{
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2020_07_29_13_25_00.gz", 
                    "filename": "CID-Synonym-filtered_2020_07_29_13_25_00.gz"
                }
            }, 
            {
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.csv", 
                    "filename": "glycan_sequences_inchi.csv"
                }
            }
        ], 
        "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"
                }
            }
        ]
    }, 
    "spec_version": "1.3.0", 
    "object_id": "https://biocomputeobject.org/GLY_000296/1.7.13", 
    "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(PUBCHEM CID)", 
                        "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 [PubChem CID]", 
        "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": "2020-08-07T11:13:26.470844", 
        "version": "1.7.13"
    }, 
    "description_domain": {
        "keywords": [
            "Glycan", 
            "GlyTouCan Accession", 
            "ChEBI (PubChem CID)", 
            "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/CID-Synonym-filtered_2020_07_29_13_25_00.gz", 
                        "filename": "CID-Synonym-filtered_2020_07_29_13_25_00.gz"
                    }, 
                    {
                        "uri": "http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.csv", 
                        "filename": "glycan_sequences_inchi.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/glycan_xref_chebi.csv", 
                        "filename": "glycan_xref_chebi.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "A python script was generated to use the GlyTouCan Ac. to PubChem CID  mapping file to extract the PubChem CID to ChEBI ID mapping from the PubChem FTP download file. Certain one-to-many PubChem to ChEBI mappings were resolved by matching the InCHI sequences associated with PubChem CID and ChEBI ID from respective databases."
            }
        ]
    }, 
    "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/glygener/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py", 
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ]
    }, 
    "parametric_domain": [
        {
            "step": "", 
            "value": "", 
            "param": ""
        }
    ], 
    "usability_domain": [
        "The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping . Using PubChem CID as an anchor database the GlyTouCans from dataset https://data.glygen.org/GLYDS000305 (v1.5.13) are being mapped or registed into ChEBI (by Gareth Owen) using different applications (like KNIME and ClassyFire). The newly added glycans from ChEBI are added back to PubChem through ChEBI's monthly submissions. This dataset uses the PubChem FTP files to map to ChEBI ID and thus only includes ChEBI ID for glycans added in PubChem via ChEBI. One-to-many PubChem CID to ChEBI mappings are resolved using InChI seqences downloaded from both (PubChem CID and ChEBI) databases. The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"
    ], 
    "etag": "8d24fa55868a66c7e44fcfe23ecbcf59", 
    "_id": "5dcc7c9cf5c47b2ed3a146f5"
}