A time series driven decomposed evolutionary optimization approach for reconstructing large-scale gene regulatory networks based on fuzzy cognitive maps

Abstract

BackgroundReconstructing gene regulatory networks (GRNs) from expression data plays an important role in understanding the fundamental cellular processes and revealing the underlying relations among genes. Although many algorithms have been proposed to reconstruct GRNs, more rapid and efficient methods which can handle large-scale problems still need to be developed. The process of reconstructing GRNs can be formulated as an optimization problem, which is actually reconstructing GRNs from time series data, and the reconstructed GRNs have good ability to simulate the observed time series. This is a typical big optimization problem, since the number of variables needs to be optimized increases quadratically with the scale of GRNs, resulting an exponential increase in the number of candidate solutions. Thus, there is a legitimate need to devise methods capable of automatically reconstructing large-scale GRNs.ResultsIn this paper, we use fuzzy cognitive maps (FCMs) to model GRNs, in which each node of FCMs represent a single gene. However, most of the current training algorithms for FCMs are only able to train FCMs with dozens of nodes. Here, a new evolutionary algorithm is proposed to train FCMs, which combines a dynamical multi-agent genetic algorithm (dMAGA) with the decomposition-based model, and termed as dMAGA-FCMD, which is able to deal with large-scale FCMs with up to 500 nodes. Both large-scale synthetic FCMs and the benchmark DREAM4 for reconstructing biological GRNs are used in the experiments to validate the performance of dMAGA-FCMD.ConclusionsThe dMAGA-FCMD is compared with the other four algorithms which are all state-of-the-art FCM training algorithms, and the results show that the dMAGA-FCMD performs the best. In addition, the experimental results on FCMs with 500 nodes and DREAM4 project demonstrate that dMAGA-FCMD is capable of effectively and computationally efficiently training large-scale FCMs and GRNs.