Ding Yanrui

Multiple-layer Quantum-behaved Particle Swarm Optimization and Toy Model for Protein Structure Prediction

Protein structure prediction, known as an NP-complete problem, is one of the basic problems in computational biology. To get an efficiency approach of protein structure prediction with Toy model, a new algorithm structure based on quantum-behaved particle swarm optimization (QPSO) structure is suggested, which is named as multiple-layer QPSO (MLQPSO). In this structure, population of each generation is divided into elite sub-population, exploitation sub-population and exploration sub-population, respectively using different strategies, sequentially leading to improve the ability of local exploitation and global exploration. Subsequently, the algorithm to predict the structure prediction is evaluated by artificial data and real protein. The experiment shows the MLQPSO is a feasible and efficient algorithm.