A Perspective on Explanations of Molecular Prediction Models

Chemists can be skeptical in using deep learning (DL) in decision making, due to the lack of interpretability in "black-box" models. Explainable artificial intelligence (XAI) is a branch of AI which addresses this drawback by providing tools to interpret DL models and their predictions. We review the principles of XAI in the domain of chemistry and emerging methods for creating and evaluating explanations. Then we focus methods developed by our group and their application to predicting solubility, blood-brain barrier permeability, and the scent of molecules. We show that XAI methods like chemical counterfactuals and descriptor explanations can both explain DL predictions and give insight into structure-property relationships. Finally, we discuss how a two step process of highly accurate black-box modeling and then creating explanations gives both highly accurate predictions and clear structure-property relationships.