pKalculator: A pKa predictor for C-H bonds

Determining the pKa values of various C-H sites in organic molecules offers valuable insights for synthetic chemists in predicting reaction sites. As molecular complexity increases, this task becomes more challenging. This paper introduces pKalculator, a quantum chemical (QM)-based workflow for automatic computations of C-H pKa values, which is used to generate a training dataset for a machine learning model (ML). The QM workflow is benchmarked against 695 experimentally determined C-H pKa values. The ML model is trained on a diverse dataset of 775 molecules with 3910 C-H sites. Our ML model predicts C-H pKa values with a mean absolute error (MAE) and a root mean squared error (RMSE) of 1.24 and 2.15 pKa units, respectively. Furthermore, we employ our model on 1043 pKa-dependent reactions (Aldol, Claisen, and Michael) and successfully indicate the reaction sites with a Matthew’s correlation coefficient (MCC) of 0.82.