基于混合并行遗传算法的大豆蛋白质二级结构预测  

Soybean Protein Secondary Structure Prediction Based on Hybrid Parallel Genetic Algorithm

作　　者：孟翔燕[1] 孟军 葛家麒[1] 

机构地区：[1]东北农业大学理学院,黑龙江哈尔滨150030 [2]国家大豆工程技术中心,黑龙江哈尔滨150030

出　　处：《大豆科学》2009年第2期200-203,209,共5页Soybean Science

基　　金：东北农业大学科技创新资助项目(CXZ010-3)

摘　　要：大豆蛋白质是人类生活不可或缺的物质,对大豆蛋白质二级结构预测是能够准确预测蛋白质分子三维空间结构功能的关键步骤。将聚类分析、并行处理技术和遗传算法相结合,提出基于混合并行遗传算法(HPGA)的蛋白质二级结构预测方法,充分考虑蛋白质序列两端氨基酸对中间氨基酸结构的影响,蛋白质疏水性对二级结构的影响。在整合、改进前人算法的基础上使得计算复杂度降低1个数量级,使得预测准确率达到74%左右。Soybean protein is indispensable material in human life. Soybean protein seeondary structure prediction is the key step of protein 3D structure and function prediction. This paper combined cluster analysis and parallel technique with genetic algorithm, then proposed protein secondary structure prediction based on hybrid parallel genetic algorithm ,in which effects on the behavior of any amino acid in a protein sequence caused hy the adjacent amino acid and hydrophobe were considered. On the basis of the former algorithms integrated and improved, the computational complexity is decreased with one magnitude order,and the average prediction accuracy is about 74%.

关 键 词：大豆蛋白质 并行遗传算法 蛋白质二级结构预测 疏水序列 

分 类 号：S565.1[农业科学—作物学]