Xinsheng Li, Daichuan Ma*, Yan Ren, Jiesi Luo and Yizhou Li
Background: The prediction of drug-protein interaction (DPI) plays an important role in drug discovery and re-positioning. Unfortunately, traditional experimental validation of DPIs is expensive and time-consuming. Therefore, it is necessary to develop in silico methods for the identification of potential DPIs.
Method: In this work, the identification of DPIs was performed by the generated recommendation of the unexplored interaction of the drug-protein bipartite graph. Three kinds of recommenders were proposed to predict the potential DPIs.
Results: The simulation results showed that the proposed models obtained good performance in cross validation and independent test.
Conclusion: Our recommendation strategy based on collaborative filtering can effectively improve the DPI identification performance, especially for certain DPIs lacking chemical structure similarity or genomic sequence similarity.
drug discovery, recommender system, bipartite graph, drug-protein interaction, collaborative filtering, Jaccard index
College of Computer Science, Sichuan University, No.24 South Section 1, Yihuan Road, Wuhou District, Chengdu, Sichuan 610065, Analytical & Testing Center, Sichuan University, No.29 Wangjiang Road, Wuhou District, Chengdu, Sichuan 610064, College of Cybersecurity, Sichuan University, Chengdu, National Clinical Research Center for Geriatrics, West China Hospital, Sichuan University, Chengdu, College of Cybersecurity, Sichuan University, No.29 Wangjiang Road, Wuhou District, Chengdu, Sichuan 610064