Inferring gene regulatory networks with hybrid of multi-agent genetic algorithm and random forests based on fuzzy cognitive maps

Abstract

Inferring gene regulatory networks (GRNs) from expression data is an important and challenging problem in the field of computational biology. With the growth of high-throughput gene expression data, GRN inference has attracted much interest from researchers. In this paper, we focus on inferring large-scale GRNs using a fast and accurate algorithm. We first use fuzzy cognitive maps (FCMs) to model GRNs. Then, multi-agent genetic algorithm (MAGA) is used to determine regulatory links, and random forests (RF) are used as the feature selection algorithm to initialize the agents, which can reduce the search space of MAGA according to the gene ranking. We improve the genetic operators of MAGA to cope with GRN inference. The proposed algorithm is termed as MAGARFFCM-GRN. In the experiments, the performance of MAGARFFCM-GRN is validated on synthetic data and the well-known benchmark DREAM3 and DREAM4. The results show that MAGARFFCM-GRN can infer directed GRNs with high accuracy and efficiency.