{
    "object_id": "https://biocomputeobject.org/GLY_000481/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": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "Proteoform",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Homo sapiens",
                        "category_name": "species"
                    },
                    {
                        "category_value": "glycosylation sites",
                        "category_name": "tags"
                    },
                    {
                        "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 [Automatic Literature Mining] [Automatically verified]",
        "contributors": [
            {
                "affiliation": "George Washington University",
                "contribution": [
                    "createdBy",
                    "contributedBy"
                ],
                "name": "Rahi Navelkar",
                "email": "rsn13@gwu.edu"
            },
            {
                "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": "University of Delaware",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Vijay Shanker",
                "email": "vijay@udel.edu"
            },
            {
                "affiliation": "Georgetown University",
                "contribution": [
                    "contributedBy"
                ],
                "name": "Karen Ross",
                "email": "ker25@georgetown.edu"
            },
            {
                "affiliation": "George Washington University",
                "contribution": [
                    "contributedBy"
                ],
                "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": "2020-04-20T16:47:37.482643",
        "modified": "2022-01-13T16:57:14.632710",
        "version": "v-2.0.2"
    },
    "description_domain": {
        "keywords": [
            "proteins",
            "canonical",
            "glycosylation sites",
            "GlyTouCan",
            "Automatic Literature Mining"
        ],
        "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/source/proteoform_glycosylation_sites_literature_mining.csv",
                        "filename": "proteoform_glycosylation_sites_literature_mining.csv"
                    }
                ],
                "output_list": [
                    {
                        "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv",
                        "filename": "human_proteoform_glycosylation_sites_literature_mining.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The input file was downloaded from the provider(s) and QC steps were done to validate the protein and site annotation. Additional QC was done to check whether the annotation (protein +site) is already present in GlyGen or not. Only those rows which passed all the QC filters where added to the output file. "
            }
        ]
    },
    "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": {},
        "emperical_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"
    ],
    "etag": "61950be5603c4dbf000e0233cc2a960c",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_harvard.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_literature.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_literature.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "/data/projects/glygen/generated/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "n_sequon_info.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/misc/n_sequon_info.csv"
                }
            },
            {
                "uri": {
                    "filename": "proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "https:/data.glygen.org/ln2downloads/lit_min/2021_04_08/proteoform_glycosylation_sites_literature_mining.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv",
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv",
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.stat.csv"
                }
            }
        ]
    }
}
