A Gated Recurrent Unit Model for Drug Repositioning by Combining Comprehensive Similarity Measures and Gaussian Interaction Profile Kernel

摘要

Drug repositioning can find new uses for existing drugs and accelerate the processing of new drugs research and developments. It is noteworthy that the number of successful drug repositioning stories is increasing rapidly. Various computational methods have been presented to predict novel drug-disease associations for drug repositioning based on similarity measures among drugs and diseases or heterogeneous networks. However, there are some known associations between drugs and diseases that previous studies not utilized. In this work, we proposed a GRU model to predict potential drug-disease interactions by using comprehensive similarity. 10-fold cross-validation and common evaluation indicators are used to evaluate the performance of our model. Our model outperformed existing methods. The experimental results proved our model is a useful tool for drug repositioning and biochemical medicine research.