{
    "bcoid": "GLY_000327",
    "title": "Mouse Protein Site Annotation",
    "description": "The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] site annotations for ...",
    "filename": "mouse_protein_site_annotation_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": "Mus musculus",
        "molecule": "Protein",
        "tags": "site annotation",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q8BH24-1...",
                "Tm9sf4..."
            ],
            [
                "Q8BH24-1...",
                "Tm9sf4..."
            ]
        ],
        "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"
                }
            ],
            [
                "Q8BH24-1",
                "Tm9sf4",
                "Modified_Residue_Annotation",
                "313",
                "313",
                "Phosphotyrosine",
                "ECO_0000250",
                "Y",
                "",
                "protein_xref_uniprotkb",
                "Q8BH24"
            ],
            [
                "Q8BH24-1",
                "Tm9sf4",
                "Modified_Residue_Annotation",
                "313",
                "313",
                "Phosphotyrosine",
                "ECO_0000250",
                "Y",
                "",
                "protein_xref_pubmed",
                "Q92544"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "203",
                "203",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "36",
                "36",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "216",
                "216",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "265",
                "265",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "426",
                "426",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "498",
                "498",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "466",
                "466",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "179",
                "179",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "357",
                "357",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "243",
                "243",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "479",
                "479",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q8BH27-1",
                "Megf9",
                "Glycosylation_Annotation",
                "303",
                "303",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q8BH27"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Active_Site_Annotation",
                "111",
                "111",
                "Proton acceptor",
                "ECO_0000255",
                "E",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Active_Site_Annotation",
                "111",
                "111",
                "Proton acceptor",
                "ECO_0000255",
                "E",
                "",
                "protein_xref_pubmed",
                "PRU10096"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Binding_Site_Annotation",
                "429",
                "429",
                "ATP",
                "ECO_0000250",
                "R",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Binding_Site_Annotation",
                "429",
                "429",
                "ATP",
                "ECO_0000250",
                "R",
                "",
                "protein_xref_pubmed",
                "P35559"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "189",
                "189",
                "Zinc",
                "ECO_0000255",
                "E",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "189",
                "189",
                "Zinc",
                "ECO_0000255",
                "E",
                "",
                "protein_xref_pubmed",
                "PRU10096"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "112",
                "112",
                "Zinc",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "112",
                "112",
                "Zinc",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_pubmed",
                "PRU10096"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "108",
                "108",
                "Zinc",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Metal_Binding_Annotation",
                "108",
                "108",
                "Zinc",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_pubmed",
                "PRU10096"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Modified_Residue_Annotation",
                "697",
                "697",
                "N6-succinyllysine",
                "ECO_0007744",
                "K",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Modified_Residue_Annotation",
                "697",
                "697",
                "N6-succinyllysine",
                "ECO_0007744",
                "K",
                "",
                "protein_xref_pubmed",
                "23806337"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Modified_Residue_Annotation",
                "192",
                "192",
                "N6-succinyllysine",
                "ECO_0007744",
                "K",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Modified_Residue_Annotation",
                "192",
                "192",
                "N6-succinyllysine",
                "ECO_0007744",
                "K",
                "",
                "protein_xref_pubmed",
                "23806337"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "NP_Binding_Annotation",
                "895",
                "901",
                "ATP",
                "ECO_0000250",
                "DKPKKLS",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "NP_Binding_Annotation",
                "895",
                "901",
                "ATP",
                "ECO_0000250",
                "DKPKKLS",
                "",
                "protein_xref_pubmed",
                "P35559"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Mutagenesis_Annotation",
                "853",
                "858",
                "Marked decrease in secretion.",
                "ECO_0000269",
                "EKPPHY",
                "",
                "protein_xref_uniprotkb",
                "Q9JHR7"
            ],
            [
                "Q9JHR7-1",
                "Ide",
                "Mutagenesis_Annotation",
                "853",
                "858",
                "Marked decrease in secretion.",
                "ECO_0000269",
                "EKPPHY",
                "",
                "protein_xref_pubmed",
                "21576244"
            ],
            [
                "B2RXV4-1",
                "Flvcr1",
                "Glycosylation_Annotation",
                "270",
                "270",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "B2RXV4"
            ],
            [
                "B2RXV4-1",
                "Flvcr1",
                "Modified_Residue_Annotation",
                "542",
                "542",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "B2RXV4"
            ],
            [
                "B2RXV4-1",
                "Flvcr1",
                "Modified_Residue_Annotation",
                "542",
                "542",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q9Y5Y0"
            ],
            [
                "O35153-1",
                "Bet1l",
                "Modified_Residue_Annotation",
                "9",
                "9",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "O35153"
            ],
            [
                "O35153-1",
                "Bet1l",
                "Modified_Residue_Annotation",
                "9",
                "9",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q9NYM9"
            ],
            [
                "O35153-1",
                "Bet1l",
                "Modified_Residue_Annotation",
                "37",
                "37",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "O35153"
            ],
            [
                "O35153-1",
                "Bet1l",
                "Modified_Residue_Annotation",
                "37",
                "37",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q9NYM9"
            ],
            [
                "Q9QYH9-1",
                "Tnfsf14",
                "Site_Annotation",
                "81",
                "82",
                "Cleavage",
                "",
                "LI",
                "",
                "protein_xref_uniprotkb",
                "Q9QYH9"
            ],
            [
                "Q9QYH9-1",
                "Tnfsf14",
                "Glycosylation_Annotation",
                "100",
                "100",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q9QYH9"
            ],
            [
                "Q9QYH9-1",
                "Tnfsf14",
                "Glycosylation_Annotation",
                "191",
                "191",
                "N-linked (GlcNAc...) asparagine",
                "",
                "N",
                "",
                "protein_xref_uniprotkb",
