{
    "object_id": "https://biocomputeobject.org/GLY_000400/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": "Rattus norvegicus",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "All Protein Sequence Info",
                        "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": "Rat Protein Sequence Info (UniProtKB)",
        "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": "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"
            },
            {
                "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"
            }
        ],
        "created": "2020-03-15T14:37:18.669955",
        "modified": "2022-09-26T09:05:56.548735",
        "version": "v-2.0.3"
    },
    "description_domain": {
        "keywords": [
            "protein sequence info",
            "fasta header",
            "UniProtKB"
        ],
        "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/source/uniprot-proteome-rattus-norvegicus.nt",
                        "filename": "uniprot-proteome-rattus-norvegicus.nt"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.3/reviewed/rat_protein_sequenceinfo.csv",
                        "filename": "rat_protein_sequenceinfo.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The script loads the UniProtKB sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"
            }
        ]
    },
    "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"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The Rat Protein Sequence Info (UniProtKB) dataset contains rat [taxid:10116] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"
    ],
    "etag": "a066d79811d766661df883812d458617",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "uniprot-proteome-rattus-norvegicus.nt",
                    "uri": "/data/shared/glyds/downloads/ebi/2022_05/uniprot-proteome-rattus-norvegicus.nt"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "fasta",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_sequenceinfo.csv",
                    "filename": "rat_protein_sequenceinfo.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_sequenceinfo.stat.csv",
                    "filename": "rat_protein_sequenceinfo.stat.csv"
                }
            }
        ]
    }
}
