The recent progress of deep-learning-based in silico prediction of drug combination

•In silico prediction of drug combination has become indispensable due to the expensive cost of experiments.•Deep learning architectures used for drug combination prediction are comprehensively reviewed.•The advantages and challenges of deep learning based methods for drug combination prediction are discussed. Drug combination therapy has become a common strategy for the treatment of complex diseases. There is an urgent need for computational methods to efficiently identify appropriate drug combinations owing to the high cost of experimental screening. In recent years, deep learning has been widely used in the field of drug discovery. Here, we provide a comprehensive review on deep-learning-based drug combination prediction algorithms from multiple aspects. Current studies highlight the flexibility of this technology in integrating multimodal data and the ability to achieve state-of-art performance; it is expected that deep-learning-based prediction of drug combinations should play an important part in future drug discovery.