Allows to visualize and analyze if the molecules of the test set and of an external set are contained in the convex hull defined by the molecules of the training set. The code generate a scatter plot and text file with molecules inside of the applicability domain.
The applicability domain is important to limit the region in which the model is applicable to make predictions for new compounds. In convex hull the Interpolation space is defined by the smallest convex area containing the entire training set.