Discovering Cancer-Related miRNAs from miRNA-Target Interactions by Support Vector Machines

Cong Pian; Shanjun Mao; Guangle Zhang; Jin Du; Fei Li; Suet Yi Leung; Xiaodan Fan

doi:10.1016/j.omtn.2020.01.019

Discovering Cancer-Related miRNAs from miRNA-Target Interactions by Support Vector Machines

Mol Ther Nucleic Acids. 2020 Mar 6:19:1423-1433. doi: 10.1016/j.omtn.2020.01.019. Epub 2020 Jan 25.

Authors

Cong Pian¹, Shanjun Mao², Guangle Zhang³, Jin Du², Fei Li⁴, Suet Yi Leung⁵, Xiaodan Fan⁶

Affiliations

¹ Department of Statistics, The Chinese University of Hong Kong, Hong Kong SAR, China; Department of Mathematics, College of Science, Nanjing Agricultural University, Nanjing, China.
² Department of Statistics, The Chinese University of Hong Kong, Hong Kong SAR, China.
³ Binjiang College, Nanjing University of Information Science and Technology, Jiangsu 214105, China.
⁴ Ministry of Agriculture Key Lab of Agricultural Entomology, Institute of Insect Sciences, College of Agriculture and Biotechnology, Zhejiang University, Hangzhou, China.
⁵ Department of Pathology, The University of Hong Kong, Queen Mary Hospital, Pokfulam, Hong Kong SAR, China.
⁶ Department of Statistics, The Chinese University of Hong Kong, Hong Kong SAR, China. Electronic address: xfan@cuhk.edu.hk.

Abstract

MicroRNAs (miRNAs) have been shown to be closely related to cancer progression. Traditional methods for discovering cancer-related miRNAs mostly require significant marginal differential expression, but some cancer-related miRNAs may be non-differentially or only weakly differentially expressed. Such miRNAs are called dark matters miRNAs (DM-miRNAs) and are targeted through the Pearson correlation change on miRNA-target interactions (MTIs), but the efficiency of their method heavily relies on restrictive assumptions. In this paper, a novel method was developed to discover DM-miRNAs using support vector machine (SVM) based on not only the miRNA expression data but also the expression of its regulating target. The application of the new method in breast and kidney cancer datasets found, respectively, 9 and 24 potential DM-miRNAs that cannot be detected by previous methods. Eight and 15 of the newly discovered miRNAs have been found to be associated with breast and kidney cancers, respectively, in existing literature. These results indicate that our new method is more effective in discovering cancer-related miRNAs.

Keywords: cancer-related miRNAs; dark matters; expression data; miRNA-target interactions; support vector machine.