Abstract—Particle Swarm Optimization (PSO) is a wellknown, competitive technique for numerical optimization with real-parameter representation. This paper introduces CCPSO, a new Cooperative Particle Swarm Optimization algorithm for combinatorial problems. The cooperative strategy is achieved by splitting the candidate solution vector into components, where each component is optimized by a particle. Particles move throughout a continuous space, their movements based on the influences exerted by static particles that then get feedback based on the fitness of the candidate solution. Here, the application of this technique to side-chain packing (a proteomics optimization problem) is investigated. To verify the efficiency of the proposed CCPSO algorithm, we test our algorithm on three side-chain packing problems and compare our results with the provably optimal result. Computational results show that the proposed algorithm is very competitive, obtaining a conformation with an energy value within 1 % of the provably optimal solution in many proteins. I.

In the past decades, a significant number of studies on the prediction of protein 3D tertiary structures have been extensively made. However, the folding rules, the core issue of protein structure prediction, still stay unsolved. Given a target protein with its primary amino acid sequence, the protein backbone structure prediction (PSP) problem is to construct the 3D coordinates of α-carbon atoms on the backbone. We propose a hybrid method by combining the homology model and the folding approach to solve the PSP problem. Our idea of protein folding is performed on the combined sliced cubic lattice, which mixes coarse lattices with fine lattices. Our computation is based on the HP (Hydrophobic-Polar) model, combined with the constraint of disulfide bonds. The folding is optimized by using the ant colony optimization (ACO) algorithm. Our experimental results show that our prediction accuracy is better than previous methods by the measurement of RMSD. Key words: bioinformatics, protein backbone,