Reconstruction of gene regulatory networks using S-system with a genetic algorithm and flower pollination algorithm hybrid

Accurate reconstruction of gene regulatory networks from time-series gene expression data is a significant challenge for computer scientists. In this paper, we have proposed a genetic algorithm and flower pollination algorithm hybrid for the reverse engineering of gene regulatory network based on decoupled S-systems. Here, genetic algorithm has been used to select the best combination of genes, which act as regulators in the network. Flower pollination algorithm has been used to calculate the best possible S-system parameters for which the training error is minimal for those regulators. The proposed method has been tested on small-scale and medium-scale; synthetic benchmark networks and in-slico benchmark networks extracted from the GeneNetWeaver database, as well as the real-world experimental datasets of the yeast IMRA and DNA SOS repair network of Escherichia coli. The experiments reveal that the proposed hybrid methodology is capable of inferring gene regulatory networks more accurately with lesser training data and in lesser computational time compared to other existing methods.