{
    "object_id": "https://biocomputeobject.org/GLY_000142/1.5.36", 
    "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": "Homo sapiens", 
                        "category_name": "species"
                    }, 
                    {
                        "category_value": "Proteoform", 
                        "category_name": "molecule"
                    }, 
                    {
                        "category_value": "Glycosylation sites (Harvard)", 
                        "category_name": "tags"
                    }, 
                    {
                        "category_value": "Reviewed", 
                        "category_name": "status"
                    }, 
                    {
                        "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 Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)", 
        "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": "Harvard University", 
                "contribution": [
                    "authoredBy", 
                    "contributedBy", 
                    "providedBy"
                ], 
                "name": "Christina Woo", 
                "email": "cwoo@chemistry.harvard.edu"
            }
        ], 
        "created": "2019-06-06T17:51:22.706056", 
        "modified": "2020-05-01T15:22:27.881080", 
        "version": "1.5.36"
    }, 
    "description_domain": {
        "keywords": [
            "Glycan", 
            "Publications", 
            "Proteoform"
        ], 
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv", 
                        "filename": "T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/human_proteoform_glycosylation_sites_harvard.csv", 
                        "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final 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/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py", 
                    "filename": "make-proteoform-dataset.py"
                }
            }
        ]
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "param": "", 
            "value": ""
        }, 
        {
            "step": "", 
            "param": "", 
            "value": ""
        }
    ], 
    "usability_domain": [
        "The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114)."
    ], 
    "etag": "7637f5578e655641cc6c855a458e3289", 
    "_id": {
        "$oid": "5cf98adaf5c47b56c79d76b9"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/harvard/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv", 
                    "filename": "T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv", 
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv", 
                    "filename": "human_proteoform_glycosylation_sites_harvard.stat.csv"
                }
            }
        ]
    }
}