Fig. 12

Analysis of the assignment correctness for models trained on human data: a NaïveBayes, b SVM, c trees, d NaïveBayes, e SVM, f trees. Class 0—unstable compounds, class 1—compounds of middle stability, class 2—stable compounds. The figure presents the distribution of probabilities of compound assignment to particular stability class, depending on the true class value for test sets derived from the human dataset. Each dot represent a single molecule, the position on x-axis indicates the correct class, the position on y-axis the probability of this class returned by the model, and the colour the class assignment based on model’s prediction