Multi-view manifold regularized learning-based method for prioritizing candidate disease miRNAs

摘要

MicroRNAs (miRNAs) are emerging as key regulators and have been reported to play critical roles in diverse cellular processes. Previous findings have shown that aberrant expression of miRNAs is associated with tumorigenesis and may lead to many human complex diseases. Although large amount of miRNAs have been identified in various species, unfortunately, the functions of majority of them still remain to be unraveled. The huge volume omics data provide an unprecedented opportunity for prioritizing disease miRNA candidates by computational methods, which contributes to elucidating the progression of human diseases and greatly facilitates cancer prevention, diagnosis and treatment. Here, we present a computational method called MRSLA to discover disease-associated miRNAs. We formulate the disease miRNA prioritization task as a recommender system that recommends those most likely miRNAs for given diseases based on low-rank approximation framework, which is an efficient machine learning algorithm that could effectively incorporate multi-modal features into the prediction model and produce a good performance. In MRSLA, we first utilized multi-view data sources, including known miRNA-disease associations, disease semantic information, experimentally verified miRNA-target gene interactions, and gene-gene interaction network, to estimate the miRNA similarity and disease similarity and then construct a bilayer heterogeneous network. After that, we project the miRNA-disease associations into two subspaces and develop a low-rank approximation-based recommendation method to predict disease miRNA candidates. In addition, to encourage sparsity and enhance the biological relevance of the results, the manifold regularizations and L-1-norm constraints are imposed into the objective formulation to guide the prediction process. The results shown that MRSLA achieves superior performance compared with other methods and could effectively discover potential disease-associated miRNAs. (C) 2019 Published by Elsevier B.V.