{
    "object_id": "https://biocomputeobject.org/GLY_000480/v-2.3.1",
    "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": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "Proteoform",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Homo sapiens",
                        "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": {
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Human Glycosylation Sites [GPTwiki]",
        "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": "Georgetown University",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Nathan Edwards",
                "email": "Georgetown University"
            },
            {
                "affiliation": "Georgetown University",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Radoslav Goldman",
                "email": "rg26@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"
            }
        ],
        "created": "2020-04-20T16:33:02.961632",
        "modified": "2022-09-26T09:05:56.429819",
        "version": "v-2.3.1"
    },
    "description_domain": {
        "keywords": [
            "proteins",
            "canonical",
            "glycosylation sites",
            "glycan",
            "GPTwiki",
            "GlyTouCan"
        ],
        "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). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\""
            }
        ]
    },
    "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": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"
    ],
    "etag": "36f43e13680ca9de3e9ea1f3e9b48d59",
    "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": "glycosites.csv",
                    "uri": "https:/data.glygen.org/ln2downloads/gptwiki/gpt_2021_06_23_14_51_10/glycosites.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv",
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv",
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.stat.csv"
                }
            }
        ]
    }
}