GNNSynergy: A Multi-View Graph Neural Network for Predicting Anti-Cancer Drug Synergy

Drug combinations play very important roles in cancer therapy, as they can enhance curative efficacy and overcome drug resistance. Due to the increasing size of combinatorial space, experimental screening for all the drug combinations becomes infeasible in practice. Therefore, there is a great need to develop accurate computational approaches that can predict potential drug combinations to direct the experimental screening. In this paper, we propose a novel method called GNNSynergy to learn drug embeddings for drug synergy prediction. Given a specific cancer cell line, we propose a multi-view graph neural network framework which considers the current cell line as main view while other cell lines from the same tissue as sub-views. In each view, we first construct different graphs to describe drug synergistic and antagonistic interactions, and adopt graph neural network as encoder to learn drug embeddings. We further combine both the main view and sub-views via an attention mechanism to derive the final drug embeddings for drug synergy prediction. We perform extensive experiments on DrugComb database and the experimental results demonstrate that our proposed GNNSynergy significantly outperforms state-of-the-art methods for novel synergistic drug combination prediction.