An Adaptive Multimeme Algorithm for Designing HIV Multidrug Therapies

Abstract

This paper proposes a period representation for modeling the multidrug HIV therapies and an Adaptive Multimeme Algorithm (AMmA) for designing the optimal therapy. The period representation offers benefits in terms of flexibility and reduction in dimensionality compared to the binary representation. The AMmA is a memetic algorithm which employs a list of three local searchers adaptively activated by an evolutionary framework. These local searchers, having different features according to the exploration logic and the pivot rule, have the role of exploring the decision space from different and complementary perspectives and, thus, assisting the standard evolutionary operators in the optimization process. Furthermore, the AMmA makes use of an adaptation which dynamically sets the algorithmic parameters in order to prevent stagnation and premature convergence. The numerical results demonstrate that the application of the proposed algorithm leads to very efficient medication schedules which quickly stimulate a strong immune response to HIV. The earlier termination of the medication schedule leads to lesser unpleasant side effects for the patient due to strong antiretroviral therapy. A numerical comparison shows that the AMmA is more efficient than three popular metaheuristics. Finally, a statistical test based on the calculation of the tolerance interval confirms the superiority of the AMmA compared to the other methods for the problem under study.

A memetic algorithm for the cyclic antibandwidth maximization problem

“…MAs are based on a population of agents and proved to be of practical success in a variety of problem domains (Burke et al 2001;Franca et al 2001;Ishibuchi et al 2003;Ishibuchi and Narukawa 2004;Ong et al 2006;Neri et al 2007;Tang and Yao 2007;Zhou et al 2007;Boughaci et al 2009;Hasan et al 2009). …”

A memetic algorithm for the optimal winner determination problem

“…Recent studies have shown that memetic approaches can lead to high quality solutions more efficiently than genetic algorithms (Hart William et al 2005;Ong et al 2007). MA has been successfully applied on many complex problems (Boughaci et al 2004;Burke et al 2001;Caponio et al 2007;Franca et al 2001;Ishibuchi and Narukawa 2004;Ishibuchi et al 2003;Neri et al 2007;Ong et al 2006;Tang and Yao 2007;Zhou et al 2007). The ability of MA in solving large problems motivates our choice to use memetic concepts to solve the WDP.…”

A memetic ant colony optimization algorithm for the dynamic travelling salesman problem

“…Multiple LS schemes can be executed in parallel based on competition and a learning mechanism can be used to give greater chances to those efficient LS operators to be used at a later stage Ong and Keane 2004). On the other hand, multiple LS schemes can also be executed based on cooperation, where different LS operators are activated during different population evolution periods (Caponio et al 2007;Neri et al 2007). In the adaptive IO (AIO) operator that is applied in our proposed M-ACO algorithms, both BI and GI work together.…”