{
    "object_id": "https://biocomputeobject.org/GLY_000858/v-2.12.1",
    "etag": "dd4df5e70d966a0fa9eab64a5dcd913f",
    "spec_version": "1.3.0",
    "provenance_domain": {
        "name": "Dicty Protein Signal Peptide",
        "version": "v-2.12.1",
        "license": "https://creativecommons.org/licenses/by/4.0/",
        "created": "",
        "modified": "2024-05-17T11:24:15.978Z",
        "derived_from": [],
        "contributors": [
            {
                "name": "Jeet Vora",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jeetvora@gwu.edu"
            },
            {
                "name": "Karina Martinez",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Robel Kahsay",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "rykahsay@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"
            }
        ],
        "review": []
    },
    "usability_domain": [
        "The Dicty Protein Signal Peptide dataset contains Dictyostelium discoideum [taxid:44689] 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 processed protein sequence files in fasta format viz. signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."
    ],
    "extension_domain": [
        {
            "dataset_extension": {
                "dataset_categories": [
                    {
                        "category_value": "Dictyostelium discoideum",
                        "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"
                    },
                    {
                        "category_name": "file_category",
                        "category_value": "annotation"
                    },
                    {
                        "category_name": "file_category",
                        "category_value": "sequence"
                    },
                    {
                        "category_name": "file_category",
                        "category_value": "sequence"
                    },
                    {
                        "category_name": "file_category",
                        "category_value": "sequence"
                    }
                ],
                "additional_license": {
                    "data_license": "https://creativecommons.org/licenses/by/4.0/",
                    "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html"
                }
            },
            "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json"
        }
    ],
    "description_domain": {
        "keywords": [
            "signal peptide",
            "ptm processing",
            "UniProtKB"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "version": "",
                "step_number": 1,
                "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"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "io_domain": {
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_annotation.csv",
                    "filename": "dicty_protein_signalp_annotation.csv"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "filename": "dicty_protein_signalp_cleavedsequences.fasta",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_cleavedsequences.fasta"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "filename": "dicty_protein_signalp_fullsequences.fasta",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_fullsequences.fasta"
                }
            },
            {
                "mediatype": "fasta",
                "uri": {
                    "filename": "dicty_protein_signalp_peptidesequences.fasta",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_peptidesequences.fasta"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_annotation.stat.csv",
                    "filename": "dicty_protein_signalp_annotation.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_cleavedsequences.stat.csv",
                    "filename": "dicty_protein_signalp_cleavedsequences.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_fullsequences.stat.csv",
                    "filename": "dicty_protein_signalp_fullsequences.stat.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.12.1/reviewed/dicty_protein_signalp_peptidesequences.stat.csv",
                    "filename": "dicty_protein_signalp_peptidesequences.stat.csv"
                }
            }
        ],
        "input_subdomain": [
            {
                "uri": {
                    "filename": "uniprot-proteome-dictyostelium-discoideum.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2026_06_13/uniprot-proteome-dictyostelium-discoideum.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-dictyostelium-discoideum.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2026_06_13/uniprot-proteome-dictyostelium-discoideum.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-dictyostelium-discoideum.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2026_06_13/uniprot-proteome-dictyostelium-discoideum.nt"
                }
            },
            {
                "uri": {
                    "filename": "uniprot-proteome-dictyostelium-discoideum.nt",
                    "uri": "https:/data.glygen.org/ln2downloads/ebi/2026_06_13/uniprot-proteome-dictyostelium-discoideum.nt"
                }
            }
        ]
    }
}
