Using Splitting Artificial Plant Optimization Algorithm to Solve Toy Model of Protein Folding

摘要

The structure prediction of Toy model of protein folding is one challenging problem in Bioinformatics. Up to now, there are many computational intelligent algorithms are applied to it. However, due to the amount of local optima, there are still many rooms to improve the efficiency. In this paper, a new algorithm, artificial plant optimization algorithm (APOA) inspired by the natural plant growing process is applied to solve this problem. Because of the slow growing process, APOA can escape from local optima easily, and to find the global optimum with a larger probability. Furthermore, the splitting strategy is also employed to increase the performance. To illustrate the efficiency, we apply APOA with splitting strategy to short sequences, Fibonacci sequences and real protein sequences, simulation results show it is effective.