pKalculator: A pK _a predictor for C-H bonds

Determining the pK _a 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 chemistry (QM)-based workflow for automatic computations of C-H pK _a values, which is used to generate a training dataset for a machine learning (ML) model. The QM workflow is benchmarked against 695 experimentally determined C-H pK _a values in DMSO. The ML model is trained on a diverse dataset of 775 molecules with 3910 C-H sites. Our ML model predicts C-H pK _a values with a mean absolute error (MAE) and a root mean squared error (RMSE) of 1.24 and 2.15 pK _a units, respectively. Furthermore, we employ our model on 1043 pK _a-dependent reactions (aldol, Claisen, and Michael) and successfully indicate the reaction sites with a Matthew's correlation coefficient (MCC) of 0.82.