{
    "object_id": "https://biocomputeobject.org/GLY_001702/v-2.12.1",
    "etag": "df779127052083803308975e3704f484",
    "spec_version": "1.3.0",
    "provenance_domain": {
        "name": "HCV1a Domains and Regions (UniProtKB)",
        "version": "v-2.12.1",
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "created": "",
        "modified": "",
        "contributors": [
            {
                "name": "Jeet Vora",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jeetvora@gwu.edu"
            },
            {
                "name": "Robel Kahsay",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "rykahsay@gwu.edu"
            },
            {
                "name": "Urnisha Bhuiyan",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "sbhuiyan28@email.gwu.edu"
            },
            {
                "name": "Kate Warner",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "k.warner1@gwu.edu"
            }
        ]
    },
    "usability_domain": [
        "The HCV1a domain and regions (UniProtKB) dataset contains Hepatitis C virus (isolate H77) [taxid:63746] domains, motifs and DNA binding data for UniProtKB canonical proteins, and any overlapping glycosylation sites provided in GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."
    ],
    "extension_domain": [
        {
            "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json",
            "dataset_extension": {
                "additional_license": {
                    "data_license": "https://creativecommons.org/licenses/by/4.0/",
                    "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
                },
                "dataset_categories": [
                    {
                        "category_value": "Hepatitis C virus (isolate H77)",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Domains and Regions",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    },
                    {
                        "category_name": "file_category",
                        "category_value": "annotation"
                    }
                ]
            }
        }
    ],
    "description_domain": {
        "keywords": [
            "domains",
            "motifs",
            "regions",
            "DNA binding"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "input_list": [],
                "description": "The script extracts the domain, motif and nucleotide binding data from their annotation triples in the UniProtKB triplestore, then maps the data to the UniProtKB canonical sequences. The extracted region of the protein is then parsed against glycosylation site data in GlyGen to see if the region contains a glycosylation site, if so the glycosite/s are added to the dataset. The extracted data to generate the dataset in a csv format.",
                "prerequisite": [],
                "output_list": []
            }
        ]
    },
    "execution_domain": {
        "external_data_endpoints": [],
        "environment_variables": {},
        "script_driver": "manual",
        "software_prerequisites": [
            {
                "version": "2.7.5",
                "name": "Python",
                "uri": {
                    "uri": "https://www.python.org/download/releases/2.7.5/"
                }
            }
        ],
        "script": [
            {
                "uri": {
                    "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "io_domain": {
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/hcv1a_protein_domains_uniprotkb.csv",
                    "filename": "hcv1a_protein_domains_uniprotkb.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/hcv1a_protein_domains_uniprotkb.stat.csv",
                    "filename": "hcv1a_protein_domains_uniprotkb.stat.csv"
                }
            }
        ],
        "input_subdomain": [
            {
                "uri": {
                    "filename": "aadict.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/misc/aadict.csv"
                }
            }
        ]
    },
    "error_domain": {}
}