DNRLMF-MDA:Predicting microRNA-disease associations based on similarities of microRNAs and diseases. Discovering miRNA-disease associations is beneficial to understanding disease mechanisms, developing drugs, and treating complex diseases. We all know that discovering the miRNA-disease associations via biological experiments is a time-consuming and expensive process. Alternatively, computational models could provide a low-cost and high-efficiency way for predicting miRNA-disease associations. In this study, we propose a method (called DNRLMF-MDA) to predict miRNA-disease associations. DNRLMF-MDA integrates known miRNA-disease associations, functional similarity and GIP kernel similarity of miRNAs, and functional similarity and GIP kernel similarity of diseases. DNRLMF-MDA models the association probability for each miRNA-disease pair by logistic matrix factorization. Positive observations are assigned higher importance levels than negative observations. Furthermore, DNRLMF-MDA further improves the prediction performance by dynamic neighborhood regularized. Through 5-fold cross validation and predicting potential diseases for new miRNAs on three datasets, the performance of DNRLMF-MDA usually outperformed other three methods in terms of the area under ROC curve (AUC). DNRLMF-MDA can predict potential diseases for new miRNAs and the computation time are shorter than PBMDAs computation time on three datasets .In addition, case studies further illustrate the practical ability of DNRLMF-MDA. It provides the basis for understanding disease mechanisms, developing drugs, and treating complex diseases.
Keywords for this software
References in zbMATH (referenced in 1 article )
Showing result 1 of 1.
- Yan, Cheng; Wang, Jianxin; Lan, Wei; Wu, Fang-Xiang; Pan, Yi: SDTRLS: predicting drug-target interactions for complex diseases based on chemical substructures (2017)