Testing the new tool PrediXcan on the DILGOM cohort. PrediXcan was used to impute gene expression from the DILGOM genotype data using models trained on the DGN and GTEx cohorts. We then compared the
Source data of all figures and tables in the article "A genome-scale deep learning model to predict gene expression changes of genetic perturbations from multiplex biological networks"
Shown is the average Spearman correlation coefficient between model-predicted score and observed log2 fold change, averaged across five cross-validation runs. The specified p-value is the upper bound