LRSSLMDA: Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction

Abstract

Predicting novel microRNA (miRNA)-disease associations is clinically significant due to miRNAs’ potential roles of diagnostic biomarkers and therapeutic targets for various human diseases. Previous studies have demonstrated the viability of utilizing different types of biological data to computationally infer new disease-related miRNAs. Yet researchers face the challenge of how to effectively integrate diverse datasets and make reliable predictions. In this study, we presented a computational model named Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction (LRSSLMDA), which projected miRNAs/diseases’ statistical feature profile and graph theoretical feature profile to a common subspace. It used Laplacian regularization to preserve the local structures of the training data and a L ₁-norm constraint to select important miRNA/disease features for prediction. The strength of dimensionality reduction enabled the model to be easily extended to much higher dimensional datasets than those exploited in this study. Experimental results showed that LRSSLMDA outperformed ten previous models: the AUC of 0.9178 in global leave-one-out cross validation (LOOCV) and the AUC of 0.8418 in local LOOCV indicated the model’s superior prediction accuracy; and the average AUC of 0.9181+/-0.0004 in 5-fold cross validation justified its accuracy and stability. In addition, three types of case studies further demonstrated its predictive power. Potential miRNAs related to Colon Neoplasms, Lymphoma, Kidney Neoplasms, Esophageal Neoplasms and Breast Neoplasms were predicted by LRSSLMDA. Respectively, 98%, 88%, 96%, 98% and 98% out of the top 50 predictions were validated by experimental evidences. Therefore, we conclude that LRSSLMDA would be a valuable computational tool for miRNA-disease association prediction.

Author summary

Discovering miRNA-disease associations promotes the understanding towards the molecular mechanisms of various human diseases at the miRNA level, and contributes to the development of diagnostic biomarkers and treatment tools for diseases. Computational models can make the discovery more efficient and experiments more productive. LRSSLMDA was proposed to computationally infer potential miRNA-disease associations via adopting sparse subspace learning with Laplacian regularization on the known miRNA-disease association network and the informative feature profiles extracted from the integrated miRNA/disease similarity networks. Experimental results in global and local leave-one-out cross validation and 5-fold cross validation showed a superior prediction performance of LRSSLMDA over previous models. Moreover, three types of case studies on five important human diseases were carried out to further demonstrate the model’s predictive power: respectively, 98%, 88%, 96%, 98% and 98% out of the top 50 predicted miRNAs were confirmed by experimental literatures. So, we believe that LRSSLMDA could make reliable predictions and might guide future experimental studies on miRNA-disease associations.