改进的系统发育谱算法在蛋白质功能注释中的应用  

Application of Improved Phylogenetic Profiling Method in Protein Functional Annotation

作　　者：马雅楠[1] 孙平平[1] 魏雅卓[1] 陆林英[1] 崔颖[1] 马志强[2,1] 

机构地区：[1]东北师范大学计算机学院,长春130117 [2]吉林大学计算机学院,长春130000

出　　处：《生物信息学》2009年第1期44-46,51,共4页Chinese Journal of Bioinformatics

基　　金：教育部应用统计重点实验室资助

摘　　要：系统发育谱方法是目前研究较多的一种基于非同源性的生物大分子功能注释方法。针对现有算法存在的一些缺陷,从两个方面对该方法做了改进:一是构造基于权重的系统发育谱;二是采用改进的聚类算法对发育谱的相似性进行分析。从NCBI上下载100条Escherichia coli K12蛋白质作为实验数据,分别使用改进的算法和经典的层次聚类算法、K均值聚类算法对相似谱进行分析。结果显示,提出的改进算法在对相似谱聚类的精确度上明显优于后两种聚类算法。Phylogenetic profiling is the mostly researched non- homology based functional armotation method. This paper introduced the basic theory of phylogenetic profiling method, and improved this method in two aspects： one is to construct weight based phylogenetic profile; ~he other is to use refined clustering arithmetic for the analysis of similarity among profiles. We downloaded 100 Escheriehia coli K12 proteins from NCBI as experimentation data, and use hierarchical cluster method, K- means algorithm and our method to analyze the profiles respectively. The results indicated that our method showed a higher accuracy compared with the former two methods in clustering of similar profiles.

关 键 词：系统发育谱 参照基因组 权值 聚类 

分 类 号：Q71[生物学—分子生物学]