Investigating Chemical Interpretability in Graph Neural Networks via Atom-wise Shapley Additive Explanations
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The rapid advancement of machine learning (ML) has revolutionized molecular property predictions with achieving remarkable accuracy. However, their black-box nature limits interpretability, making it challenging for chemists to extract scientific insights and validate predictions against established chemical principles. To address this, Shapley Additive Explanations (SHAP) have been widely adopted, yet their application to graph neural networks (GNNs) remains challenging. Here, we develop a modified SHAP strategy to extract atom-wise contribution values from GNN predictions. We apply this approach to GNN models predicting fuel reactivity (cetane number) and Gibbs free energy of solvation. Our method provides chemically meaningful interpretations, aligning SHAP-derived descriptors with known chemical knowledge, including fuel's reactivity and solvation effects. The results demonstrate that atom-wise SHAP explanations offer valuable insights into molecular properties without requiring expensive quantum-mechanical calculations, enhancing the interpretability of ML-driven chemical predictions.
Abstract
The rapid advancement of machine learning (ML) has revolutionized molecular property predictions with achieving remarkable accuracy. However, their black-box nature limits interpretability, making it challenging for chemists to extract scientific insights and validate predictions against established chemical principles. To address this, Shapley Additive Explanations (SHAP) have been widely adopted, yet their application to graph neural networks (GNNs) remains challenging. Here, we develop a modified SHAP strategy to extract atom-wise contribution values from GNN predictions. We apply this approach to GNN models predicting fuel reactivity (cetane number) and Gibbs free energy of solvation. Our method provides chemically meaningful interpretations, aligning SHAP-derived descriptors with known chemical knowledge, including fuel's reactivity and solvation effects. The results demonstrate that atom-wise SHAP explanations offer valuable insights into molecular properties without requiring expensive quantum-mechanical calculations, enhancing the interpretability of ML-driven chemical predictions.