{
    "object_id": "https://biocomputeobject.org/GLY_000555/v-2.9.1",
    "spec_version": "1.3.0",
    "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": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "glycan",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "tsv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "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": "Severe acute respiratory syndrome coronavirus 2"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome-related coronavirus"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "",
        "name": "UniProtKB ProtVista Mapping",
        "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"
            },
            {
                "affiliation": "",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Not Applicable",
                "email": ""
            },
            {
                "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"
            }
        ],
        "created": "2021-02-26T12:11:00.289136",
        "modified": "2024-05-17T11:24:04.501Z",
        "version": "v-2.9.1"
    },
    "description_domain": {
        "keywords": [
            "UniProtKB",
            "Glycans",
            "ChEBI ID",
            "ProtVista"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "Glycosylation annotation from input files were combined together. The glytoucan_ac was mapped to chebi_id using another input file. Additionally, two new columns uniprot_ac and tax_id were added in the output file. The following filtering rules wer applied: 1) Only those protein + site were inlcuded which are present in UniProtKB database 2) Only those rows were included where a valid ChEBI ID was present. "
            }
        ]
    },
    "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/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "
    ],
    "etag": "8e36ad7e1e896c16710699c0bafe18c2",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "arabidopsis_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/arabidopsis_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/arabidopsis_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "bovine_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/bovine_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "bovine_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/bovine_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "chicken_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/chicken_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "chicken_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/chicken_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "dicty_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/dicty_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "dicty_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/dicty_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycan_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/glycan_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycan_xref_chebi.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/glycan_xref_chebi.csv"
                }
            },
            {
                "uri": {
                    "filename": "hamster_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/hamster_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "hamster_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/hamster_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "pig_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/pig_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "pig_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/pig_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "zebrafish_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/zebrafish_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "tsv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv",
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.tsv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv",
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.stat.csv"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    }
}
