{
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv", 
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv", 
                    "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv", 
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv", 
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", 
                    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv", 
                    "filename": "human_proteoform_glycosylation_sites_glyconnect.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/glycan_xref_chebi.csv", 
                    "filename": "glycan_xref_chebi.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv", 
                    "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv", 
                    "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv", 
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv", 
                    "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", 
                    "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            }, 
            {
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv", 
                    "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "tsv", 
                "uri": {
                    "access_time": "2021-02-26T12:13:00.289136", 
                    "sha1_chksum": "", 
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_protvista_mapping.tsv", 
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.tsv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_protvista_mapping.stat.csv", 
                    "filename": "protein_glygen_uniprotkb_protvista_mapping.stat.csv"
                }
            }
        ]
    }, 
    "bco_spec_version": "1.3", 
    "checksum": "df9dffed9de6a1fe2ca13a5443d91e8c", 
    "extension_domain": {
        "additional_license": {
            "data_license": "https://creativecommons.org/licenses/by/4.0/", 
            "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
        }, 
        "fhir_extension": [], 
        "scm_extension": {
            "scm_repository": "", 
            "scm_path": "", 
            "scm_type": "git", 
            "scm_commit": ""
        }, 
        "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": [
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Rahi Navelkar", 
                "email": "rsn13@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Jeet Vora", 
                "email": "jeetvora@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Robel Kahsay", 
                "email": "rykahsay@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Karina Martinez", 
                "email": "karinamartinez@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Amanda Bell", 
                "email": "amandab2140@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Jonathon Keeney", 
                "email": "keeneyjg@gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Millicent Quartey", 
                "email": "mquartey@email.gwu.edu"
            }, 
            {
                "orcid": "", 
                "affiliation": "", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Not Applicable", 
                "email": ""
            }
        ], 
        "created": "2021-02-26T12:11:00.289136", 
        "modified": "2022-01-18T12:39:08.581365", 
        "version": "1.11.2"
    }, 
    "description_domain": {
        "keywords": [
            "UniProtKB", 
            "Glycans", 
            "ChEBI ID", 
            "ProtVista"
        ], 
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv", 
                        "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", 
                        "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv", 
                        "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", 
                        "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv", 
                        "filename": "human_proteoform_glycosylation_sites_glyconnect.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv", 
                        "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv", 
                        "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv", 
                        "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv", 
                        "filename": "human_proteoform_glycosylation_sites_gptwiki.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv", 
                        "filename": "human_proteoform_glycosylation_sites_harvard.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv", 
                        "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": " https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": " hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": " https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": " hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv", 
                        "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                    }, 
                    {
                        "access_time": "2021-02-26T12:11:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.csv", 
                        "filename": "glycan_xref_chebi.csv"
                    }
                ], 
                "output_list": [
                    {
                        "access_time": "2021-02-26T12:13:00.289136", 
                        "sha1_chksum": "", 
                        "uri": "https://data.glygen.org/ln2wwwdata/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": {
                    "access_time": "", 
                    "sha1_chksum": "", 
                    "uri": "", 
                    "filename": ""
                }
            }
        ], 
        "script": [
            {
                "uri": {
                    "access_time": "2021-02-26T12:11:00.289136", 
                    "sha1_chksum": "", 
                    "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py", 
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    }, 
    "error_domain": {
        "empirical_error": {}, 
        "algorithmic_error": {}
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "value": "", 
            "param": ""
        }
    ], 
    "usability_domain": [
        "The file includes glycan annotation (GlyTouCan ac and ChEBI Id) for the protein + site included in UniProtKB(https://uniprot.org/) database. "
    ], 
    "_id": {
        "$oid": "60392ba4f5c47b3cb0dd1e1e"
    }, 
    "bco_id": "http://data.glygen.org/GLY_000555"
}
