Allows users to predict potential miRNA-disease associations. SDMMDA combines known associations, disease semantic similarity, miRNA functional similarity, and Gaussian interaction profile kernel similarity for diseases and miRNAs. It also can be used for detecting new diseases without any known associated miRNAs or new miRNAs without any known associated diseases. It obtained areas under the curves (AUCs) of 0.9032, 0.8323, 8970 based on leave-one-out cross validation and local leave-one-out cross validation, and 5-fold cross validation.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China; School of Electronics and Information Engineering, Tongji University, Shanghai, China; School of Mathematics, Liaoning University, Shenyang, China; Research Center for Computer Simulating and Information Processing of Bio-Macromolecules of Liaoning Province, Shenyang, China; Academy of Mathematics and Systems Science,Chinese Academy of Sciences, Beijing, China; Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Science, Urümqi, China
SDMMDA funding source(s)
Supported by National Natural Science Foundation of China (Grant No. 11631014); National Natural Science Foundation of China (Grant No. 61133010, 61520106006, 31571364, 61532008, and 61572364); Innovation Team Project from the 50 Education Department of Liaoning Province (Grant No.LT2015011); National Natural Science Foundation of China (Grant No. 11371355 and 11631014); National Natural Science Foundation of China (Grant No. 61572506); Pioneer Hundred Talents 55 Program of Chinese Academy of Sciences.