{
    "bcoid": "GLY_000043",
    "title": "Mouse Glycosylation Sites (RCSB PDB)",
    "description": "The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped ...",
    "filename": "mouse_proteoform_glycosylation_sites_pdb.csv",
    "filetype": "csv",
    "categories": {
        "species": "Mus musculus",
        "molecule": "Proteoform",
        "tags": "Glycosylation Sites",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q01705-1...",
                "O-linked..."
            ],
            [
                "Q01705-1...",
                "O-linked..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "glycosylatio..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "glycosylation_type"
                },
                {
                    "type": "string",
                    "label": "saccharide"
                },
                {
                    "type": "string",
                    "label": "amino_acid"
                },
                {
                    "type": "string",
                    "label": "glycosylation_site_uniprotkb"
                },
                {
                    "type": "string",
                    "label": "evidence"
                },
                {
                    "type": "string",
                    "label": "pdb_id"
                },
                {
                    "type": "string",
                    "label": "amino_acid_chain"
                },
                {
                    "type": "string",
                    "label": "glycosylation_site_pdb"
                }
            ],
            [
                "Q01705-1",
                "O-linked",
                "FUC",
                "Thr",
                "466",
                "",
                "2RQZ",
                "A",
                "15"
            ],
            [
                "Q01705-1",
                "O-linked",
                "FUC",
                "Thr",
                "466",
                "",
                "2RR2",
                "A",
                "15"
            ],
            [
                "Q62011-1",
                "O-linked",
                "A2G",
                "Thr",
                "77",
                "",
                "3IET",
                "X",
                "2"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "580",
                "",
                "3Q2V",
                "B",
                "424"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "360",
                "",
                "3Q2V",
                "B",
                "204"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "578",
                "",
                "3Q2V",
                "A",
                "422"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "580",
                "",
                "3Q2V",
                "A",
                "424"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "582",
                "",
                "3Q2V",
                "B",
                "426"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "360",
                "",
                "3Q2V",
                "A",
                "204"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "472",
                "",
                "3Q2V",
                "B",
                "316"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "474",
                "",
                "3Q2V",
                "B",
                "318"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "578",
                "",
                "3Q2V",
                "B",
                "422"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "474",
                "",
                "3Q2V",
                "A",
                "318"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "511",
                "",
                "3Q2V",
                "A",
                "355"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "582",
                "",
                "3Q2V",
                "A",
                "426"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "472",
                "",
                "3Q2V",
                "A",
                "316"
            ],
            [
                "P09803-1",
                "O-linked",
                "MAN",
                "Thr",
                "511",
                "",
                "3Q2V",
                "B",
                "355"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "483",
                "",
                "3Q2W",
                "A",
                "324"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "588",
                "",
                "3Q2W",
                "A",
                "429"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "481",
                "",
                "3Q2W",
                "A",
                "322"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "590",
                "",
                "3Q2W",
                "A",
                "431"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "367",
                "",
                "3Q2W",
                "A",
                "208"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "290",
                "",
                "3Q2W",
                "A",
                "131"
            ],
            [
                "P15116-1",
                "O-linked",
                "MAN",
                "Thr",
                "365",
                "",
                "3Q2W",
                "A",
                "206"
            ],
            [
                "Q91Y09-1",
                "O-linked",
                "MAN",
                "Thr",
                "239",
                "",
                "4ZPM",
                "A",
                "198"
            ],
            [
                "Q91Y09-1",
                "O-linked",
                "MAN",
                "Thr",
                "239",
                "",
                "4ZPM",
                "B",
                "198"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPN",
                "A",
                "201"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPN",
                "B",
                "201"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPO",
