Hybrid Artificial Bee Colony and Particle Swarm Optimization Approach to Protein Secondary Structure Prediction

摘要

Proteins are crucial in the biological processes, and their structure determines whether they can function well or not. Since the theory presented by Anfinsen that proteins' space structure is entirely determined by the primary structure came out, it is possible for us to predict the structure of proteins through their primary structure without any experiment. In order to reach this target, the prediction problem can be formulated as an optimization problem that is set to find the lowest free energy conformation. In this paper, a hybrid Artificial Bee Colony (ABC) with Particle Swarm Optimization (PSO) Algorithm is used to solve this problem. Considering that the two algorithms have complementary characteristics, we combine them together and find out a better optimization results through this new approach. Experimental results have demonstrated the feasibility and effectiveness of our proposed approaches.