D",
                "S",
                "protein_xref_pubmed",
                "20417731"
            ],
            [
                "P25372-1",
                "TRX3",
                "Active_Site_Annotation",
                "58",
                "58",
                "Nucleophile",
                "",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Active_Site_Annotation",
                "55",
                "55",
                "Nucleophile",
                "",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Site_Annotation",
                "56",
                "56",
                "Contributes to redox potential value",
                "",
                "G",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Site_Annotation",
                "49",
                "49",
                "Deprotonates C-terminal active site Cys",
                "",
                "D",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Site_Annotation",
                "57",
                "57",
                "Contributes to redox potential value",
                "",
                "P",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Disulfide_Bond_Annotation",
                "58",
                "58",
                "Redox-active",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Disulfide_Bond_Annotation",
                "58",
                "58",
                "Redox-active",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_pubmed",
                "PRU00691"
            ],
            [
                "P25372-1",
                "TRX3",
                "Disulfide_Bond_Annotation",
                "55",
                "55",
                "Redox-active",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P25372"
            ],
            [
                "P25372-1",
                "TRX3",
                "Disulfide_Bond_Annotation",
                "55",
                "55",
                "Redox-active",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_pubmed",
                "PRU00691"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "172",
                "172",
                "Loss of function.",
                "ECO_0000269",
                "N",
                "K",
                "protein_xref_uniprotkb",
                "Q06563"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "172",
                "172",
                "Loss of function.",
                "ECO_0000269",
                "N",
                "K",
                "protein_xref_pubmed",
                "16582910"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "54",
                "54",
                "Almost abolishes function.",
                "ECO_0000269",
                "R",
                "Q",
                "protein_xref_uniprotkb",
                "Q06563"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "54",
                "54",
                "Almost abolishes function.",
                "ECO_0000269",
                "R",
                "Q",
                "protein_xref_pubmed",
                "16582910"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "54",
                "54",
                "Loss of function.",
                "ECO_0000269",
                "R",
                "W",
                "protein_xref_uniprotkb",
                "Q06563"
            ],
            [
                "Q06563-1",
                "SYM1",
                "Mutagenesis_Annotation",
                "54",
                "54",
                "Loss of function.",
                "ECO_0000269",
                "R",
                "W",
                "protein_xref_pubmed",
                "16582910"
            ]
        ]
    },
    "readme": "Name\n   - Yeast Protein Site Annotation\n\nVersion\n   - v-2.2.1\n\nCreated on\n  - 2022-08-31T11:08:19.037259\n\nModified on\n   - 2023-09-11T19:24:27\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], 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 Yeast Protein Site Annotation (UniProtKB) dataset contains yeast [taxid:559292] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  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 sequnces asnd 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: yeast_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_masterlist.csv\n      Name: uniprot-proteome-saccharomyces-cerevisiae.nt\n      URI: https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-saccharomyces-cerevisiae.nt\n   Output Subdomain\n      Name: yeast_protein_site_annotation_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_site_annotation_uniprotkb.csv\n      Name: yeast_protein_site_annotation_uniprotkb.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/yeast_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"3606\"\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: \"3417\"\n      Name: \"ann_type\"\n     Description: \"Annotation Type\"\n      Unique Values: \"10\"\n      Name: \"start_pos\"\n     Description: \"Start position of the gene on the chromosome\"\n      Unique Values: \"1467\"\n      Name: \"end_pos\"\n     Description: \"End position of the gene on the chromosome\"\n      Unique Values: \"1473\"\n      Name: \"annotation\"\n     Description: \"Function annotation from UniProtKB|RefSeq database\"\n      Unique Values: \"4146\"\n      Name: \"ecoid\"\n     Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n      Unique Values: \"7\"\n      Name: \"ref_aa\"\n     Description: \"Reference amino acid residue\"\n      Unique Values: \"589\"\n      Name: \"alt_aa\"\n     Description: \"Altered amino acid residue\"\n      Unique Values: \"230\"\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: \"5913\"",
    "downloadurl": "/ln2data/releases/data/v-2.2.1/reviewed/yeast_protein_site_annotation_uniprotkb.csv"
}
