{
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "n_sequon_info.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/n_sequon_info.csv"
                }
            },
            {
                "uri": {
                    "filename": "sample_mapping.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/misc/sample_mapping.csv"
                }
            },
            {
                "uri": {
                    "filename": "cellosaurus.txt",
                    "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2023_10_11/cellosaurus.txt"
                }
            },
            {
                "uri": {
                    "filename": "glycosylation_sites_legacy.csv",
                    "uri": "https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/glycosylation_sites_legacy.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycosylation_sites_set_30k.csv",
                    "uri": "https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/glycosylation_sites_set_30k.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv",
                    "filename": "mouse_proteoform_glycosylation_sites_literature_mining.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.stat.csv",
                    "filename": "mouse_proteoform_glycosylation_sites_literature_mining.stat.csv"
                }
            }
        ]
    },
    "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": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "Proteoform",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Mus musculus",
                        "category_name": "species"
                    },
                    {
                        "category_value": "glycosylation sites",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "contributors": [
            {
                "affiliation": "George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jeet Vora",
                "email": "jeetvora@gwu.edu"
            },
            {
                "affiliation": "George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Robel Kahsay",
                "email": "rykahsay@email.gwu.edu"
            },
            {
                "affiliation": "University of Delaware",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Vijay Shanker",
                "email": "vijay@udel.edu"
            },
            {
                "affiliation": "Georgetown University",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Karen Ross",
                "email": "ker25@georgetown.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            }
        ],
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "created": "2020-04-30T10:27:18.537975",
        "modified": "2022-09-26T09:05:56.493570",
        "version": "v-2.3.1",
        "name": "Mouse Glycosylation Sites [Automatic Literature Mining] [Automatically verified]"
    },
    "description_domain": {
        "keywords": [
            "proteins",
            "canonical",
            "glycosylation sites",
            "GlyTouCan",
            "Automatic Literature Mining"
        ],
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check wether the annotion (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "
            }
        ]
    },
    "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-proteoform-dataset.py",
                    "filename": "make-proteoform-dataset.py"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "value": "",
            "param": ""
        }
    ],
    "usability_domain": [
        "List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"
    ],
    "object_id": "https://biocomputeobject.org/GLY_000492/v-2.3.1",
    "spec_version": "1.3.0",
    "etag": "67f070d98507eafb7ea21db24bdbd608"
}