基于单核苷酸统计和支持向量机集成的人类基因启动子识别  

Human promoter recognition based on single nucleotide statistics and support vector machine ensemble

作　　者：徐文轩[1] 张莉[1,2] 

机构地区：[1]苏州大学计算机科学与技术学院系,江苏苏州215006 [2]江苏省计算机信息处理技术重点实验室(苏州大学),江苏苏州215006

出　　处：《计算机应用》2015年第10期2808-2812,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61373093);国家级大学生创新创业训练计划项目(201410285032);江苏省自然科学基金资助项目(BK20140008;BK201222725);江苏省高校自然科学研究项目(13KJA520001);江苏省"青蓝工程"资助项目;苏州大学大学生课外学术科研基金资助项目(KY2014687B;KY2015544B;KY2015818B);苏州大学敬文书院"3I工程"项目(29)

摘　　要：为高效地判别人类基因启动子,提出了一种基于单核苷酸统计和支持向量机集成的人类基因启动子识别算法。首先通过基因单核苷酸统计,从而将一个基因数据集分为C偏好和G偏好两个子集;然后分别对这两个子集提取DNA刚性特征、词频统计特征和Cp G岛特征;最后采用多个支持向量机(SVM)集成的方式来学习这三种特征,并讨论了三种集成方式,包括单层SVM集成、双层SVM集成和级联SVM集成。实验结果表明所提算法能够提高人类基因启动子识别的敏感性和特异性,其中双层SVM集成的敏感性达到79.51%,且级联SVM集成的特异性高达84.58%。To efficiently discriminate the promoter in human genome, an algorithm for human promoter recognition based on single nucleotide statistics and Support Vector Machine （SVM） ensemble was proposed. Firstly, a gene dataset was divided into two subsets such as C-preferred and G-perferred subsets by using single nucleotide statistics. Secondly, DNA rigidity feature, word-based feature and CpG-island feature were extracted for each subset. Finally, these features were combined by using SVM ensemble learning. In addition, three ensemble ways were discussed, including single SVM ensemble, double- layer SVM ensemble and cascaded SVM ensemble. The experimental resuh shows that the proposed method can improve the sensitivity and specificity of human propoter recognition. Especially, the double-layer SVM ensemble can achieve the highest sensitivity of 79.51%, while the cascaded SVM ensemble has the highest specificity of 84.58%.

关 键 词：CPG岛 DNA刚性 人类启动子识别 KL散度 单核苷酸统计 支持向量机 

分 类 号：TP3-05[自动化与计算机技术—计算机科学与技术] TP301.6