Gene Regulatory Network Construction Based on a Particle Swarm Optimization of a Long Short-term Memory Network

Abstract

: The gene regulatory network (GRN) is a model for studying the function and behavior of genes by treating the genome as a whole, which can reveal the gene expression mechanism. However, due to the dynamics, nonlinearity, and complexity of gene expression data, it is a challenging task to construct a GRN precisely. In this paper, a combination method of long short-term memory network (LSTM) and mean impact value (MIV) was applied for GRN reconstruction. Firstly, LSTM was employed to establish a gene expression prediction model. To improve the performance of LSTM, a particle swarm optimization (PSO) was introduced to optimize the weight and learning rate. Then, the MIV was used to infer the regulation among genes. In order to test the proposed approach, it was applied to three datasets: a simulated dataset and two real biology datasets. By comparing with other methods, the experimental results indicate that the proposed method has higher modeling accuracy and it can be used to effectively construct a GRN. At last, in view of the fouling-forming problem of slime-forming bacteria (SFB), we have designed electromagnetic field experiments and transcriptome sequencing experiments to locate the fouling-forming genes and obtain gene expression data. And a GRN of fouling-forming genes of SFB was constructed using the proposed approach.

Parallel ant colony optimization for the training of cell signaling networks

“…To efficiently solve this calibration problem, many research efforts have focused on developing metaheuristic methods that are capable of finding good solutions in reasonable computation times (Balsa-Canto, Banga, Egea, Fernandez-Villaverde, & de Hijas-Liste, 2012;Banga & Balsa-Canto, 2008;Gábor & Banga, 2015;Sun, Garibaldi, & Hodgman, 2012). Many examples using various metaheuristics can be found in the literature, such as simulating annealing (Perkins, Jaeger, Reinitz, & Glass, 2006), evolutionary strategies (Ji & Xu, 2006;Jostins & Jaeger, 2010), differential evolution (Da Ros et al, 2013;Villaverde & Banga, 2014;Zúñiga, Cruz, & García, 2014), scatter search (Egea, Balsa-Canto, García, & Banga, 2009;Egea, Martí, & Banga, 2010), particle swarm optimization (Palafox, Noman, & Iba, 2012;Tang, Chai, Wang, & Cao, 2020), among others. Also, many proposals exploit different parallelization strategies and infrastructures to solve these problems in competitive execution times (Adams et al, 2013;González et al, 2017;Lee, Hsiao, & Hwang, 2014;Penas, González, Egea, Banga and Doallo, 2015;Teijeiro et al, 2017).…”