Extending pK(a) prediction accuracy: High-throughput pK(a) measurements to understand pK(a) modulation of new chemical series

We have recently developed a tool, MoKa, to predict the pKa of organic compounds using a large dataset of over 26,500 literature pKa values as a training set. However, predicting accurately pKa (<0.5 pH units) remains challenging for novel series, and this can be a drawback in the optimization of activity and ADME properties of lead compounds. To address this issue it is important to expand our knowledge of pKa determinants, therefore we have conducted high-throughput pKa measurements by using Spectral Gradient Analysis (SGA) on novel series of compounds selected from vendor databases. Here we report our findings on the effect of specific chemical groups and steric constraints on the pKa of common functionalities in medicinal chemistry, such as amines, sulfonamides, and amides. Furthermore, we report the pKa of ionizable groups that were not well represented in the database of literature pKa of MoKα, such as hydrazide derivatives. These findings helped us to enhance MoKα, which is here benchmarked on a set of experimental pKa values from the Roche in-house library (N = 5581; RMSE = 1.09; R2 = 0.82). The accuracy of the predictions was greatly improved (RMSE = 0.49, R2 = 0.96) after training the software by using the automated tool Kibitzer with 6226 pK a values taken from a different set of Roche compounds appropriately selected, and this demonstrates the value of using high-throughput pK a measurements to expand the training set of pKa values used by the software MoKα.