Disentangling Causal Substructures for Interpretable and Generalizable Drug Synergy Prediction
This addresses the need for interpretable and generalizable models in drug discovery for complex diseases like cancer, though it appears incremental by building on existing causal methods.
The paper tackled the problem of drug synergy prediction by proposing CausalDDS, a framework that disentangles causal and spurious substructures in drug molecules, resulting in improved accuracy and interpretability, with experiments showing it outperforms baselines in cold start and out-of-distribution settings.
Drug synergy prediction is a critical task in the development of effective combination therapies for complex diseases, including cancer. Although existing methods have shown promising results, they often operate as black-box predictors that rely predominantly on statistical correlations between drug characteristics and results. To address this limitation, we propose CausalDDS, a novel framework that disentangles drug molecules into causal and spurious substructures, utilizing the causal substructure representations for predicting drug synergy. By focusing on causal sub-structures, CausalDDS effectively mitigates the impact of redundant features introduced by spurious substructures, enhancing the accuracy and interpretability of the model. In addition, CausalDDS employs a conditional intervention mechanism, where interventions are conditioned on paired molecular structures, and introduces a novel optimization objective guided by the principles of sufficiency and independence. Extensive experiments demonstrate that our method outperforms baseline models, particularly in cold start and out-of-distribution settings. Besides, CausalDDS effectively identifies key substructures underlying drug synergy, providing clear insights into how drug combinations work at the molecular level. These results underscore the potential of CausalDDS as a practical tool for predicting drug synergy and facilitating drug discovery.