{
    "object_id": "https://biocomputeobject.org/GLY_000042/v-2.2.1",
    "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": "Homo sapiens",
                        "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": "https://creativecommons.org/licenses/by/4.0/",
        "name": "Human Glycosylation Sites (RCSB PDB)",
        "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": "RCSB PDB",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Jasmine Young",
                "email": "jasmine@rcsb.rutgers.edu"
            },
            {
                "affiliation": "RCSB PDB",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Chenghua Shao",
                "email": "chenghua@rcsb.rutgers.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": "2019-01-23T17:21:05.909814",
        "modified": "2022-09-26T08:48:18.837668",
        "version": "v-2.2.1"
    },
    "description_domain": {
        "keywords": [
            "PDB",
            "glycosylation sites",
            "amino acid",
            "amino acid chain"
        ],
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."
            },
            {
                "name": "",
                "step_number": 0,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": ""
            }
        ]
    },
    "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 Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."
    ],
    "etag": "e179fa55324d1afe556ccc687bc99096",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "n_sequon_info.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/n_sequon_info.csv"
                }
            },
            {
                "uri": {
                    "filename": "sample_mapping.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/misc/sample_mapping.csv"
                }
            },
            {
                "uri": {
                    "filename": "cellosaurus.txt",
                    "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2023_07_13/cellosaurus.txt"
                }
            },
            {
                "uri": {
                    "filename": "N-linked-ARG-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details"
                }
            },
            {
                "uri": {
                    "filename": "N-linked-ASN-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/N-linked-ASN-details"
                }
            },
            {
                "uri": {
                    "filename": "O-linked-ASP-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details"
                }
            },
            {
                "uri": {
                    "filename": "O-linked-GLU-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details"
                }
            },
            {
                "uri": {
                    "filename": "O-linked-SER-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-SER-details"
                }
            },
            {
                "uri": {
                    "filename": "O-linked-THR-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-THR-details"
                }
            },
            {
                "uri": {
                    "filename": "O-linked-TYR-details",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details"
                }
            },
            {
                "uri": {
                    "filename": "pdb_chain_uniprot.csv",
                    "uri": "https:/data.glygen.org/ln2downloads/pdb/download_2018_10_23/pdb_chain_uniprot.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_pdb.csv",
                    "filename": "human_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.2.1/reviewed/human_proteoform_glycosylation_sites_pdb.stat.csv",
                    "filename": "human_proteoform_glycosylation_sites_pdb.stat.csv"
                }
            }
        ]
    }
}