MADSP: predicting anti-cancer drug synergy through multi-source integration and attention-based representation learning.

Abstract

Drug combination therapy is an effective strategy for cancer treatment, enhancing drug efficacy and reducing toxic side effects. However, in vitro drug screening experiments are time-consuming and expensive, necessitating the development of computational methods for drug synergy prediction. While current methods focus on molecular chemical structures, they often overlook the biological context, limiting their ability to capture complex drug synergies. In this work, we propose MADSP, a novel method for anti-cancer drug synergy prediction that integrates target and pathway knowledge for a more comprehensive understanding of systems biology. MADSP first incorporates chemical structure, target, and pathway features of drugs, using a multi-head self-attention mechanism to learn a unified drug representation. It then integrates protein-protein interaction data with omics data from cell lines, extracting a low-dimensional dense embedding of cell lines via an autoencoder. Finally, the synergy scores for drug combinations are predicted using a fully connected neural network. Experiments on benchmark datasets demonstrate that MADSP outperforms state-of-the-art methods. The ablation study reveals that multi-source information fusion and attention mechanisms significantly enhance model performance. The case study further illustrates the practical applicability of MADSP as a powerful tool for drug synergy prediction, offering potential for advancing cancer treatment strategies. MADSP is available at https://github.com/Hhyqi/MADSP.