Inferring Gene Regulatory Network Using An Evolutionary Multi-Objective Method

TL;DR

This paper introduces a multi-objective evolutionary approach for inferring gene regulatory networks, optimizing both network fit and complexity, and effectively identifying network structures without preset parameters.

Contribution

It proposes a novel bi-objective minimization model combined with an evolutionary algorithm and AIC for robust GRN inference without needing problem-specific parameter tuning.

Findings

Successfully identified network topologies and parameters for benchmark systems.

No preset parameter values required for effective inference.

Applicable to various GRN models with improved accuracy.

Abstract

Inference of gene regulatory networks (GRNs) based on experimental data is a challenging task in bioinformatics. In this paper, we present a bi-objective minimization model (BoMM) for inference of GRNs, where one objective is the fitting error of derivatives, and the other is the number of connections in the network. To solve the BoMM efficiently, we propose a multi-objective evolutionary algorithm (MOEA), and utilize the separable parameter estimation method (SPEM) decoupling the ordinary differential equation (ODE) system. Then, the Akaike Information Criterion (AIC) is employed to select one inference result from the obtained Pareto set. Taking the S-system as the investigated GRN model, our method can properly identify the topologies and parameter values of benchmark systems. There is no need to preset problem-dependent parameter values to obtain appropriate results, and thus, our method could be applicable to inference of various GRNs models.