Search papers, labs, and topics across Lattice.
This study introduces VINCENT, a post-training framework designed to enhance the interpretability of drug synergy predictions by identifying chemically coherent motif pairs that contribute to synergy. By employing a closed-loop validation approach, VINCENT ensures that the extracted explanations are stable under perturbations and aligned with the predictor's behavior, achieving a mean motif recall of 0.826 compared to 0.49-0.66 for existing models. The findings underscore the importance of validated explanations in drug combination discovery, offering a more reliable method for understanding the molecular interactions that drive therapeutic synergy.
VINCENT achieves a remarkable mean motif recall of 0.826, significantly outperforming existing models in identifying key molecular regions driving drug synergy.
Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers also need to know which molecular regions jointly drive the prediction. We study motif-pair synergy explanation, which identifies pairs of chemically coherent regions, one from each drug, that jointly contribute to predicted synergy. Existing interpretable synergy models expose atom- or substructure-level signals, but their explanations are built into the predictor architecture, and none validates cross-drug region scores under repeated perturbations or feeds that evidence back to refine the explanation. A reliable motif-pair explanation should instead be chemically coherent, perturbation-stable, and aligned with predictor behavior. We introduce VINCENT (Validated Interaction Network for Cross-drug Explanation of Therapeutics), a post-training framework for a fixed interaction-aware synergy predictor. VINCENT extracts atom-pair evidence from attention and gradient signals, groups atoms into chemically coherent motifs, and validates candidate motif pairs through repeated local perturbations. The validated evidence is fed back to refine motif assignments, yielding explanations that satisfy these three criteria. On a 25-pair literature-annotated subset, VINCENT achieves a mean motif recall of 0.826 (95% CI: 0.78-0.87), compared with 0.49-0.66 for baselines. Across all 71 test pairs, its validated interaction scores yield a TP/TN separation of 3.36. These results show that closed-loop perturbation validation recovers literature-supported molecular regions more accurately than existing alternatives while producing cross-drug interaction scores that better reflect predictor behavior.
