{
    "object_id": "https://biocomputeobject.org/GLY_000815/v-2.2.1",
    "etag": "2c1a51e331070e1d02e15aaeacf89cf4",
    "spec_version": "1.3.0",
    "provenance_domain": {
        "name": "EuropePMC Linkouts",
        "version": "v-2.2.1",
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "created": "",
        "modified": "2023-09-28T20:00:04",
        "contributors": [
            {
                "name": "Jeet Vora",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jeetvora@gwu.edu"
            },
            {
                "name": "Karina Martinez",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Robel Kahsay",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "rykahsay@gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            }
        ]
    },
    "usability_domain": [
        "The EuropePMC Linkouts contains XML files that contains NCBI PubMed IDs associated with all of GlyGen's proteins and glycans with their corresponding GlyGen publication detail page URLs. Glycan Image URL is also present if available. The dataset is formatted as per EuropePMC linkouts guidelines where 2167 is the GlyGen's provider ID. The dataset is for all GlyGen's organisms and the output file is split into multiple XML files of <10MB and packaged as a zip file. For more info - https://gwu0.sharepoint.com/:w:/r/sites/GlyGenTeam-GRP/Shared%20Documents/Backend/Documents/EuropePMC%20linkouts.docx?d=w8fc9c465fd094eee89b370747e7eac80&csf=1&web=1&e=ZiatbN and https://europepmc.org/LabsLink"
    ],
    "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_name": "species",
                        "category_value": "Homo sapiens"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Mus musculus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus norvegicus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Drosophila melanogaster"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Hepatitis c virus (isolate h)"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Hepatitis c virus (isolate japanese)"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome coronavirus 2"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome-related coronavirus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Saccharomyces cerevisiae S288C"
                    },
                    {
                        "category_value": "",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "EuropePMC Linkouts",
                        "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": [
            "EuropePMC Linkouts",
            "PMID"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "version": "",
                "step_number": 1,
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script loads the PubMed IDs from the input files associated with proteins and glycans in GlyGen and generates publication detail page URLs for corresponding proteins and glycans; glycan URLs for glycans when available. The script also enters the other fields as defined by the EuropePMC Linkouts to generate a csv dataset that is split into multiple XML files of <10MB and packaged as a zip file."
            }
        ]
    },
    "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-species-agnostic-dataset.py",
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "io_domain": {
        "input_subdomain": [],
        "output_subdomain": [
            {
                "mediatype": "zip",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_one.zip",
                    "filename": "all_europepmc_linkouts_one.zip"
                }
            },
            {
                "mediatype": "zip",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_two.zip",
                    "filename": "all_europepmc_linkouts_two.zip"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_one.stat.csv",
                    "filename": "all_europepmc_linkouts_one.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/all_europepmc_linkouts_two.stat.csv",
                    "filename": "all_europepmc_linkouts_two.stat.csv"
                }
            }
        ]
    }
}