Feedback Memetic Algorithms for Modeling Gene Regulatory Networks

— In this paper we address the problem of finding gene regulatory networks from experimental DNA microarray data. We focus on the evaluation of the performance of memetic algorithms on the inference problem. These algorithms are used to evolve an underlying quantitative mathematical model. The dynamics of the regulatory system are modeled with two commonly used approaches, namely linear weight matrices and S-systems. Due to the complexity of the inference problem, some researchers suggested evolutionary algorithms for this purpose. We introduce memetic enhancements to this optimization process to infer the parameters of sparsely connected nonlinear systems from the observed data. Due to the limited number of available data, the inferring problem is underdetermined and ambiguous. Further on, the problem often is multimodal and therefore appropriate optimization strategies become necessary. We propose a memetic method, which separates the overall inference problem into two subproblems...

• Type: Conference
• Year: 2005
• Where: CIBCB
• Authors: Christian Spieth, Felix Streichert, Jochen Supper, Nora Speer, Andreas Zell
• Keywords: Algorithms, CIBCB 2005, Inference Problem, Memetic Algorithms