{
    "provenance_domain": {
        "name": "Fruitfly Protein Site Annotation",
        "version": "v-2.2.1",
        "created": "2022-08-31T11:08:19.037259",
        "modified": "2022-09-26T09:08:12.471396",
        "contributors": [
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jeet Vora",
                "email": "jeetvora@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Robel Kahsay",
                "email": "rykahsay@gwu.edu"
            },
            {
                "affiliation": "EMBL-EBI-UniProt",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Maria Martin",
                "email": "martin@ebi.ac.uk"
            },
            {
                "affiliation": "EMBL-EBI-UniProt",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Preethi Vasudev",
                "email": "pvasudev@ebi.ac.uk"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            }
        ],
        "license": "https://creativecommons.org/licenses/by/4.0/"
    },
    "usability_domain": [
        "The Fruitfly Protein Site Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range.  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": "Drosophila melanogaster",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "site annotation",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "description_domain": {
        "keywords": [
            "site annotation",
            "amino acid range",
            "UniProtKB"
        ],
        "pipeline_steps": [
            {
                "step_number": 1,
                "name": "make-protein-dataset.py",
                "description": "The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format",
                "version": "",
                "prerequisite": [],
                "input_list": [],
                "output_list": []
            }
        ]
    },
    "execution_domain": {
        "script": [
            {
                "uri": {
                    "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ],
        "script_driver": "manual",
        "software_prerequisites": [
            {
                "version": "2.7.5",
                "name": "Python",
                "uri": {
                    "uri": "https://www.python.org/download/releases/2.7.5/"
                }
            }
        ],
        "external_data_endpoints": [],
        "environment_variables": {}
    },
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "fruitfly_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-drosophila-melanogaster.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2023_10_30/uniprot-proteome-drosophila-melanogaster.nt"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv",
                    "filename": "fruitfly_protein_site_annotation_uniprotkb.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/fruitfly_protein_site_annotation_uniprotkb.stat.csv",
                    "filename": "fruitfly_protein_site_annotation_uniprotkb.stat.csv"
                }
            }
        ]
    },
    "object_id": "https://biocomputeobject.org/GLY_000654/v-2.2.1",
    "spec_version": "1.3.0",
    "etag": "c2a4804803668429e3de448d79c07f8f",
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    }
}
