CimpleG DNAm benchmarking datasets for cell-type classification and deconvolution

<p><strong>Two large DNAm benchmarking datasets</strong> specifically gathered and <strong>curated for cell-type classification and deconvolution problems.</strong></p> <p>It includes <strong>a leukocytes dataset</strong> and <strong>a somatic cells dataset</strong> in the GenomicRatioSet format from the minfi package.</p> <p>These can be easily <strong>loaded into R with the readRDS function:</strong></p> <blockquote> <p>my_data &lt;- readRDS("CimpleG_benchmarking_datasets_2/leukocytes/tidy_leuk_data.rds")</p> </blockquote> <p>Each dataset includes therein sample data like GEO accession numbers, sample name or ID in their original dataset, cell-type label, one-hot encoded data for each cell-type, preferred train/test splits, and others.</p> <p>Alternatively, <strong>you can also load the individual .csv files</strong>. If you choose this option, I recommend using the function fread from the package data.table.&nbsp;Below I briefly describe these (.csv and .txt) files for the leukocytes dataset, the same logic applies to the somatic cells dataset:</p> <ul> <li> <div> <div>tidy_leuk_data_beta-values.csv</div> <div> <ul> <li>Methylation Beta values matrix</li> </ul> </div> </div> </li> <li> <div> <div> <div>tidy_leuk_data_m-values.csv</div> <div> <ul> <li>Methylation M values matrix</li> </ul> </div> </div> </div> </li> <li> <div> <div> <div>tidy_leuk_data_probe-annotation.txt</div> <div> <ul> <li>Note regarding probe annotation</li> </ul> </div> </div> </div> </li> <li> <div> <div> <div>tidy_leuk_data_probe-metadata.csv</div> <div> <ul> <li>Probe metadata matrix (chr and location)</li> </ul> </div> </div> </div> </li> <li> <div> <div> <div>tidy_leuk_data_sample-metadata.csv</div> <div> <ul> <li>Sample metadata matrix (sample ID, cell type labels, one-hot encoded labels, etc.)</li> </ul> </div> </div> </div> </li> </ul>