{
    "object_id": "https://biocomputeobject.org/GLY_000021/1.0.13", 
    "license": "https://creativecommons.org/licenses/by/4.0/", 
    "contributors": [
        {
            "orcid": "", 
            "affiliation": "", 
            "contribution": [
                "createdBy"
            ], 
            "name": "Jeet Vora", 
            "email": "jeetvora@gwu.edu"
        }, 
        {
            "orcid": "", 
            "affiliation": "", 
            "contribution": [
                "createdBy"
            ], 
            "name": "Rahi Navelkar", 
            "email": "rsn13@gwu.edu"
        }
    ], 
    "created": "2019-01-23T17:21:05.888176", 
    "spec_version": "1.3.0", 
    "modified": "2019-02-19T13:43:16.094584", 
    "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"
                    }
                ]
            }
        }
    ], 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff", 
                    "filename": "refseq_protein_all_9606.gpff"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv", 
                    "filename": "human_protein_idmapping.csv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "", 
                "uri": {
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.csv", 
                    "filename": "human_protein_refseq_protein_info.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.stat.csv", 
                    "filename": "human_protein_refseq_protein_info.stat.csv"
                }
            }
        ]
    }, 
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/", 
        "name": "Human RefSeq Protein Information", 
        "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"
            }
        ], 
        "created": "2019-01-23T17:21:05.888176", 
        "modified": "2019-04-23T13:57:53.499636", 
        "version": "1.0.13"
    }, 
    "description_domain": {
        "keywords": [
            "protein information", 
            "protein length"
        ], 
        "pipeline_steps": [
            {
                "name": "extract-from-gp.py", 
                "step_number": 1, 
                "version": "1", 
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff", 
                        "filename": "refseq_protein_all_9606.gpff"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv", 
                        "filename": "human_protein_idmapping.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.csv", 
                        "filename": "human_protein_refseq_protein_info.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "This script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion 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/pipeline/extractor/extract-from-gp.py", 
                    "filename": "extract-from-gp.py"
                }
            }
        ]
    }, 
    "version": "1.0.5", 
    "error_domain": {
        "empirical_error": {}, 
        "algorithmic_error": {}, 
        "emperical_error": {}
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "value": "", 
            "param": ""
        }
    ], 
    "usability_domain": [
        "The Human RefSeq Protein Information dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summmary from NCBI RefSeq database", 
        "If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"
    ], 
    "etag": "d562fc28279074c14b3a3438fcf0f001", 
    "_id": {
        "$oid": "5c48e8d1f5c47b65ae4b5d00"
    }, 
    "name": ""
}