                "Q9QYH9"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "743",
                "743",
                "Proton acceptor",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "743",
                "743",
                "Proton acceptor",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_pubmed",
                "PRU10092"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "743",
                "743",
                "Proton acceptor",
                "ECO_0000255",
                "H",
                "",
                "protein_xref_pubmed",
                "PRU10093"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "418",
                "418",
                "Nucleophile",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "418",
                "418",
                "Nucleophile",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_pubmed",
                "PRU10092"
            ],
            [
                "P52479-1",
                "Usp10",
                "Active_Site_Annotation",
                "418",
                "418",
                "Nucleophile",
                "ECO_0000255",
                "C",
                "",
                "protein_xref_pubmed",
                "PRU10093"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "24",
                "24",
                "Phosphothreonine",
                "ECO_0000250",
                "T",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "24",
                "24",
                "Phosphothreonine",
                "ECO_0000250",
                "T",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "364",
                "364",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "364",
                "364",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylalanine",
                "ECO_0000250",
                "A",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "2",
                "2",
                "N-acetylalanine",
                "ECO_0000250",
                "A",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "541",
                "541",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "541",
                "541",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "314",
                "314",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "314",
                "314",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "330",
                "330",
                "Phosphoserine; by ATM",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "330",
                "330",
                "Phosphoserine; by ATM",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q14694"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "359",
                "359",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "359",
                "359",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "15345747"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "359",
                "359",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "566",
                "566",
                "Phosphothreonine",
                "ECO_0007744",
                "T",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "566",
                "566",
                "Phosphothreonine",
                "ECO_0007744",
                "T",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "208",
                "208",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "208",
                "208",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "570",
                "570",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "570",
                "570",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "17242355"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "570",
                "570",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "570",
                "570",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "18630941"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "570",
                "570",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "19144319"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "223",
                "223",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "P52479"
            ],
            [
                "P52479-1",
                "Usp10",
                "Modified_Residue_Annotation",
                "223",
                "223",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "177",
                "177",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_uniprotkb",
                "Q5EBH1"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "177",
                "177",
                "Phosphoserine",
                "ECO_0007744",
                "S",
                "",
                "protein_xref_pubmed",
                "21183079"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "274",
                "274",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_uniprotkb",
                "Q5EBH1"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "274",
                "274",
                "Phosphoserine",
                "ECO_0000250",
                "S",
                "",
                "protein_xref_pubmed",
                "Q8WWW0"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "347",
                "347",
                "Phosphothreonine",
                "ECO_0000250",
                "T",
                "",
                "protein_xref_uniprotkb",
                "Q5EBH1"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Modified_Residue_Annotation",
                "347",
                "347",
                "Phosphothreonine",
                "ECO_0000250",
                "T",
                "",
                "protein_xref_pubmed",
                "Q8WWW0"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Mutagenesis_Annotation",
                "220",
                "220",
                "Reduced interaction with HRAS.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_uniprotkb",
                "Q5EBH1"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Mutagenesis_Annotation",
                "220",
                "220",
                "Reduced interaction with HRAS.",
                "ECO_0000269",
                "C",
                "A",
                "protein_xref_pubmed",
                "18596699"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Mutagenesis_Annotation",
                "302",
                "302",
                "Reduced specificity for HRAS and diminished discrimination between HRAS and RAP1A.",
                "ECO_0000269",
                "K",
                "D",
                "protein_xref_uniprotkb",
                "Q5EBH1"
            ],
            [
                "Q5EBH1-1",
                "Rassf5",
                "Mutagenesis_Annotation",
                "302",
                "302",
                "Reduced specificity for HRAS and diminished discrimination between HRAS and RAP1A.",
                "ECO_0000269",
                "K",
                "D",
                "protein_xref_pubmed",
                "18596699"
            ]
        ]
    },
    "readme": "Name\n   - Mouse Protein Site Annotation\n\nVersion\n   - 1.11.2\n\nCreated on\n  - 2019-12-04T12:16:57.929402\n\nModified on\n   - 2022-01-12T16:35:17.794615\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.gwu.edu]\n\nAuthors\n   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] 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 it as a dataset in a csv format\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/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: mouse_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/mouse_protein_masterlist.csv\n      Name: uniprot-proteome-mus-musculus.nt\n      URI: https:/data.glygen.org/ln2downloads/ebi/2021_04/uniprot-proteome-mus-musculus.nt\n   Output Subdomain\n      Name: mouse_protein_site_annotation_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/mouse_protein_site_annotation_uniprotkb.csv\n      Name: mouse_protein_site_annotation_uniprotkb.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-1.12.3/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"13459\"\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: \"13366\"\n      Name: \"ann_type\"\n     Description: \"Annotation Type\"\n      Unique Values: \"13\"\n      Name: \"start_pos\"\n     Description: \"Start position of the gene on the chromosome\"\n      Unique Values: \"3323\"\n      Name: \"end_pos\"\n     Description: \"End position of the gene on the chromosome\"\n      Unique Values: \"3322\"\n      Name: \"annotation\"\n     Description: \"Function annotation from UniProtKB|RefSeq database\"\n      Unique Values: \"8345\"\n      Name: \"ecoid\"\n     Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n      Unique Values: \"10\"\n      Name: \"ref_aa\"\n     Description: \"Reference amino acid residue\"\n      Unique Values: \"4046\"\n      Name: \"alt_aa\"\n     Description: \"Altered amino acid residue\"\n      Unique Values: \"368\"\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: \"28145\"",
    "downloadurl": "/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_site_annotation_uniprotkb.csv"
}
