Supplementary Data for DISCAN

<p>Supplementary data for &quot;The frequency of somatic mutations in cancer predicts the phenotypic relevance of germline mutations&quot;. This entry includes two data tables, uploaded as compressed text files:</p> <ul> <li><strong>features.csv.gz</strong> contains all the covariates used to train the models.&nbsp;</li> <li><strong>phenotype_probabilities.csv.gz</strong> contains the Random Forest probabilities for 1,361 phenotypes</li> </ul> <p>Gene identifiers are reported as Entrez ID.</p>