Interpretable High-order Knowledge Graph Neural Network for Predicting Synthetic Lethality in Human Cancers
This work addresses the need for interpretable and trustworthy predictions in cancer research, though it is incremental by building on existing graph neural network methods.
The paper tackled the problem of generating faithful and diverse explanations for synthetic lethality predictions in cancer therapy by proposing a knowledge graph neural network that integrates a novel objective and motif-based structures, achieving state-of-the-art performance and providing multiple explanations for gene pairs.
Synthetic lethality (SL) is a promising gene interaction for cancer therapy. Recent SL prediction methods integrate knowledge graphs (KGs) into graph neural networks (GNNs) and employ attention mechanisms to extract local subgraphs as explanations for target gene pairs. However, attention mechanisms often lack fidelity, typically generate a single explanation per gene pair, and fail to ensure trustworthy high-order structures in their explanations. To overcome these limitations, we propose Diverse Graph Information Bottleneck for Synthetic Lethality (DGIB4SL), a KG-based GNN that generates multiple faithful explanations for the same gene pair and effectively encodes high-order structures. Specifically, we introduce a novel DGIB objective, integrating a Determinant Point Process (DPP) constraint into the standard IB objective, and employ 13 motif-based adjacency matrices to capture high-order structures in gene representations. Experimental results show that DGIB4SL outperforms state-of-the-art baselines and provides multiple explanations for SL prediction, revealing diverse biological mechanisms underlying SL inference.