{
    "object_id": "https://biocomputeobject.org/GLY_000458/v-2.7.1",
    "spec_version": "1.3.0",
    "extension_domain": [
        {
            "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/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": "Signal Peptide",
                        "category_name": "tag"
                    },
                    {
                        "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 Protein Signal Peptide",
        "contributors": [
            {
                "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": "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"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Luke Johnson",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "luke.johnson@email.gwu.edu"
            },
            {
                "name": "Urnisha Bhuiyan",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "sbhuiyan28@email.gwu.edu"
            },
            {
                "name": "Cyrus Au-Yeung",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "cyruschauyeung@gwu.edu"
            },
            {
                "name": "Kate Warner",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "k.warner1@gwu.edu"
            }
        ],
        "created": "2020-04-03T15:52:36.427462",
        "modified": "2024-05-17T11:24:01.278Z",
        "version": "v-2.7.1"
    },
    "description_domain": {
        "keywords": [
            "signal peptide",
            "ptm processing",
            "UniProtKB"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"
            }
        ]
    },
    "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/dataset-maker/make-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "usability_domain": [
        "The Rat Protein Signal Peptide dataset contains Rattus norvegicus [taxid:10116] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence\u2019s files in fasta format. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."
    ],
    "etag": "893079ffb545e3f6809428841a5d827d",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "uniprot-proteome-rattus-norvegicus.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2024_09_19/uniprot-proteome-rattus-norvegicus.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-rattus-norvegicus.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2024_09_19/uniprot-proteome-rattus-norvegicus.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-rattus-norvegicus.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2024_09_19/uniprot-proteome-rattus-norvegicus.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-rattus-norvegicus.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2024_09_19/uniprot-proteome-rattus-norvegicus.nt"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_annotation.csv",
                    "filename": "rat_protein_signalp_annotation.csv"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_peptidesequences.fasta",
                    "filename": "rat_protein_signalp_peptidesequences.fasta"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_cleavedsequences.fasta",
                    "filename": "rat_protein_signalp_cleavedsequences.fasta"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_fullsequences.fasta",
                    "filename": "rat_protein_signalp_fullsequences.fasta"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_annotation.stat.csv",
                    "filename": "rat_protein_signalp_annotation.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_peptidesequences.stat.csv",
                    "filename": "rat_protein_signalp_peptidesequences.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_cleavedsequences.stat.csv",
                    "filename": "rat_protein_signalp_cleavedsequences.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/rat_protein_signalp_fullsequences.stat.csv",
                    "filename": "rat_protein_signalp_fullsequences.stat.csv"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    }
}
