Summary


The ability to predict the propensity of a molecule to lose or gain a proton in water is crucial for the development of new chemical entities with desirable pharmacokinetic (PK), absorption, distribution, metabolism and excretion (ADME) and binding properties. This study aimed to create a model using a semi-empirical quantum mechanics (QM) approach combined with machine learning (ML).The resultant model displayed excellent accuracy, comparable to other much more computationally intensive methods.

The results of a QMML approach to predict pKa  of different compounds is shown, with predictions compared to observed pka.

Citation details


P. Hunt, L. Hosseini-Gerami, T. Chrien, J. Plante, D. J. Ponting, M. Segall, J.Chem. Inf. Model., 2020, 60(6) pp2989-2997. DOI: 10.1021/acs.jcim.0c00105

Find out more about predicting pKa

Watch our webinar for an overview on how to predict pKa in StarDrop.

More predictive modelling resources