                "A",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPP",
                "A",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPP",
                "B",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPQ",
                "A",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPQ",
                "B",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPQ",
                "C",
                "196"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "4ZPS",
                "A",
                "196"
            ],
            [
                "Q91Y13-1",
                "O-linked",
                "MAN",
                "Thr",
                "223",
                "",
                "5DZV",
                "A",
                "194"
            ],
            [
                "Q91Y13-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZV",
                "A",
                "196"
            ],
            [
                "Q91Y13-1",
                "O-linked",
                "MAN",
                "Thr",
                "223",
                "",
                "5DZV",
                "B",
                "194"
            ],
            [
                "Q91Y13-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZV",
                "B",
                "196"
            ],
            [
                "Q91Y13-1",
                "O-linked",
                "MAN",
                "Thr",
                "438",
                "",
                "5DZV",
                "B",
                "409"
            ],
            [
                "O88689-1",
                "O-linked",
                "MAN",
                "Thr",
                "438",
                "",
                "5DZW",
                "A",
                "409"
            ],
            [
                "Q91XZ4-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZX",
                "B",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "C",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "C",
                "199"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "D",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "D",
                "199"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "E",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "E",
                "199"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "F",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "F",
                "199"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "A",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "A",
                "199"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5DZY",
                "B",
                "197"
            ],
            [
                "Q91XZ2-1",
                "O-linked",
                "MAN",
                "Thr",
                "227",
                "",
                "5DZY",
                "B",
                "199"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZL",
                "C",
                "197"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZL",
                "D",
                "197"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZL",
                "A",
                "197"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZL",
                "B",
                "197"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZM",
                "A",
                "196"
            ],
            [
                "Q91XX9-1",
                "O-linked",
                "MAN",
                "Thr",
                "226",
                "",
                "5SZN",
                "A",
                "197"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZO",
                "A",
                "195"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZO",
                "B",
                "195"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZP",
                "A",
                "195"
            ],
            [
                "Q91XW9-1",
                "O-linked",
                "MAN",
                "Thr",
                "225",
                "",
                "5SZP",
                "B",
                "195"
            ],
            [
                "Q99PJ1-1",
                "O-linked",
                "MAN",
                "Thr",
                "170",
                "",
                "6CV7",
                "A",
                "144"
            ],
            [
                "Q99PJ1-1",
                "O-linked",
                "MAN",
                "Thr",
                "251",
                "",
                "6CV7",
                "A",
                "225"
            ],
            [
                "Q99PJ1-1",
                "O-linked",
                "MAN",
                "Thr",
                "253",
                "",
                "6CV7",
                "A",
                "227"
            ],
            [
                "Q99PJ1-1",
                "O-linked",
                "MAN",
                "Thr",
                "255",
                "",
                "6CV7",
                "A",
                "229"
            ],
            [
                "Q99PJ1-1",
                "O-linked",
                "MAN",
                "Thr",
                "257",
                "",
                "6CV7",
                "A",
                "231"
            ],
            [
                "O35744-1",
                "O-linked",
                "GCS",
                "Tyr",
                "233",
                "",
                "1E9L",
                "A",
                "212"
            ],
            [
                "P01901-1",
                "N-linked",
                "NAG",
                "Arg",
                "178",
                "",
                "1BQH",
                "D",
                "157"
            ],
            [
                "Q8BGN3-1",
                "N-linked",
                "FUL",
                "Arg",
                "351",
                "",
                "5EGE",
                "C",
                "351"
            ],
            [
                "P36368-1",
