{
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt",
                    "filename": "uniprot-proteome-9606-homo-sapiens-2018-11.nt"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_protein_idmapping.csv",
                    "filename": "human_protein_idmapping.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_protein_transcriptlocus.csv",
                    "filename": "human_protein_transcriptlocus.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/datasets/reviewed/human_protein_transcriptlocus.stat.csv",
                    "filename": "human_protein_transcriptlocus.stat.csv"
                }
            }
        ]
    },
    "spec_version": "1.3.0",
    "object_id": "https://biocomputeobject.org/GLY_000135/v-1.0.13",
    "extension_domain": [
        {
            "extension_schema": "http://www.w3id.org/biocompute/extension_domain/1.1.0/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": "Reviewed",
                        "category_name": "status"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Human Transcript Locus",
        "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": [],
                "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": "Leyla Garcia",
                "email": "ljgarcia@ebi.ac.uk"
            },
            {
                "affiliation": "EMBL-EBI-UniProt",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Preethi Vasudev",
                "email": "pvasudev@ebi.ac.uk"
            }
        ],
        "created": "2019-03-16T16:05:08.939322",
        "modified": "2019-04-24T10:51:28.532984",
        "version": "v-1.0.13"
    },
    "description_domain": {
        "keywords": [
            "transcript locus",
            "peptide id",
            "Ensembl"
        ],
        "pipeline_steps": [
            {
                "name": "extract-from-endpoint.py",
                "step_number": 1,
                "version": "1.0",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt",
                        "filename": "uniprot-proteome-9606-homo-sapiens-2018-11.nt"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_protein_idmapping.csv",
                        "filename": "human_protein_idmapping.csv"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.0.13/reviewed/human_protein_transcriptlocus.csv",
                        "filename": "human_protein_transcriptlocus.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset"
            }
        ]
    },
    "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/pipeline/extractor/extract-from-endpoint.py",
                    "filename": "extract-from-endpoint.py"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {},
        "emperical_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "value": "",
            "param": ""
        }
    ],
    "usability_domain": [
        "The Human Transcript Locus contains UniProtKB human [taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts's start and end position",
        "The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"
    ],
    "etag": "50eb71f64ba39f59df3c149e5a456668",
    "_id": {
        "$oid": "5c8d56f4f5c47b3476ee9534"
    }
}