Synergistic drug combinations play an important role in the treatment of complex diseases.
The identification of effective drug combination is vital to further reduce the side effects and improve
therapeutic efficiency. In previous years, in vitro method has been the main route to discover synergistic
drug combinations. However, many limitations of time and resource consumption lie within the in
vitro method. Therefore, with the rapid development of computational models and the explosive growth
of large and phenotypic data, computational methods for discovering synergistic drug combinations are
an efficient and promising tool and contribute to precision medicine. It is the key of computational
methods how to construct the computational model. Different computational strategies generate different
performance. In this review, the recent advancements in computational methods for predicting effective
drug combination are concluded from multiple aspects. First, various datasets utilized to discover
synergistic drug combinations are summarized. Second, we discussed feature-based approaches and
partitioned these methods into two classes including feature-based methods in terms of similarity measure,
and feature-based methods in terms of machine learning. Third, we discussed network-based approaches
for uncovering synergistic drug combinations. Finally, we analyzed and prospected computational
methods for predicting effective drug combinations.