{
    "object_id": "https://biocomputeobject.org/GLY_000284/v-1.12.3",
    "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": "",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Glycan",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Biosynthetic Enzyme",
                        "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 Enzyme",
        "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"
            },
            {
                "affiliation": "University of Georgia",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Will York",
                "email": "will@ccrc.uga.edu"
            },
            {
                "affiliation": "University of Georgia",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Allison Nairn",
                "email": "avnairn@uga.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Amanda Bell",
                "email": "amandab2140@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jonathon Keeney",
                "email": "keeneyjg@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Millicent Quartey",
                "email": "mquartey@email.gwu.edu"
            }
        ],
        "created": "2019-11-13T13:19:08.883378",
        "modified": "2022-01-12T16:20:52.337922",
        "version": "v-1.12.3"
    },
    "description_domain": {
        "keywords": [
            "Glycan",
            "GlyTouCan Accession",
            "Enzyme"
        ],
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/annotated_glycans.csv",
                        "filename": "annotated_glycans.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/human_protein_recnames.csv",
                        "filename": "human_protein_recnames.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/mouse_protein_recnames.csv",
                        "filename": "mouse_protein_recnames.csv"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.12.3/source/glycan_enzyme.csv",
                        "filename": "glycan_enzyme.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The input file was downloaded from the source authors and a python script was used to extract columns: glytoucan_ac,residue_name,residue_id,uniprot,gene_name,gene_id,parent_residue_id,type,species. The script also assigned protein recommended name based on the UniProtKB accession. "
            }
        ]
    },
    "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"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {},
        "emperical_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the Glyco tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan."
    ],
    "etag": "670be3192b913fc525ecb2d4b011d8f8",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "glycan_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/sarscov2_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/sarscov1_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/rat_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/hcv1b_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/hcv1a_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/human_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/hcv1a_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/human_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/sarscov1_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/mouse_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/sarscov2_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/hcv1b_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_protein_recnames.csv",
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/rat_protein_recnames.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycotree_annotated_glycans.tsv",
                    "uri": "https:/data.glygen.org/ln2downloads/sandbox/02_06_2022/glycotree_annotated_glycans.tsv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_enzyme.csv",
                    "filename": "glycan_enzyme.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/glycan_enzyme.stat.csv",
                    "filename": "glycan_enzyme.stat.csv"
                }
            }
        ]
    }
}
