Statistical and Machine Learning Approaches to Predict Gene Regulatory Networks From Transcriptome Datasets.

Keiichi Mochida,Komaki Inoue,Ryuei Nishii,Satoru Koda

doi:10.3389/fpls.2018.01770

Abstract

Statistical and machine learning (ML)-based methods have recently advanced in construction of gene regulatory network (GRNs) based on high-throughput biological datasets. GRNs underlie almost all cellular phenomena; hence, comprehensive GRN maps are essential tools to elucidate gene function, thereby facilitating the identification and prioritization of candidate genes for functional analysis. High-throughput gene expression datasets have yielded various statistical and ML-based algorithms to infer causal relationship between genes and decipher GRNs. This review summarizes the recent advancements in the computational inference of GRNs, based on large-scale transcriptome sequencing datasets of model plants and crops. We highlight strategies to select contextual genes for GRN inference, and statistical and ML-based methods for inferring GRNs based on transcriptome datasets from plants. Furthermore, we discuss the challenges and opportunities for the elucidation of GRNs based on large-scale datasets obtained from emerging transcriptomic applications, such as from population-scale, single-cell level, and life-course transcriptome analyses.

Highlights

Gene regulatory networks (GRNs) represent the causal relationship between genes regulating cellular functions (Barabasi and Oltvai, 2004; Blais and Dynlacht, 2005)
In the last few years, approaches to reconstruct GRNs have advanced by synergistic innovation of high-throughput sequencing and computational techniques; GRNs have played crucial roles to elucidate cellular systems and identify key genes that manipulate cellular functions
A lot of statisticaland machine learning (ML)-based approaches have been proposed and applied to infer GRNs based on transcriptome datasets; these have contributed to identify regulatory relationships of genes involved in various biological phenomena in plants

Summary

INTRODUCTION

Gene regulatory networks (GRNs) represent the causal relationship between genes regulating cellular functions (Barabasi and Oltvai, 2004; Blais and Dynlacht, 2005). We highlight statistical methods, including sparse modeling and machine-learning methods, for inferring GRNs based on transcriptomic datasets from plants. Graphical modeling method and a Random Forest method to infer the robust edges (Marchand et al, 2014) In addition to these approaches, genetics-based approaches to identify genotype-phenotype relationship can provide plausible sets of genes that are involved in a GRN. Through analysis of eQTL and eQTL-guided co-expression network, Basnet et al (2016) identified candidate genes that genetically regulate the fatty acid composition in Brassica rapa seeds, based on cis- and trans-QTLs, detected by the eQTL analysis; this demonstrated that eQTLs can suggest a causal relationship between genes, complementary to networks inferred by computational methods

CONTEXTUAL GENE SELECTION

Fusarium graminearum Zea maize Arabidopsis thaliana

Combined Approaches

GRNs WITH EMERGING APPLICATIONS

Population Transcriptomics for GRN Construction

CONCLUSION AND PERSPECTIVES