A Case-Based Explainable Graph Neural Network Framework for Mechanistic Drug Repositioning

Drug repositioning offers a cost-effective alternative to traditional drug development by identifying new uses for existing drugs. Recent advances leverage Graph Neural Networks (GNN) to model complex biological data, showing promise in predicting novel drug-disease associations. However, these frameworks often lack explainability, a critical factor for validating predictions and understanding drug mechanisms. Here, we introduce Drug-Based Reasoning Explainer (DBR-X), an explainable GNN model that combines a link prediction module and a path-identification module to generate interpretable and faithful explanations. When benchmarked against other GNN link prediction frameworks, DBR-X achieves superior performance in identifying known drug-disease associations, demonstrating higher accuracy across all evaluation metrics. The quality of DBR-X biological explanations was assessed through multiple approaches: comparison with manually-curated drug mechanisms, evaluation of explanation faithfulness through deletion and insertion studies, and measurement of stability under graph perturbations. Together, our model not only advances the state-of-the-art in drug repositioning predictions but also provides multi-hop explanations that can accelerate the translation of computational predictions into clinical applications.