Variable neighborhood search for reverse engineering of gene regulatory networks

Abstract

A new search heuristic, Divided Neighborhood Exploration Search, designed to be used with inference algorithms such as Bayesian networks to improve on the reverse engineering of gene regulatory networks is presented. The approach systematically moves through the search space to find topologies representative of gene regulatory networks that are more likely to explain microarray data. In empirical testing it is demonstrated that the novel method is superior to the widely employed greedy search techniques in both the quality of the inferred networks and computational time.

Identification of self-regulatory network motifs in reverse engineering gene regulatory networks using microarray gene expression data

“…To model the regulatory interactions of genes, the Gene Regulatory Networks (GRNs) are deemed as essential tools in computational systems biology. GRNs help in understanding the molecular role and predicting cellular phenotypes [2 –4 ]. Reverse engineering of GRNs by visualising the dynamics of gene regulations [5, 6 ] has grabbed the attention of biological research community due to its benefits in several applications, such as in discovering the direct drug targets [7 ], in knowledge provisioning about the molecular basis of diseases [8, 9 ], in determining the complex traits of living cells assisting the process of identifying phenotypic characteristics of the genomics data [10 ] etc.…”