基于特征综合的启动子识别方法  

Promoter recognition method based on integrated features

作　　者：刘咏梅[1] 董宜堃[1] 

机构地区：[1]哈尔滨工程大学计算机科学与技术学院,哈尔滨150001

出　　处：《计算机工程与应用》2012年第11期201-204,共4页Computer Engineering and Applications

基　　金：教育部留学回国人员科研启动基金资助项目;中央高校基本科研业务费专项资金自由探索项目(No.HEUCF100604)

摘　　要：针对真核生物启动子识别的高假阳性现状,提出了一种基于特征综合的真核启动子识别方法。通过提取人类启动子核苷酸联体统计信息作为特征,并使用主成分分析法进行主元提取。将10维主成分特征与2维CpG岛特征进行特征综合,共同作为BP神经网络的输入来识别启动子。对人类基因序列启动子的预测结果表明,不但有效地减小了假阳性,而且具有较好的敏感性和特异性。In order to improve the situation of high false positive in eukaryotic promoter recognition,a promoter predication method based on integrate-features is presented.The method employs human promoter codon and pentamer information as features,and extracts principal components by PCA.The 10-dimension features and 2-dimension CpG island information,based on integrated features,are put into the BP neural network as classifier.The experimental results show that the method not only reduces the false positives but also obtains a higher sensitivity and specificity.

关 键 词：启动子 启动子识别 主成分分析 CPG岛 反向传播(BP)神经网络 

分 类 号：TP319.4[自动化与计算机技术—计算机软件与理论]