{
    "object_id": "https://biocomputeobject.org/GLY_000291/v-1.7.13",
    "spec_version": "1.3.0",
    "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": "SMILES Isomeric sequence format",
                        "category_name": "tags"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Glycan Sequences SMILES Isomeric",
        "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": "2019-11-13T16:37:56.677676",
        "modified": "2020-05-01T16:34:08.669990",
        "version": "v-1.7.13"
    },
    "description_domain": {
        "keywords": [
            "Glycan",
            "GlyTouCan Accession",
            "SMILES Isomeric"
        ],
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.7.13/source/CID-SMILES_2020_04_29_15_19_03.gz",
                        "filename": "CID-SMILES_2020_04_29_15_19_03.gz"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.7.13/source/glycan_sequences_smiles_isomeric.csv",
                        "filename": "glycan_sequences_smiles_isomeric.csv"
                    }
                ],
                "prerequisite": [],
                "description": "A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"
            }
        ]
    },
    "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": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"
    ],
    "etag": "241bf8757179ba345ee0014873cf428e",
    "_id": {
        "$oid": "5dcc77b4f5c47b2bd2bf006a"
    },
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pubchem/compound/2020_11_02/CID-SMILES",
                    "filename": "CID-SMILES_2020_04_29_15_19_03.gz"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/glycan_sequences_smiles_isomeric.csv",
                    "filename": "glycan_sequences_smiles_isomeric.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/glycan_sequences_smiles_isomeric.stat.csv",
                    "filename": "glycan_sequences_smiles_isomeric.stat.csv"
                }
            }
        ]
    }
}