{
    "object_id": "https://biocomputeobject.org/GLY_000580/v-2.8.1",
    "spec_version": "1.3.0",
    "etag": "e25fea2ac68c9959fafb9e1a660c8ca5",
    "provenance_domain": {
        "name": "Glycan sequence GWB",
        "version": "v-2.8.1",
        "created": "2021-08-02T12:45:09.980974",
        "modified": "2024-05-17T11:24:05.411Z",
        "embargo": {
            "start_time": "",
            "end_time": ""
        },
        "contributors": [
            {
                "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"
            },
            {
                "affiliation": "Georgetown University",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Nathan Edwards",
                "email": "nje5@georgetown.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Luke Johnson",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "luke.johnson@email.gwu.edu"
            },
            {
                "name": "Urnisha Bhuiyan",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "sbhuiyan28@email.gwu.edu"
            },
            {
                "name": "Cyrus Au-Yeung",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "cyruschauyeung@gwu.edu"
            },
            {
                "name": "Kate Warner",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "k.warner1@gwu.edu"
            }
        ],
        "license": "https://creativecommons.org/licenses/by/4.0/"
    },
    "usability_domain": [
        "The dataset provides the glycan sequences in GlycoWorkBench format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281)."
    ],
    "description_domain": {
        "keywords": [
            "Glycan",
            "GlyTouCan Accession",
            "GWB"
        ],
        "platform": [],
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "A python script is used to generate the GlycoWorkBench format based on the compositioon for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."
            }
        ]
    },
    "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": {}
    },
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "glycan_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.8.1/reviewed/glycan_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "names.tsv",
                    "uri": "https:/data.glygen.org/ln2downloads/glytoucan/2025_02_10/export/names.tsv"
                }
            },
            {
                "uri": {
                    "filename": "subsumption.tsv",
                    "uri": "https:/data.glygen.org/ln2downloads/glytoucan/2025_02_10/export/subsumption.tsv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.8.1/reviewed/glycan_sequences_gwb.csv",
                    "filename": "glycan_sequences_gwb.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.8.1/reviewed/glycan_sequences_gwb.stat.csv",
                    "filename": "glycan_sequences_gwb.stat.csv"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "value": "",
            "param": ""
        }
    ],
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    },
    "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": "GWB sequence format",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Sus scrofa"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Homo sapiens"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Mus musculus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Saccharomyces cerevisiae"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Drosophila melanogaster"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus norvegicus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome coronavirus 2"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Sus scrofa domesticus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Dictyostelium discoideum"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Hepacivirus C"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome-related coronavirus"
                    }
                ]
            }
        }
    ]
}
