{
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2data/releases/data/v-1.5.30/source/database_accession_2020_04_29_03_38_01.tsv",
                    "filename": "database_accession_2020_04_29_03_38_01.tsv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2data/releases/data/v-1.5.30/source/glycan_xref_kegg.csv",
                    "filename": "glycan_xref_kegg.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.5.30/reviewed/glycan_xref_chebi_from_kegg.csv",
                    "filename": "glycan_xref_chebi_from_kegg.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.5.30/reviewed/glycan_xref_chebi_from_kegg.stat.csv",
                    "filename": "glycan_xref_chebi_from_kegg.stat.csv"
                }
            }
        ]
    },
    "spec_version": "1.3.0",
    "object_id": "https://biocomputeobject.org/GLY_000297/v-1.5.30",
    "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": "Glycan",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "ChEBI cross-references (KEGG GLYCAN)",
                        "category_name": "tags"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "external",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Glycan Xref ChEBI [KEGG ID] ",
        "contributors": [
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Rahi Navelkar",
                "email": "rsn13@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jeet Vora",
                "email": "jeetvora@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Robel Kahsay",
                "email": "rykahsay@gwu.edu"
            }
        ],
        "created": "2019-11-13T17:04:38.641719",
        "modified": "2020-05-01T16:37:53.419575",
        "version": "v-1.5.30"
    },
    "description_domain": {
        "keywords": [
            "Glycan",
            "GlyTouCan Accession",
            "ChEBI (KEGG Glycan ID)",
            "Cross-references",
            "ID/Accession Mapping"
        ],
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.5.30/source/glycan_xref_kegg.csv",
                        "filename": "glycan_xref_kegg.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.5.30/source/database_accession_2020_04_29_03_38_01.tsv",
                        "filename": "database_accession_2020_04_29_03_38_01.tsv"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.5.30/source/glycan_xref_chebi_from_kegg.csv",
                        "filename": "glycan_xref_chebi_from_kegg.csv"
                    }
                ],
                "prerequisite": [],
                "description": "A python script was generated to use the GlyTouCan Ac. to KEGG glycan  mapping file to extract the KEGG Glycan ID to ChEBI ID mapping from the ChEBI FTP download file."
            }
        ]
    },
    "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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py",
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "value": "",
            "param": ""
        }
    ],
    "usability_domain": [
        "The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to KEGG glycan ID mapping .  The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"
    ],
    "etag": "945584ddd7a15310db27ed0472925325",
    "_id": {
        "$oid": "5dcc7df6f5c47b310d7a5f29"
    }
}
