PROJECT TITLE :

A Dynamic Multiagent Genetic Algorithm for Gene Regulatory Network Reconstruction Based on Fuzzy Cognitive Maps

ABSTRACT:

In order to reconstruct giant-scale gene regulatory networks (GRNs) with high accuracy, a robust evolutionary algorithm, a dynamic multiagent genetic algorithm (dMAGA), is proposed to reconstruct GRNs from time-series expression profiles based mostly on fuzzy cognitive maps (FCMs) during this paper. The algorithm is labeled as dMAGAFCM-GRN. In dMAGAFCM-GRN, agents and their behaviors are designed with the intrinsic properties of GRN reconstruction issues in mind. All agents live during a lattice-like atmosphere, and therefore the neighbors of each agent are changed dynamically consistent with their energy in each generation. dMAGAFCM-GRN can learn continuous states directly for FCMs from knowledge. Within the experiments, the performance of dMAGAFCM-GRN is validated on both large-scale artificial information and therefore the benchmark DREAM3 and DREAM4. The experimental results show that dMAGAFCM-GRN is ready to effectively learn FCMs with 200 nodes; that's, 40 00zero weights would like to be optimized. The systematic comparison with five existing algorithms shows that dMAGAFCM-GRN outperforms all different algorithms and will approximate the time series with high accuracy.