{
    "object_id": "https://biocomputeobject.org/GLY_000289/v-2.9.1",
    "spec_version": "1.3.0",
    "etag": "22285e1226609d13640f73b63b1d3738",
    "provenance_domain": {
        "name": "Glycan Sequences InChI",
        "version": "v-2.9.1",
        "created": "2019-11-13T16:26:03.109539",
        "modified": "2024-05-17T11:23:55.142Z",
        "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": "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 sequences in InChI format and InChI key for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping dataset (https://data.glygen.org/GLY_000305). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLY_000281). InChI sequences and keys are retrieved from the PubChem ftp site (ftp://ftp.ncbi.nlm.nih.gov/pubchem/Compound/CURRENT-Full/SDF/)."
    ],
    "description_domain": {
        "keywords": [
            "Glycan",
            "GlyTouCan Accession",
            "InChI",
            "PubChem"
        ],
        "platform": [],
        "pipeline_steps": [
            {
                "name": "dataset-maker/pubchem-download-step1.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The GlyTouCan to PubChem CID mapping file was used download sdf PubChem compound files from the PubChem CID ftp site. Python scripts were used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."
            },
            {
                "step_number": 2,
                "name": "pubchem-download-step2.py",
                "description": "",
                "prerequisite": [],
                "input_list": [],
                "output_list": []
            },
            {
                "step_number": 3,
                "name": "pubchem-download-step3.py",
                "description": "",
                "prerequisite": [],
                "input_list": [],
                "output_list": []
            },
            {
                "step_number": 4,
                "name": "pubchem-download-step4.py",
                "description": "",
                "prerequisite": [],
                "input_list": [],
                "output_list": []
            },
            {
                "step_number": 5,
                "name": "make-species-agnostic-dataset.py",
                "description": "",
                "prerequisite": [],
                "input_list": [],
                "output_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-2.9.1/reviewed/glycan_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycan_xref_pubchem.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/glycan_xref_pubchem.csv"
                }
            },
            {
                "uri": {
                    "filename": "CID-InChI-Key.gz",
                    "uri": "https:/data.glygen.org/ln2downloads/pubchem/compound/archive/CID-InChI-Key.gz"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/glycan_sequences_inchi.csv",
                    "filename": "glycan_sequences_inchi.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/glycan_sequences_inchi.stat.csv",
                    "filename": "glycan_sequences_inchi.stat.csv"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "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": "InChI 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": "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"
                    }
                ]
            }
        }
    ]
}