基于投票表决特征融合的蛋白质结构类预测  

Prediction of Protein Structural Classes Based on Voting Fusion Algorithm

作　　者：邵壮超[1] 张绍武[1] 潘泉[1] 施建宇[1] 姜涛[1] 

机构地区：[1]西北工业大学自动化学院,西安710072

出　　处：《河南大学学报（自然科学版）》2007年第4期395-398,共4页Journal of Henan University:Natural Science

基　　金：国家自然科学基金资助(60372085);陕西省科学技术研究发展计划项目(2006K04-G14)资助

摘　　要：根据氨基酸的物化特性,基于氨基酸组成成分与氨基酸残基指数自相关函数相结合特征提取法,从非同源蛋白质序列中提取7个特征集(COMP、FINA、MAXF、NAKH、BIOV、OOBM、RICJ),采用有先验知识的投票表决特征融合算法融合这7个特征集,对蛋白质结构类进行预测.结果表明,投票表决融合算法的预测总精度及每一类别的预测精度与7个特征集相比较均有不同程度的提高,说明投票表决融合算法在一定程度上能较多地反映蛋白质的空间结构信息.According to physicochemical properties of amino acid, the approach of feature extraction of incorporating amino acid composition with different auto-correlation functions has been introduced to predict non-homologous protein structural classes, and seven feature sets（COMP, FINA, MAXF, NAKH, BIOV, OOBM, RICJ ）could be gained. We have combined multiple features using voting based on information algorithm to predict protein structural classes. The comparisons of the predictive results from the fusion of multiple features and each parameter data set show that the total predictive accuracies and each class predictive accuracy are remarkably improved by voting based on information algorithm. To some extent, fusion of multiple features can reflect more protein spatial information.

关 键 词：蛋白质结构类 自相关函数 有先验知识的投票表决 特征融合 

分 类 号：Q617[生物学—生物物理学]