Multilayer network analysis of miRNA and protein expression profiles in breast cancer patients.

Yang Zhang,Jiannan Chen,Weihui Cong,Yi Zhao,Dehua Wang,Yu Wang,Bo Shiun Lai,Irene Sendiña-Nadal

doi:10.1371/journal.pone.0202311

Abstract

MiRNAs and proteins play important roles in different stages of breast tumor development and serve as biomarkers for the early diagnosis of breast cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to screen the most important miRNAs and proteins. Maximal information coefficient was applied to assess intralayer and interlayer connection. A multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. The degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer.

Highlights

Breast cancer is the second leading cause of cancer death among women and results in millions of new cases every year [1]
Computation of importance scores (Fig 2b) through the use of XGBoost algorithm suggests that mir.139, mir.21, mir.183, mir.96, mir.190b and mir.6507 are significantly associated with breast cancer
After obtaining two miRNA candidate sets and two protein candidate sets selected by two algorithms, the union of the two miRNA sets was taken as the final miRNA candidate set, in the same manner, the final proteins candidate set was obtained

Summary

Introduction

Breast cancer is the second leading cause of cancer death among women and results in millions of new cases every year [1]. Often assuming regulatory roles in eukaryotic cells, miRNAs are small, non-coding RNAs of roughly 20~22 nucleotides that can bind to and inhibit protein coding mRNAs [2]. The expression profiles of miRNAs are correlated with cancer type, stage, and other clinical variables [3]. MiRNA expression profiling could be a useful tool for cancer diagnosis and prognosis. MiRNAs play important roles in almost all aspects of cancer biology, including proliferation, apoptosis, tissue invasion, metastasis, and angiogenesis [4]. MiRNAs play important roles in toxicogenomics and may explain the relationship between toxicant exposure and tumorigenesis. Previous work has identified 63 miRNA genes shown to be epigenetically regulated in association with 21 diseases, including 11 cancer types [4].

Methods

Results

Discussion

Conclusion