{
    "object_id": "https://biocomputeobject.org/GLY_000481/1.5.36", 
    "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]", 
        "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"
            }
        ], 
        "created": "2020-04-20T16:47:37.482643", 
        "modified": "2020-04-30T10:37:24.842264", 
        "version": "1.5.36"
    }, 
    "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/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv", 
                        "filename": "proteoform_glycosylation_sites_literature_mining.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "http://data.glygen.org/ln2wwwdata/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). Following QC steps were done using a python script: 1. Map the uniprotkb accessions to uniprotkb canonical accessions. 2. Validate the \"amino_acid\" and \"glycosylation_site\" with the .fasta sequence. 3. Add new column: Evidence with 2 values: Automatic literature Mining | GLYDS000481  (split into 2 rows)4.change column headers: uniprotkb_ac to uniprotkb_canonical_ac"
            }
        ]
    }, 
    "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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/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": "ea59168b4c41e30b4c71ade321adfe2a", 
    "_id": {
        "$oid": "5e9e0a69f5c47b468c0163f1"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/lit_min/2020_04_09/proteoform_glycosylation_sites_literature_mining.csv", 
                    "filename": "proteoform_glycosylation_sites_literature_mining.csv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv", 
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv", 
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.stat.csv"
                }
            }
        ]
    }
}