{
    "object_id": "https://biocomputeobject.org/GLY_000226/1.7.13", 
    "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": "Rattus norvegicus", 
                        "category_name": "species"
                    }, 
                    {
                        "category_value": "Protein", 
                        "category_name": "molecule"
                    }, 
                    {
                        "category_value": "Glycosylation Sites", 
                        "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": "Rat Glycosylation Sites (RCSB PDB)", 
        "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": "RCSB PDB", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Jasmine Young", 
                "email": "jasmine@rcsb.rutgers.edu"
            }, 
            {
                "affiliation": "RCSB PDB", 
                "contribution": [
                    "contributedBy"
                ], 
                "name": "Chenghua Shao", 
                "email": "chenghua@rcsb.rutgers.edu"
            }
        ], 
        "created": "2019-09-06T14:06:38.954510", 
        "modified": "2020-04-10T11:52:41.075559", 
        "version": "1.7.13"
    }, 
    "description_domain": {
        "keywords": [
            "glycosylation", 
            "reported glycosylation", 
            "predicted glycosylation", 
            "UniProtKB", 
            "PubMed", 
            "Evidence and conclusion Ontology"
        ], 
        "pipeline_steps": [
            {
                "name": "make-proteoform-dataset.py", 
                "step_number": 1, 
                "version": "", 
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details", 
                        "filename": "N-linked-ARG-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/N-linked-ASN-details", 
                        "filename": "N-linked-ASN-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details", 
                        "filename": "O-linked-ASP-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details", 
                        "filename": "O-linked-GLU-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details", 
                        "filename": "O-linked-SER-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details", 
                        "filename": "O-linked-THR-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details", 
                        "filename": "O-linked-TYR-details"
                    }, 
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv", 
                        "filename": "rat_protein_masterlist.csv"
                    }, 
                    {
                        "uri": "http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta", 
                        "filename": "rat_protein_canonicalsequences.fasta"
                    }, 
                    {
                        "uri": "http://data.glygen.org/ln2wwwdata/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv", 
                        "filename": "pdb_chain_uniprot_2018_11_8_11_44_50.csv"
                    }
                ], 
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv", 
                        "filename": "rat_proteoform_glycosylation_sites_pdb.csv"
                    }
                ], 
                "prerequisite": [], 
                "description": "The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."
            }
        ]
    }, 
    "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"
                }
            }
        ]
    }, 
    "usability_domain": [
        "The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:11106] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."
    ], 
    "etag": "613f11f077999a838157860d6208a742", 
    "_id": {
        "$oid": "5d72a02ef5c47b0f43423353"
    }, 
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.7.13/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv", 
                    "filename": "pdb_chain_uniprot_2018_11_8_11_44_50.csv"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.7.13/reviewed/rat_protein_masterlist.csv", 
                    "filename": "rat_protein_masterlist.csv"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/O-linked-TYR-details", 
                    "filename": "O-linked-TYR-details"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/O-linked-ASP-details", 
                    "filename": "O-linked-ASP-details"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/O-linked-GLU-details", 
                    "filename": "O-linked-GLU-details"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2releases/data/v-1.7.13/reviewed/rat_protein_canonicalsequences.fasta", 
                    "filename": "rat_protein_canonicalsequences.fasta"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/O-linked-SER-details", 
                    "filename": "O-linked-SER-details"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/O-linked-THR-details", 
                    "filename": "O-linked-THR-details"
                }
            }, 
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/pdb/download_2018_10_23/N-linked-ARG-details", 
                    "filename": "N-linked-ARG-details"
                }
            }
        ], 
        "output_subdomain": [
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv", 
                    "filename": "rat_proteoform_glycosylation_sites_pdb.csv"
                }
            }, 
            {
                "mediatype": "csv", 
                "uri": {
                    "uri": "http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.stat.csv", 
                    "filename": "rat_proteoform_glycosylation_sites_pdb.stat.csv"
                }
            }
        ]
    }
}
