SCMFMDA: Predicting microRNA-disease associations based on similarity constrained matrix factorization

• DOI: 10.1371/journal.pcbi.1009165
• Publication Date: 2021-07-12T17:45:07Z
• Authors: Lei Li; Zhen Gao; Yu-Tian Wang; Ming-Wen Zhang; Jian-Cheng Ni; Chun-Hou Zheng; Yansen Su
• Keywords: Similarity (geometry); Kernel (algebra); Non-negative Matrix Factorization

miRNAs belong to small non-coding RNAs that are related a number of complicated biological processes. Considerable studies have suggested closely associated with many human diseases. In this study, we proposed computational model based on Similarity Constrained Matrix Factorization for miRNA-Disease Association Prediction (SCMFMDA). order effectively combine different disease and miRNA similarity data, applied network fusion algorithm obtain integrated (composed functional similarity, semantic Gaussian interaction profile kernel similarity) sequence similarity). addition, the L 2 regularization terms constraint were added traditional Nonnegative predict disease-related miRNAs. SCMFMDA achieved AUCs 0.9675 0.9447 global Leave-one-out cross validation five-fold validation, respectively. Furthermore, case two common diseases also implemented demonstrate prediction accuracy SCMFMDA. The out top 50 predicted confirmed by experimental reports indicated was effective relationship between