Figure 3

Variability of calculated uncertainty profiles. Model logP2-2 uses three hidden neurons and 45 descriptors as input. The voting threshold (indicated by the vertical black dotted line) was 16.5. The horizontal dotted lines running across the thresholds indicate where an error rate of 0.5 would fall. (A) Distribution of predictions (blue) and errors (red) for the external validation set. Dashed lines represent the fitted beta binomial distributions for the corresponding training pool results. (B) Observed (red symbols) error rate profile for the validation set and uncertainty profile (dashed black curve) calculated from the prediction and error distributions fitted to the training pool.