Inferring gene regulatory network using path consistency algorithm based on conditional mutual information and genetic algorithm

The interactions between genes can be described in the form of an intrinsic and interwoven network called Gene Regulatory Network. Discovering this interaction and accurate modeling of Gene Regulatory Network is one of the key issues in understanding the fundamental cell processes which may be used in various medical, complex genetic diseases and drug discovery applications. In this paper, a method for inferring the gene regulatory network using a combination of Genetic Algorithm and Path Consistency Algorithm based on Conditional Mutual information is presented. In this method, for each gene, a genetic algorithm is utilized to find the most suitable predictor set of that gene. Moreover, in order to reduce the search space, the initial population for each target gene is created using the predictors obtained from Path Consistency Algorithm based on Conditional Mutual information method. To guide Genetic Algorithm, the multiple Pearson correlation coefficient is used. The obtained results using three evaluation criteria for biological data show that the proposed model performs better than recent similar methods.