In a unique collaboration between a software company and a pharmaceutical company, we were able to develop a new in silico pK_a prediction tool with outstanding prediction quality. An existing pK_a prediction method from Simulations Plus based on artificial neural network ensembles (ANNE), microstates analysis, and literature data was retrained with a large homogeneous data set of drug-like molecules from Bayer. The new model was thus built with curated sets of ∼14,000 literature pK_a values (∼11,000 compounds, representing literature chemical space) and ∼19,500 pK_a values experimentally determined at Bayer Pharma (∼16,000 compounds, representing industry chemical space). Model validation was performed with several test sets consisting of a total of ∼31,000 new pK_a values measured at Bayer. For the largest and most difficult test set with >16,000 pK_a values that were not used for training, the original model achieved a mean absolute error (MAE) of 0.72, root-mean-square error (RMSE) of 0.94, and squared correlation coefficient (R²) of 0.87. The new model achieves significantly improved prediction statistics, with MAE = 0.50, RMSE = 0.67, and R² = 0.93. It is commercially available as part of the Simulations Plus ADMET Predictor release 7.0. Good predictions are only of value when delivered effectively to those who can use them. The new pK_a prediction model has been integrated into Pipeline Pilot and the PharmacophorInformatics (PIx) platform used by scientists at Bayer Pharma. Different output formats allow customized application by medicinal chemists, physical chemists, and computational chemists.

By Robert Fraczkiewicz & Robert D Clark