MVCASyn: Predicting Synergistic Drug Combinations Based on Multi-View Learning and Cross-Attention Mechanism

The increase in cancer drug resistance poses a huge challenge to effective therapeutic intervention. Combination therapy has emerged as an effective method to combat this resistance, but traditional methods for identifying viable drug combinations are often cumbersome and resource-intensive. Recently, computational models have been developed to simplify the prediction of viable drug combinations, thereby improving the efficiency of this field. However, many existing models treat drug combinations as operating independently, ignoring the crucial interaction dynamics between them. Moreover, these models fail to exploit the complementary insights provided by cell line multi-omics data. In this work, we propose MVCASyn, an innovative deep learning framework that predicts synergistic drug combinations. Compared with existing models, MVCASyn combines a dual-view representation learning module to effectively extract multi-level features of atomic interactions and adopts a cross-attention mechanism to fuse cell line multi-omics data. Our experimental results show that MVCASyn consistently outperforms current advanced models across all evaluation metrics. Visualization experiments of drug atomic importance scores further emphasize the ability of MVCASyn to identify key drug substructures. Case study experiments also confirm that MVCASyn is effective in practical applications.