Controllable Edge-Type-Specific Interpretation in Multi-Relational Graph Neural Networks for Drug Response Prediction

TL;DR

This paper introduces CETExplainer, a novel interpretability algorithm for cancer drug response prediction using multi-relational graph neural networks, emphasizing biological relevance and controllable edge-type-specific explanations.

Contribution

The paper presents CETExplainer, a post-hoc interpretability method with a controllable edge-type weighting mechanism tailored for biological insights in drug response prediction.

Findings

CETExplainer outperforms existing algorithms in explanation stability.

It provides biologically meaningful, fine-grained explanations.

Empirical results demonstrate improved explanation quality.

Abstract

Graph Neural Networks have been widely applied in critical decision-making areas that demand interpretable predictions, leading to the flourishing development of interpretability algorithms. However, current graph interpretability algorithms tend to emphasize generality and often overlook biological significance, thereby limiting their applicability in predicting cancer drug responses. In this paper, we propose a novel post-hoc interpretability algorithm for cancer drug response prediction, CETExplainer, which incorporates a controllable edge-type-specific weighting mechanism. It considers the mutual information between subgraphs and predictions, proposing a structural scoring approach to provide fine-grained, biologically meaningful explanations for predictive models. We also introduce a method for constructing ground truth based on real-world datasets to quantitatively evaluate the proposed interpretability algorithm. Empirical analysis on the real-world dataset demonstrates that CETExplainer achieves superior stability and improves explanation quality compared to leading algorithms, thereby offering a robust and insightful tool for cancer drug prediction.