{
    "object_id": "https://biocomputeobject.org/GLY_000530/v-2.7.1",
    "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": "Severe acute respiratory syndrome coronavirus 2",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Proteoform",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Glycosylation Sites",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "csv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "",
        "name": "SARS-CoV2 Glycosylation sites",
        "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": "GlyConnect",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Frederique Lisacek",
                "email": "frederique.lisacek@sib.swiss"
            },
            {
                "affiliation": "GlyConnect",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Julien Mariethoz",
                "email": "julien.mariethoz@sib.swiss"
            },
            {
                "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"
            }
        ],
        "created": "2020-09-24T13:36:00.724463",
        "modified": "2024-05-17T11:24:03.671Z",
        "version": "v-2.7.1"
    },
    "description_domain": {
        "keywords": [
            "glycosylation",
            "reported glycosylation"
        ],
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in UniProtKB for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (sarscov2_proteoform_glycosylation_sites_glyconnect.1.log)"
            }
        ]
    },
    "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": [
        "The SARS-CoV2 Glycosylation Sites (GlyConnect) dataset contains Severe acute respiratory syndrome coronavirus 2 [taxid:2697049] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."
    ],
    "etag": "6f0f0c5917b7a0474587590d61d6947d",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "n_sequon_info.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/misc/n_sequon_info.csv"
                }
            },
            {
                "uri": {
                    "filename": "sample_mapping.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/misc/sample_mapping.csv"
                }
            },
            {
                "uri": {
                    "filename": "cellosaurus.txt",
                    "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2024_09_05/cellosaurus.txt"
                }
            },
            {
                "uri": {
                    "filename": "glyconnect_sarscov2.json",
                    "uri": "https:/data.glygen.org/ln2downloads/glyconnect/2024_09_05/glyconnect_sarscov2.json"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv",
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.stat.csv"
                }
            }
        ]
    }
}