Figure 2
From: New machine learning and physics-based scoring functions for drug discovery
Correlation plot of the experimental and predicted binding affinities by the MLR (left) and RF (right) general scoring functions. Models trained on the PDBbind v2013 refined set (N = 2764) and evaluated on curated v2013 core set (N = 195). R is the Pearson’s correlation coefficient and RMSE is the root mean squared error given in kcal mol−1.
