{
    "object_id": "https://biocomputeobject.org/GLY_000121/v-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": "Homo sapiens",
                        "category_name": "species"
                    },
                    {
                        "category_value": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "Pfam cross-references",
                        "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": "Human UniProtKB Xref Pfam",
        "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": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Xavier Holmes",
                "email": "xavierh@email.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"
            }
        ],
        "created": "2019-03-15T15:58:30.083377",
        "modified": "2020-04-10T11:39:12.484631",
        "version": "v-1.7.13"
    },
    "description_domain": {
        "keywords": [
            "protein family",
            "Pfam",
            "cross-reference"
        ],
        "pipeline_steps": [
            {
                "name": "make-protein-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_masterlist.csv",
                        "filename": "human_protein_masterlist.csv"
                    },
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.7.13/source/uniprot-proteome-homo-sapiens.nt",
                        "filename": "uniprot-proteome-homo-sapiens.nt"
                    }
                ],
                "output_list": [
                    {
                        "uri": "https://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_xref_pfam.csv",
                        "filename": "human_protein_xref_pfam.csv"
                    }
                ],
                "prerequisite": [],
                "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"
            }
        ]
    },
    "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-protein-dataset.py",
                    "filename": "make-protein-dataset.py"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {},
        "emperical_error": {}
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The Human UniProtKB Xref Pfam contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen",
        "Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."
    ],
    "etag": "2803051e3a98df541bedc317062b840a",
    "_id": {
        "$oid": "5c8c03e6f5c47b59903c90e1"
    },
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "uri": "https://data.glygen.org//ln2downloads/ebi/2020_05/uniprot-proteome-homo-sapiens.nt",
                    "filename": "uniprot-proteome-homo-sapiens.nt"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_xref_pfam.csv",
                    "filename": "human_protein_xref_pfam.csv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "http://data.glygen.org/ln2data/releases/data/v-1.7.13/reviewed/human_protein_xref_pfam.stat.csv",
                    "filename": "human_protein_xref_pfam.stat.csv"
                }
            }
        ]
    }
}