Journal of Computational Information Systems 6:6(2010) 1787-1794 Available at http://www.Jofcis.com 1553-9105/ Copyright © 2010 Binary Information Press June, 2010 Polymorphic BCO for Protein Folding Model Yudong ZHANG † , Yuankai HUO, Qing ZHU, Shuihua WANG , Lenan WU School of Information Science and Engineering, Southeast University, Nanjing 210096, China Abstract To improve the protein folding simulations, polymorphic bacterial chemotaxis optimization (PBCO) was investigated on a 2D lattice model. PBCO is a novel intelligent problem solving technique inspired from the foraging behavior of bacteria. We compared PBCO with standard genetic algorithm (SGA) and Immune Genetic Algorithm (IGA) for various chain lengths. It shows that PBCO has the highest successful rate and the lowest computation time. Keywords: Polymorphic Bacterial Chemotaxis Optimization; Protein Folding Model; Standard Genetic Algorithm; Immune Genetic Algorithm 1. Introduction Since nature identifies the global minimum from more than 10 50 possible conformations for the backbone of a small protein the process of protein folding has a challenging search space. [1]. A successful prediction requires two major components: 1) a set of free energy components for the protein, which are computationally inexpensive enough to be used in the search procedure and sufficiently accurate to ensure the uniqueness of the native fold; and 2) an efficient optimization procedure which is capable of finding an appropriate minimum for the strongly anisotropic function of hundreds of variables [2]. Genetic Algorithm (GA) mimics the strategy of natural selection and is well suited to optimizing solutions over large combinatorial spaces. Selection of parents in a GA is performed by a fitness function, encompassing and balancing the driving forces of folding [3]. GA is a promising search strategy for conformational analysis of large molecules including simulations of protein evolution, optimization of sequences for protein engineering, folding analysis and prediction of the 3D structure of proteins [4], and finding low-energy conformations of organic molecules [5]. However, GA is easy to be trapped in local minimum and consumes more time. In recent years, the popularity of Bacterial Chemotaxis Optimization (BCO) has grown significantly as a new global search technique and it has achieved widespread success in solving practical optimization problems in different domains [6-8]. Compared with SGA, the BCO not only provides better solutions, but also enhances the convergent speed. This article extended the line of the research by introducing a polymorphic BCO (PBCO † Corresponding author. Email addresses: yuzhang@childpsych.columbia.edu (Yudong ZHANG)