February 7, 2026Genome biology0 citationsOpen Access
Ver artículo completoUniSyn: a multi-modal framework with knowledge transfer for anti-cancer drug synergy prediction
Puntos clave
- This research aims to enhance drug-synergy prediction using a multi-modal deep learning framework.
- Developed UniSyn, a multi-modal deep learning framework for drug synergy prediction.
- Integrated drug and cell-line features using hybrid attention-based methods.
- Applied the framework to predict synergy across various tumor cell lines.
- UniSyn effectively predicts drug synergy with robust performance across multiple metrics.
- It retains consistent accuracy for unseen drug pairs and cell types.
- The framework highlights context-specific synergy signals for prioritizing therapeutic combinations.
Resumen
Drug combinations can improve cancer therapy by boosting efficacy, limiting dose-related toxicity, and delaying resistance. We present UniSyn, an interpretable multi-modal deep learning framework that transfers knowledge from monotherapy responses to enhance drug-synergy prediction. Through hybrid attention–based integration of drug and cell-line features, UniSyn supports multi-task learning and yields mechanistic insights. It generalizes robustly to unseen drug pairs and cell types, maintaining consistent performance across multiple synergy scoring metrics. Applied at scale to tumor cell lines, UniSyn captures context-specific synergy signals and prioritizes therapeutic combinations with translational potential.