{
    "bco_spec_version": "1.3.0", 
    "checksum": "b6383a0d8f52b159202b1509e62a3f3f", 
    "extension_domain": {
        "additional_license": {
            "data_license": "https://creativecommons.org/licenses/by/4.0/", 
            "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
        }, 
        "fhir_extension": [], 
        "scm_extension": {
            "scm_repository": "", 
            "scm_path": "", 
            "scm_type": "git", 
            "scm_commit": ""
        }, 
        "dataset_categories": [
            {
                "category_value": "Homo sapiens", 
                "category_name": "species"
            }, 
            {
                "category_value": "Protein", 
                "category_name": "molecule"
            }, 
            {
                "category_value": "Literature Mutations", 
                "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": "", 
        "name": "Human Literature Mutations", 
        "contributors": [
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Jeet Vora", 
                "email": "jeetvora@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Rahi Navelkar", 
                "email": "rsn13@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Robel Kahsay", 
                "email": "rykahsay@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Xavier Holmes", 
                "email": "xavierh@email.gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "EMBL-EBI-UniProt", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Maria Martin", 
                "email": "martin@ebi.ac.uk"
            }, 
            {
                "orcid": "", 
                "affiliation": "EMBL-EBI-UniProt", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Preethi Vasudev", 
                "email": "pvasudev@ebi.ac.uk"
            }
        ], 
        "created": "2020-04-03T17:37:22.702254", 
        "modified": "2020-04-03T17:43:08.293957", 
        "version": "1.7.13"
    }, 
    "description_domain": {
        "keywords": [
            "single-nucleotide variations (nsSNVs)", 
            "literature mutations", 
            "dbSNP", 
            "disease", 
            "ClinVar"
        ], 
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "access_time": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv", 
                        "filename": "human_protein_masterlist.csv"
                    }, 
                    {
                        "access_time": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/source/human_cancer_mutation_literature.csv", 
                        "filename": "human_cancer_mutation_literature.csv"
                    }
                ], 
                "output_list": [
                    {
                        "access_time": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv", 
                        "filename": "human_protein_mutation_literature.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "The script extracts the mutation data only for the mutations that have amino acid information and position from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"
            }
        ]
    }, 
    "execution_domain": {
        "external_data_endpoints": [], 
        "environment_variables": {}, 
        "script_driver": "manual", 
        "software_prerequisites": [
            {
                "version": "2.7.5", 
                "name": "Python", 
                "uri": {
                    "access_time": "2019-01-07T17:43:17-0500", 
                    "sha1_chksum": "", 
                    "uri": "https://www.python.org/download/releases/2.7.5/"
                }
            }
        ], 
        "script": [
            {
                "uri": {
                    "access_time": "2019-07-26T17:43:17-0500", 
                    "sha1_chksum": "", 
                    "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py", 
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    }, 
    "error_domain": {
        "empirical_error": {}, 
        "algorithmic_error": {}, 
        "emperical_error": {}
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "param": "", 
            "value": ""
        }
    ], 
    "usability_domain": [
        "The Human Literature Mutation dataset contains human [taxid:9606] mutation data extracted from literature using the DIMEX tool. The dataset contains only the mutations that have amino acid information and position in the mutation mention column.. If you use this dataset provide proper attribution to GlyGen and OncoMX."
    ], 
    "bco_id": "http://data.glygen.org/GLY_000463", 
    "_id": {
        "$oid": "5e87ac92f5c47b12b553d6e1"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org/ln2wwwdata/source/human_cancer_mutation_literature.csv", 
                    "filename": "human_cancer_mutation_literature.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv", 
                    "filename": "human_protein_masterlist.csv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_literature.csv", 
                    "filename": "human_protein_mutation_literature.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_literature.stat.csv", 
                    "filename": "human_protein_mutation_literature.stat.csv"
                }
            }
        ]
    }
}