Fig. 3
From: DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning
Model performance on external datasets. Correlation plots, Pearson’s r values, MAE, RMSE, and total percent of predictions correctly indicating a positive or negative change from the starting molecule (pie charts) for Random Forest, ChemProp, and DeepDelta models on cross-merged external test sets. Aqueous solubility is in units of logS and volume of distribution at steady state is in units of log(body/blood concentration in L/kg). Coloring is based on data density with the most densely populated regions shown in yellow, medium density shown in green, and least dense regions in blue and linear interpolation between these groups