{
    "object_id": "https://biocomputeobject.org/GLY_000555/v-1.11.2",
    "spec_version": "1.3",
    "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": "",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "glycan",
                        "category_name": "tags"
                    },
                    {
                        "category_value": "tsv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "",
        "name": "UniProtKB ProtVista Mapping",
        "contributors": [
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Rahi Navelkar",
                "email": "rsn13@gwu.edu"
            },
            {
                "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": "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"
            },
            {
                "affiliation": "",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Not Applicable",
                "email": ""
            }
        ],
        "created": "2021-02-26T12:11:00.289136",
        "modified": "2022-01-18T12:39:08.581365",
        "version": "v-1.11.2"
    },
    "description_domain": {
        "keywords": [
            "UniProtKB",
            "Glycans",
            "ChEBI ID",
            "ProtVista"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv",
                        "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv",
                        "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv",
                        "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv",
                        "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv",
                        "filename": "human_proteoform_glycosylation_sites_glyconnect.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv",
                        "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv",
                        "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                        "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv",
                        "filename": "human_proteoform_glycosylation_sites_gptwiki.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv",
                        "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                        "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": " https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": " hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": " https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": " hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv",
                        "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/glycan_xref_chebi.csv",
                        "filename": "glycan_xref_chebi.csv"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv",
                        "filename": "protein_glygen_uniprotkb_protvista_mapping.tsv"
                    }
                ],
                "prerequisite": [],
                "description": "Glycosylation annotation from input files were combined together. The glytoucan_ac was mapped to chebi_id using another input file. Additionally, two new columns uniprot_ac and tax_id were added in the output file. The following filtering rules wer applied: 1) Only those protein + site were inlcuded which are present in UniProtKB database 2) Only those rows were included where a valid ChEBI ID was present. "
            }
        ]
    },
    "execution_domain": {
        "external_data_endpoints": [],
        "environment_variables": {},
        "script_driver": "manual",
        "software_prerequisites": [
            {
                "version": "2.7.5",
                "name": "Python",
                "uri": {
                    "uri": "",
                    "filename": ""
                }
            }
        ],
        "script": [
            {
                "uri": {
                    "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "
    ],
    "etag": "df9dffed9de6a1fe2ca13a5443d91e8c",
    "_id": {
        "$oid": "60392ba4f5c47b3cb0dd1e1e"
    },
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv",
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                    "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv",
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv",
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv",
                    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv",
                    "filename": "human_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/glycan_xref_chebi.csv",
                    "filename": "glycan_xref_chebi.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv",
                    "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv",
                    "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv",
                    "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv",
                    "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2data/releases/data/v-1.11.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv",
                    "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "tsv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv",
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.tsv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv",
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.stat.csv"
                }
            }
        ]
    }
}
