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 when it comes to designing molecules
and debugging models. However, attention has only been paid to which
atoms are important in the prediction and not to whether the attribution
is reasonable. In this study, we developed a graph neural network
model, a highly 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.

随着机器学习模型的不断发展，其可信度已成为一项重要研究议题。在化学领域，开展分子设计与模型调试工作时，归因赋值（attribution assignment）的重要性日益凸显。然而过往研究仅聚焦于预测任务中哪些原子具备重要性，却未对归因结果的合理性进行验证。本研究构建了一款面向化学领域的高可解释性归因模型——图神经网络（Graph Neural Network），并对集成梯度（Integrated Gradients）方法进行了改进。我们通过预测正辛醇-水分配系数（logP），并针对归因赋值任务的三项评估指标——准确性、一致性与稳定性——开展评测，验证了所提方法的可信度。