{
    "object_id": "https://biocomputeobject.org/GLY_000428/1.8.25", 
    "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": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)", 
                        "category_name": "species"
                    }, 
                    {
                        "category_value": "Protein", 
                        "category_name": "molecule"
                    }, 
                    {
                        "category_value": "N-Glycosylation Sequon", 
                        "category_name": "tags"
                    }, 
                    {
                        "category_value": "csv", 
                        "category_name": "file_type"
                    }, 
                    {
                        "category_value": "Reviewed", 
                        "category_name": "status"
                    }, 
                    {
                        "category_value": "internal", 
                        "category_name": "scope"
                    }
                ]
            }
        }
    ], 
    "provenance_domain": {
        "license": "https://creativecommons.org/licenses/by/4.0/", 
        "name": "SARS-CoV2 N-Glycosylation Sequon", 
        "contributors": [
            {
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Jeet Vora", 
                "email": "jeetvora@gwu.edu"
            }, 
            {
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Rahi Navelkar", 
                "email": "rsn13@gwu.edu"
            }, 
            {
                "affiliation": "The George Washington University", 
                "contribution": [
                    "createdBy"
                ], 
                "name": "Robel Kahsay", 
                "email": "rykahsay@gwu.edu"
            }, 
            {
                "affiliation": "EMBL-EBI-UniProt", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Maria Martin", 
                "email": "martin@ebi.ac.uk"
            }, 
            {
                "affiliation": "EMBL-EBI-UniProt", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Preethi Vasudev", 
                "email": "pvasudev@ebi.ac.uk"
            }
        ], 
        "created": "2020-04-03T11:46:41.584409", 
        "modified": "2020-04-10T12:26:05.361474", 
        "version": "1.8.25"
    }, 
    "description_domain": {
        "keywords": [
            "n-glycosylation sequon", 
            "NXS/T", 
            "n-glycosylation motif", 
            "n-glycosylation consensus sequence"
        ], 
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta", 
                        "filename": "sarscov2_protein_canonicalsequences.fasta"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.csv", 
                        "filename": "sarscov2_protein_glycosylation_motifs.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."
            }
        ]
    }, 
    "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-protein-dataset.py", 
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    }, 
    "usability_domain": [
        "The SARS coronavirus (SARS-CoV-2 or 2019-nCov) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov2 [taxid:2697049] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."
    ], 
    "etag": "322ee948d5fd04ece05d8363d94a1ec2", 
    "_id": {
        "$oid": "5e86bd8df5c47b20de0f5981"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.8.25/reviewed/sarscov2_protein_canonicalsequences.fasta", 
                    "filename": "sarscov2_protein_canonicalsequences.fasta"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.csv", 
                    "filename": "sarscov2_protein_glycosylation_motifs.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.stat.csv", 
                    "filename": "sarscov2_protein_glycosylation_motifs.stat.csv"
                }
            }
        ]
    }
}