Holistic Prediction of the pK_a in Diverse Solvents Based on a Machine-Learning Approach

While many approaches to predict aqueous pK_a values exist, the fast and accurate prediction of non-aqueous pK_a values is still challenging. Based on the iBonD experimental pK_a database (39 solvents), a holistic pK_a prediction model was established using machine learning. Structural and physical-organic-parameter-based descriptors (SPOC) were introduced to represent the electronic and structural features of the molecules. The models trained with a neural network or the XGBoost algorithm showed the best prediction performance with a low MAE value of 0.87 pK_a units. The approach allows a comprehensive mapping of all possible pK_a correlations between different solvents and it was validated by predicting the aqueous pK_a and micro-pK_a of pharmaceutical molecules and pK_a values of organocatalysts in DMSO and MeCN with high accuracy. An online prediction platform was constructed based on the current model, which can provide pK_a prediction for different types of X-H acidity in the most commonly used solvents.