{
    "object_id": "https://biocomputeobject.org/GLY_000296/1.8.25", 
    "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": "Glycan", 
                        "category_name": "molecule"
                    }, 
                    {
                        "category_value": "ChEBI cross-references", 
                        "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": "Glycan Xref ChEBI", 
        "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": "EBI-ChEBI", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Gareth Owen", 
                "email": "gowen@ebi.ac.uk"
            }
        ], 
        "created": "2019-11-13T16:58:52.830892", 
        "modified": "2021-03-02T12:30:09.109730", 
        "version": "1.8.25"
    }, 
    "description_domain": {
        "keywords": [
            "Glycan", 
            "GlyTouCan Accession", 
            "ChEBI", 
            "Cross-references", 
            "ID/Accession Mapping"
        ], 
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/database_accession.tsv", 
                        "filename": "database_accession.tsv"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv", 
                        "filename": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.csv", 
                        "filename": "glycan_xref_chebi.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "The input file (database_accession) was downloaded directly from the CHEBI-EBI FTP dowloads (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The following rules were applied to generate the final output file: 1) rows where \"SOURCE\" column = GlyTouCan were filtered out. 2) for such rows  \"COMPOUND_ID\" is chebi_id and \"ACCESSION_NUMBER\" is glytoucan_ac. 2) the extracted glytoucan_ac were checked against the GlyGen glycan masterlist (https://data.glygen.org/GLY_000281 or input file glycan_masterlist.csv) and the GlyTouCan accessions not included in the GlyGen glycan masterlist were excluded to generate the final output file. The glycans are submitted into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."
            }
        ]
    }, 
    "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-species-agnostic-dataset.py", 
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ]
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "param": "", 
            "value": ""
        }
    ], 
    "usability_domain": [
        " The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession). The mapping is produced using the direct download files(database_accession.tsv) from the ChEBI-EBI FTP (ftp://ftp.ebi.ac.uk/pub/databases/chebi/). The glycans are mapped/registered into the ChEBI database as follows: 1) GlyTouCan accession is mapped directly to ChEBI ID through PubChem CID (if the PubChem CID has a ChEBI cross-reference) 2) glycans with PubChem CID (which lack a ChEBI cross-reference) are integrated into ChEBI through applications like KNIME (https://europepmc.org/article/med/28757290) and ClassyFire (https://pubmed.ncbi.nlm.nih.gov/27867422/). 2) glycans without a PubChem CID are registered manually into the CHEBI database."
    ], 
    "etag": "bd1256081de6b46f9439ab987ab2440e", 
    "_id": {
        "$oid": "5dcc7c9cf5c47b2ed3a146f5"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.8.25/reviewed/glycan_masterlist.csv", 
                    "filename": "glycan_masterlist.csv"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/chebi/2021_04_08/database_accession.tsv", 
                    "filename": "database_accession.tsv"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.csv", 
                    "filename": "glycan_xref_chebi.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.stat.csv", 
                    "filename": "glycan_xref_chebi.stat.csv"
                }
            }
        ]
    }
}