{
    "object_id": "https://biocomputeobject.org/GLY_001685/v-2.12.1",
    "etag": "edaaa9a6ff93ecc1a48b61bc08b8d5d7",
    "spec_version": "1.3.0",
    "provenance_domain": {
        "name": "Zebrafish Binding Sites Citations (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 Zebrafish binding sites citations (UniProtKB) dataset contains Danio rerio [taxid:7955] publication information for UniProtKB canonical protein binding sites provided in GlyGen. The dataset includes PMID, journal name, date and author and title. If you use this dataset please give proper attribution to UniProtKB, ChEBI 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": "Danio rerio",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Binding sites citations",
                        "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": "citations"
                    }
                ]
            }
        }
    ],
    "description_domain": {
        "keywords": [
            "binding sites",
            "ligands",
            "metal binding sites",
            "calcium binding sites",
            "citations"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "input_list": [],
                "description": "The script extracts the PMID from the Binding_Site_Annotation triple then accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniProtKB.",
                "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/zebrafish_protein_citations_binding_sites_uniprotkb.csv",
                    "filename": "zebrafish_protein_citations_binding_sites_uniprotkb.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/zebrafish_protein_citations_binding_sites_uniprotkb.stat.csv",
                    "filename": "zebrafish_protein_citations_binding_sites_uniprotkb.stat.csv"
                }
            }
        ],
        "input_subdomain": [
            {
                "uri": {
                    "filename": "zebrafish_protein_binding_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/zebrafish_protein_binding_sites_uniprotkb.csv"
                }
            }
        ]
    },
    "error_domain": {}
}