                "N-linked",
                "NAG",
                "Asn",
                "119",
                "",
                "1AO5",
                "A",
                "95"
            ],
            [
                "P36368-1",
                "N-linked",
                "NAG",
                "Asn",
                "119",
                "",
                "1AO5",
                "B",
                "95"
            ],
            [
                "P01731-1",
                "N-linked",
                "NAG",
                "Asn",
                "69",
                "",
                "1BQH",
                "H",
                "42"
            ],
            [
                "P01731-1",
                "N-linked",
                "NAG",
                "Asn",
                "69",
                "",
                "1BQH",
                "I",
                "42"
            ],
            [
                "P01731-1",
                "N-linked",
                "NAG",
                "Asn",
                "69",
                "",
                "1BQH",
                "K",
                "42"
            ],
            [
                "P01731-1",
                "N-linked",
                "NDG",
                "Asn",
                "69",
                "",
                "1BQH",
                "G",
                "42"
            ],
            [
                "P40223-1",
                "N-linked",
                "NAG",
                "Asn",
                "129",
                "",
                "1CD9",
                "B",
                "10"
            ],
            [
                "P40223-1",
                "N-linked",
                "NAG",
                "Asn",
                "129",
                "",
                "1CD9",
                "D",
                "10"
            ],
            [
                "P01901-1",
                "N-linked",
                "NAG",
                "Asn",
                "107",
                "",
                "1FZJ",
                "A",
                "86"
            ],
            [
                "P01901-1",
                "N-linked",
                "NAG",
                "Asn",
                "197",
                "",
                "1FZJ",
                "A",
                "176"
            ],
            [
                "P01901-1",
                "N-linked",
                "NAG",
                "Asn",
                "197",
                "",
                "1FZK",
                "A",
                "176"
            ],
            [
                "P01901-1",
                "N-linked",
                "NAG",
                "Asn",
                "107",
                "",
                "1FZK",
                "A",
                "86"
            ]
        ]
    },
    "readme": "Name\n   - Mouse Glycosylation Sites (RCSB PDB)\n\nVersion\n   - 1.5.18\n\nCreated on\n  - 2019-01-23T17:21:05.910839\n\nModified on\n   - 2020-04-10T12:35:07.324192\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]\n\nAuthors\n   - Jasmine Young [jasmine@rcsb.rutgers.edu], Chenghua Shao [chenghua@rcsb.rutgers.edu]\n\nChecksum\n   - \n\nUsability Domain\n   - The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)].\n\nDescription Domain\n   Keywords\n   - PDB\n   - glycosylation sites\n   - amino acid\n   - amino acid chain\n\n   Pipeline Steps\n   - Step-1: The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB.\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py\n\n\n   Software Prerequisites\n      Name: Python\n      Version: 2.7.5\n      URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n   Input Subdomain\n      Name: N-linked-ARG-details\n      URI: https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details\n      Name: O-linked-ASP-details\n      URI: https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details\n      Name: O-linked-GLU-details\n      URI: https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details\n      Name: O-linked-SER-details\n      URI: https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details\n      Name: O-linked-THR-details\n      URI: https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details\n      Name: O-linked-TYR-details\n      URI: https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details\n      Name: mouse_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv\n      Name: mouse_protein_canonicalsequences.fasta\n      URI: https://data.glygen.org/ln2wwwdata/source/mouse_protein_canonicalsequences.fasta\n      Name: pdb_chain_uniprot_2018_11_8_11_44_50.csv\n      URI: https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv\n   Output Subdomain\n      Name: mouse_proteoform_glycosylation_sites_pdb.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv\n      Name: mouse_proteoform_glycosylation_sites_pdb.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n      Unique Values: \"63\"\n      Name: \"glycosylation_site_uniprotkb\"\n     Description: \"Site on the protein sequence of the UniProtKB entry where glycosylation is observed\"\n      Unique Values: \"130\"\n      Name: \"glycosylation_type\"\n     Description: \"Type of glycosylation (N/O/C/S linked glycosylation)\"\n      Unique Values: \"2\"\n      Name: \"amino_acid\"\n     Description: \"Three letter abbreviation code of the amino acid\"\n      Unique Values: \"5\"\n      Name: \"glycosylation_site_pdb\"\n     Description: \"Site on the protein sequence of the PDB entry where glycosylation is observed\"\n      Unique Values: \"127\"\n      Name: \"evidence\"\n     Description: \"NCBI PubMed Id (PMID) as evidence for the entry/annotation\"\n      Unique Values: \"1\"\n      Name: \"pdb_id\"\n     Description: \"4-character id assigned to each protein structure in Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB)\"\n      Unique Values: \"233\"\n      Name: \"saccharide\"\n     Description: \"Sugar\"\n      Unique Values: \"7\"\n      Name: \"amino_acid_chain\"\n     Description: \"Amino acid chain in pdb\"\n      Unique Values: \"15\"",
    "downloadurl": "/ln2data/releases/data/v-1.5.18/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"
}
