{
    "object_id": "https://biocomputeobject.org/GLY_000268/v-2.0.2",
    "spec_version": "1.3.0",
    "extension_domain": [
        {
            "extension_schema": "http://www.w3id.org/biocompute/extension_domain/1.1.0/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": "tags"
                    },
                    {
                        "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 Tyr O-Linked 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": "Rahi Navelkar",
                "email": "rsn13@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Robel Kahsay",
                "email": "rykahsay@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Xavier Holmes",
                "email": "xavierh@email.gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Amanda Bell",
                "email": "amandab2140@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Jonathon Keeney",
                "email": "keeneyjg@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Millicent Quartey",
                "email": "mquartey@email.gwu.edu"
            }
        ],
        "created": "2019-09-06T14:06:38.994596",
        "modified": "2020-08-19T15:56:55.296314",
        "version": "v-2.0.2"
    },
    "description_domain": {
        "keywords": [
            "tyrosine",
            "o-linked glycosylation",
            "glycosylation sites"
        ],
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv",
                        "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv",
                        "filename": "human_protein_masterlist.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/source/uniprot-proteome-homo-sapiens.nt",
                        "filename": "uniprot-proteome-homo-sapiens.nt"
                    }
                ],
                "output_list": [
                    {
                        "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv",
                        "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries."
            }
        ]
    },
    "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"
                }
            }
        ]
    },
    "usability_domain": [
        "The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen"
    ],
    "etag": "95dba99d5bc9525a12d554e0b0059304",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv",
                    "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv",
                    "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv"
                }
            }
        ]
    }
}
