基于混合蚁群遗传算法的RNA二级结构预测  

Predicting RNA Secondary Structure Based on Hybrid Ant Colony System and Genetic Algorithm

作　　者：高冬[1] 

机构地区：[1]吉林大学计算机科学与技术学院,吉林长春130012

出　　处：《计算机与现代化》2011年第8期1-4,8,共5页Computer and Modernization

摘　　要：RNA二级结构预测是生物信息学的重要研究领域。本文提出一种新的基于混合蚁群遗传算法的RNA二级结构预测方法。充分利用茎区和茎区之间的关系信息和累积的信息,通过蚁群算法产生初始种群和新的个体,进而替换遗传算法中的变异算子。构造蚁群算法中的启发式信息、初始信息素矩阵、下一茎区的选取规则和信息素的更新机制,给出遗传算法中交叉算子的交叉策略。最后通过测试已知二级结构的RNA序列,实验结果表明,该方法相对于遗传算法不仅节省程序运行的时间,而且可提高预测的准确性。RNA secondary structure prediction is an important research field in bioinformatics.A new method is presented to predict RNA secondary structure based on hybrid ant colony system and genetic algorithm.The relationship information between different stems is used to generate the initial population and the accumulated pheromone information is used to construct new secondary structure.Then the folding pathway is simulated,including such processes as construction of the heuristic information,the rule of initializing the pheromone,the mechanism of choosing the initial and next stem and the strategy of updating the pheromone between two different stems.And a new crossover strategy is proposed.By testing the RNA sequences with known structures,experiment result shows that this algorithm improves the prediction accuracy compared with genetic algorithm.

关 键 词：生物信息学 RNA 二级结构 蚁群算法 遗传算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]