BioSchemas – Dataset json

{
    "@context": "http://schema.org",
    "@type": "Dataset",
    "version": "YYYYMMDD",
    "name": "SweGen Variant Frequency Dataset",
    "description": "This dataset contains whole-genome variant frequencies for 1000 Swedish individuals generated within the SweGen project. The frequency data is intended to be used as a resource for the research community and clinical genetics laboratories. Please note that the 1000 individuals included in the SweGen project represent a cross-section of the Swedish population and that no disease information has been used for the selection. The frequency data may therefore include genetic variants that are associated with, or causative of, disease.",
    "url": "https://swefreq.nbis.se/dataset/SweGen/YYYYMMDD",
    "identifier": "SweGen",
    "sameAs": "http://doi.org/10.17044/NBIS/G000003", // dataset_version: ref_doi, om specificerat
    "keywords": [ // t.ex. sample_set: ethnicity, collection, phenotype; dataset: seq_type & seq_tech
        "genome variation", "WGS", "Illumina HiSeq X", "Swedish Twin Registry", "Sweden"
    ],
    "includedinDataCatalog": {
        "@type": "DataCatalog",
        "name": "SweFreq",
        "url": "https://swefreq.nbis.se/"
    },  
    "creator": [ // Vi har inte alla namn, så får nöja oss med PI
        {
             "@type": "Person",
             "name": "Ulf Gyllenstén", //study: pi_name
             "email": "[email protected]" //study: pi_email
        }
    ],
    "license": "https://swefreq.nbis.se/dataset/SweGen/version/YYYYMMDD/terms", // dataset_version: terms
    "measurementTechnique": "Illumina HiSeq X", //dataset: seq_tech,
    "datePublished": "YYYY-MM-DD",
    "fileFormat":"vcf",
    "publication": { 
        "@type": "PublicationEvent",
        "@id": "https://dx.doi.org/10.1038/ejhg.2017.130" // Hmmm, det här kanske är den enda info vi har för   
    }
}