Interpretable attribution assignment for octanol-water partition coefficient

With the increasing development of machine learning models, their credibility has become an important issue. In chemistry, attribution assignment is gaining relevance in designing molecules and debugging models. However, attention has been paid to which atoms are important in the prediction without considering whether the attribution is reasonable. In this study, we developed a graph neural network model, a high interpretable attribution model in chemistry, and modified the integrated gradients method. The credibility of our approach was confirmed by predicting the octanol--water partition coefficient (logP) and evaluating the three metrics --accuracy, consistency, and stability-- in the attribution assignment.