{
    "object_id": "https://biocomputeobject.org/GLY_000256/v-2.0.3",
    "spec_version": "1.3.0",
    "extension_domain": [
        {
            "extension_schema": "http://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": "Homo sapiens",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Protein Citations",
                        "category_name": "tags"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Human Protein Citations (RefSeq)",
        "contributors": [
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jeet Vora",
                "email": "jeetvora@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Rahi Navelkar",
                "email": "rsn13@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Robel Kahsay",
                "email": "rykahsay@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Xavier Holmes",
                "email": "xavierh@email.gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Amanda Bell",
                "email": "amandab2140@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jonathon Keeney",
                "email": "keeneyjg@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Millicent Quartey",
                "email": "mquartey@email.gwu.edu"
            },
            {
                "affiliation": "",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Not Applicable",
                "email": ""
            }
        ],
        "created": "2019-09-06T14:06:38.983152",
        "modified": "2022-09-26T09:04:47.995186",
        "version": "v-2.0.3"
    },
    "description_domain": {
        "keywords": [
            "PMID",
            "journal",
            "citations",
            "authors",
            "RefSeq",
            "PubMed"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.3/reviewed/human_protein_xref_refseq.csv",
                        "filename": "human_protein_xref_refseq.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.3/source/refseq_protein_all_9606.gpff",
                        "filename": "refseq_protein_all_9606.gpff"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.3/reviewed/human_protein_citations_refseq.csv",
                        "filename": "human_protein_citations_refseq.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accessions to the UniProtKB Canonical accessions. "
            }
        ]
    },
    "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"
                }
            }
        ]
    },
    "usability_domain": [
        "The Human Protein Citations (RefSeq) datasets contains human [taxid:9606] UniProtKB accessions mapped to publication information (PMID, title, journal name, publication, date, authors of corresponding RefSeq accessions). The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen. "
    ],
    "etag": "5d358e56bfd133e8a5293d68fcd9ddc2",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "human_protein_blacklisted_pmids_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/compiled/human_protein_blacklisted_pmids_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_protein_function_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_function_refseq.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_citations_refseq.csv",
                    "filename": "human_protein_citations_refseq.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_citations_refseq.stat.csv",
                    "filename": "human_protein_citations_refseq.stat.csv"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    }
}