混合优化策略的蛋白质折叠结构预测

为提高蛋白质折叠结构的预测精度,提出了一种融合改进模拟退火算法与序列二次规划法的预测策略.将序列二次规划法加入具有回火退火功能的模拟退火算法中,利用其局部最优化的能力对由模拟退火算法求得的全局优化结果进行二次优化,进而求得全局最优化结果.对所提方法进行了计算机仿真研究,并与其它方法进行了性能比较,实验结果表明,该方法能够有效提高蛋白质折叠结构的预测精度.

Prediction of protein folding based on hybrid optimization strategy

In order to increase the prediction accuracy of protein folding,a prediction strategy of combining the improved simulated annealing algorithm and the sequential quadratic programming is brought forward.In this strategy,the sequential quadratic programming is introduced into the simulated annealing algorithm with tempering annealing function,and its local optimization capacity is used to optimize the optimal result gained by the simulated annealing algorithm once more,then the global optimization can be achieved.Simulation results show that the proposed method can effectively improve the prediction accuracy of protein folding by comparison with other methods.