{
    "object_id": "https://biocomputeobject.org/GLY_001526/v-2.11.1",
    "spec_version": "1.3.0",
    "etag": "f4290de7d859d94f0c166f0948900cf3",
    "provenance_domain": {
        "name": "UniChem Glycan Linkouts",
        "version": "v-2.11.1",
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "modified": "2026-03-03T12:09:03.539Z",
        "contributors": [
            {
                "name": "Jeet Vora",
                "affiliation": "The George Washington University",
                "email": "jeetvora@gwu.edu",
                "contribution": [
                    "createdBy"
                ]
            },
            {
                "name": "Robel Kahsay",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "rykahsay@gwu.edu"
            },
            {
                "name": "Urnisha Bhuiyan",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "sbhuiyan28@email.gwu.edu"
            },
            {
                "name": "Kate Warner",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "k.warner1@gwu.edu"
            }
        ]
    },
    "usability_domain": [
        "The UniChem Glycan Linkouts dataset contains 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). The dataset is formatted as per the UniChem submission guidelines."
    ],
    "description_domain": {
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "input_list": [],
                "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. The script also formats the dataset as defined by the UniChem guidelines to generate a tsv dataset.",
                "prerequisite": [],
                "output_list": []
            }
        ],
        "keywords": [
            "UniChem Glycan Linkouts",
            "UniChem",
            "Glycan",
            "GlyTouCan Accession",
            "SMILES Isomeric"
        ]
    },
    "parametric_domain": [
        {
            "value": ""
        }
    ],
    "io_domain": {
        "output_subdomain": [
            {
                "mediatype": "tsv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.11.1/reviewed/glycan_unichem_linkout.tsv",
                    "filename": "glycan_unichem_linkout.tsv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.11.1/reviewed/glycan_unichem_linkout.stat.csv",
                    "filename": "glycan_unichem_linkout.stat.csv"
                }
            }
        ],
        "input_subdomain": [
            {
                "uri": {
                    "filename": "glycan_sequences_smiles_isomeric.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.11.1/reviewed/glycan_sequences_smiles_isomeric.csv"
                }
            }
        ]
    },
    "execution_domain": {
        "script": [
            {
                "uri": {
                    "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-species-agnostic-dataset.py",
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ],
        "script_driver": "manual",
        "software_prerequisites": [
            {
                "version": "2.7.5",
                "name": "Python",
                "uri": {
                    "uri": "https://www.python.org/download/releases/2.7.5/"
                }
            }
        ],
        "external_data_endpoints": [],
        "environment_variables": {}
    },
    "extension_domain": [
        {
            "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/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": "UniChem glycan linkouts",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "tsv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Homo sapiens"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Mus musculus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus norvegicus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Saccharomyces cerevisiae"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Drosophila melanogaster"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome coronavirus 2"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Dictyostelium discoideum"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Sus scrofa"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Sus scrofa domesticus"
                    }
                ]
            }
        }
    ],
    "error_domain": {}
}