基于碱基偏好分析和SVM的植物启动子识别  

Plant promoter recognition based on analysis of base bias and SVM

作　　者：李文举[1] 寇秋波[1] 韦丽华[1] 刘锦[2] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,辽宁大连116081 [2]辽宁师范大学数学学院,辽宁大连116029

出　　处：《辽宁师范大学学报（自然科学版）》2012年第2期183-187,共5页Journal of Liaoning Normal University:Natural Science Edition

基　　金：辽宁省教育厅高等学校科研基金项目(L2010232)

摘　　要：植物启动子识别是真核启动子识别中的重要研究领域.针对目前植物启动子识别算法的特异性较低的问题,提出了一种基于GC碱基偏好分析和支持向量机(SVM)的植物启动子识别算法.首先通过对GC含量的分析将DNA序列分类为GC偏好序列和非GC偏好序列,然后进行结构特征和信号特征的提取,最后通过SVM分类器进行启动子识别.SVM分类器由四个SVM子分类器组成,即启动子-3’UTR子分类器,启动子-5’UTR子分类器,启动子-Intergenics子分类器和启动子-CDS子分类器.实验结果表明,该算法比其他算法具有更高的特异性,对植物启动子识别具有积极意义.Plant promoter recognition is an important research field in eukaryotic promoter recogni- tion. Aiming at the problem of the lower specificity for the plant promoter recognition,a novel plant promoter recognition algorithm based on analysis of base GC bias and support vector machine（SVM） is proposed. Firstly, DNA sequences are classified as GC bias and non-GC bias sequences by analyzing their GC contents, and then the structure and signal features are gained in the sequence, finally, SVM classifier is used to recognize the promoters. The SVM classifier has four SVM sub-classifiers, that is, promoter-3＇ UTR sub-classifier, promoter-5＇ UTR sub-？classifier, promoter-Intergenics sub- classifier and promoter-CDS sub-classifier. The experimental results show that proposed algorithm in this paper has higher specificity than other algorithms and it has a positive impact on plant promoter recognition.

关 键 词：植物启动子识别 碱基偏好 结构特征 信号特征 支持向量机 分类器 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]