Identification of MicroRNA Regulatory Modules by Clustering MicroRNA-Target Interactions

Yi Yang,Xuting Wan

doi:10.1109/access.2020.3018105

Abstract

Identification of microRNA regulatory modules can help decipher microRNA synergistic regulatory mechanism in the development and progression of complex diseases, especially cancers. Experimentally validated microRNA-target interactions provide strong direct evidence for the analysis of microRNA regulatory functions. We here developed a novel computational framework named CMIN to identify microRNA regulatory modules by performing link clustering on such experimentally verified microRNA-target interactions. CMIN runs in two main steps: it first utilizes convolutional autoencoders to extract high-level microRNA-target interaction features from the expression profile data, and then applied affinity propagation clustering algorithm to interaction feature to obtain overlapping microRNA-target clusters. Clusters with significant synergy correlations are considered as microRNA regulatory modules. We tested the proposed framework and other three existing methods on three types of cancer data sets from TCGA (The Cancer Genome Atlas). The results showed that the microRNA regulatory modules detected by CMIN exhibit stronger topological correlation and more functional enrichment compared with other methods. Availability: The supplementary files of CMIN are available at https://github.com/snryou/CMIN.

Highlights

MicroRNAs are a class of non-coding RNAs that bind to target messenger RNAs to induce mRNA degradation or translational repression [1], [2]
For CMIN, we set the parameters of convolutional autoencoder (CAE) model and Affinity Propagation (AP) clustering algorithm according to the description in Section II throughout the test
In this article, we propose a novel link clustering method CMIN that provides a new insight for the identification of microRNA regulatory modules

Summary

Introduction

MicroRNAs (miRNAs) are a class of non-coding RNAs that bind to target messenger RNAs (mRNAs) to induce mRNA degradation or translational repression [1], [2]. A large number of studies have monitored cancer progression by measuring the expression of miRNA [5]-[7]. This monitoring is typically based on the expression of individual miRNAs, but miRNAs are more likely to coordinate together to perform their functions [8], [9]. Based on the network elements used for identifying modules, the existing methods can be classified into two categories: node-based and structure-based [13]. The former finds a partition of network nodes to assign each node to one and only one module, whereas the latter assigns each specific substructure to one and only one module

Methods

Results

Conclusion