{
    "bcoid": "GLY_000440",
    "title": "SARS-CoV1 Protein Sequence Info (UniProtKB)",
    "description": "The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains sarscov1 [taxid:694009] ...",
    "filename": "sarscov1_protein_sequenceinfo.csv",
    "filetype": "csv",
    "categories": {
        "species": "SARS coronavirus (SARS-CoV-1)",
        "molecule": "Protein",
        "tags": "All Protein Sequence Info",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "P59596-1...",
                "P59596-1..."
            ],
            [
                "P0C6U8-1...",
                "P0C6U8-1..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "uniprotkb_is..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_isoform_ac"
                },
                {
                    "type": "string",
                    "label": "protein_existence"
                },
                {
                    "type": "string",
                    "label": "sequence_version"
                },
                {
                    "type": "string",
                    "label": "sequence_header"
                }
            ],
            [
                "P59596-1",
                "P59596-1",
                "1",
                "1",
                "sp|P59596-1|VME1_CVHSA Isoform 1 of Membrane protein  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN=M PE=1 SV=1 CANONICAL=P59596-1"
            ],
            [
                "P0C6U8-1",
                "P0C6U8-1",
                "1",
                "1",
                "sp|P0C6U8-1|R1A_CVHSA Isoform 1 of Replicase polyprotein 1a  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=1 SV=1 CANONICAL=P0C6U8-1"
            ],
            [
                "P59594-1",
                "P59594-1",
                "1",
                "1",
                "sp|P59594-1|SPIKE_CVHSA Isoform 1 of Spike glycoprotein  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN=S PE=1 SV=1 CANONICAL=P59594-1"
            ],
            [
                "P59595-1",
                "P59595-1",
                "1",
                "1",
                "sp|P59595-1|NCAP_CVHSA Isoform 1 of Nucleoprotein  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN=N PE=1 SV=1 CANONICAL=P59595-1"
            ],
            [
                "Q7TLC7-1",
                "Q7TLC7-1",
                "4",
                "1",
                "sp|Q7TLC7-1|Y14_CVHSA Isoform 1 of Uncharacterized protein 14  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=4 SV=1 CANONICAL=Q7TLC7-1"
            ],
            [
                "Q80H93-1",
                "Q80H93-1",
                "4",
                "1",
                "sp|Q80H93-1|NS8B_CVHSA Isoform 1 of Non-structural protein 8b  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=4 SV=1 CANONICAL=Q80H93-1"
            ],
            [
                "P59635-1",
                "P59635-1",
                "1",
                "1",
                "sp|P59635-1|NS7A_CVHSA Isoform 1 of Protein 7a  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=1 SV=1 CANONICAL=P59635-1"
            ],
            [
                "Q7TFA1-1",
                "Q7TFA1-1",
                "4",
                "1",
                "sp|Q7TFA1-1|NS7B_CVHSA Isoform 1 of Protein non-structural 7b  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=4 SV=1 CANONICAL=Q7TFA1-1"
            ],
            [
                "Q7TFA0-1",
                "Q7TFA0-1",
                "3",
                "1",
                "sp|Q7TFA0-1|NS8A_CVHSA Isoform 1 of Protein non-structural 8a  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=3 SV=1 CANONICAL=Q7TFA0-1"
            ],
            [
                "P59633-1",
                "P59633-1",
                "1",
                "1",
                "sp|P59633-1|NS3B_CVHSA Isoform 1 of Non-structural protein 3b  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=1 SV=1 CANONICAL=P59633-1"
            ],
            [
                "P59632-1",
                "P59632-1",
                "1",
                "1",
                "sp|P59632-1|AP3A_CVHSA Isoform 1 of Protein 3a  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=1 SV=1 CANONICAL=P59632-1"
            ],
            [
                "P59637-1",
                "P59637-1",
                "1",
                "1",
                "sp|P59637-1|VEMP_CVHSA Isoform 1 of Envelope small membrane protein  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN=E PE=1 SV=1 CANONICAL=P59637-1"
            ],
            [
                "P59636-1",
                "P59636-1",
                "1",
                "1",
                "sp|P59636-1|ORF9B_CVHSA Isoform 1 of Protein 9b  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=1 SV=1 CANONICAL=P59636-1"
            ],
            [
                "P0C6X7-1",
                "P0C6X7-1",
                "1",
                "1",
                "sp|P0C6X7-1|R1AB_CVHSA Isoform 1 of Replicase polyprotein 1ab  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN=rep PE=1 SV=1 CANONICAL=P0C6X7-1"
            ],
            [
                "P59634-1",
                "P59634-1",
                "3",
                "1",
                "sp|P59634-1|NS6_CVHSA Isoform 1 of Non-structural protein 6  OS=Human SARS coronavirus (SARS-CoV) OX=694009 GN= PE=3 SV=1 CANONICAL=P59634-1"
            ]
        ]
    },
    "readme": "Name\n   - SARS-CoV1 Protein Sequence Info (UniProtKB)\n\nVersion\n   - 1.5.27\n\nCreated on\n  - 2020-04-03T11:46:41.584409\n\nModified on\n   - 2020-04-09T18:48:20.300109\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n   Keywords\n   - protein sequence info\n   - fasta header\n   - UniProtKB\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta 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: uniprot-proteome-human-sars-coronavirus.nt\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.5.27/source/uniprot-proteome-human-sars-coronavirus.nt\n   Output Subdomain\n      Name: sarscov1_protein_sequenceinfo.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/sarscov1_protein_sequenceinfo.csv\n      Name: sarscov1_protein_sequenceinfo.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.5.27/reviewed/sarscov1_protein_sarscov1_sequenceinfo.stat.csv\n\nFields\n      Name: \"uniprotkb_isoform_ac\"\n     Description: \"UniProtKB isoform that includes the canonical accession and other isoforms generated by alternative splicing\n      Unique Values: \"15\"\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: \"15\"\n      Name: \"sequence_header\"\n     Description: \"The FASTA header for the UniProtKB protein FASTA sequences\"\n      Unique Values: \"15\"\n      Name: \"sequence_version\"\n     Description: \"The version of the protein fasta sequence for a given accession in UniProtKB\"\n      Unique Values: \"1\"\n      Name: \"protein_existence\"\n     Description: \"In UniProtKB there are 5 types of evidence for the existence of a protein: 1. Experimental evidence at protein level; 2. Experimental evidence at transcript level; 3. Protein inferred from homology; 4. Protein predicted; 5. Protein uncertain\"\n      Unique Values: \"3\"",
    "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/sarscov1_protein_sequenceinfo.csv"
}