概率密度函数的特征相关法DNA序列分析

提出了一种客观的特征提取和相关的方法用于DNA序列的结构分析.这种方法是从DNA序列码的碱基和片段码中提取统计特征和相关特征.然后计算样本序列和已知类之间的平均相关系数.如果最大的相关系数大于对应类的平均相关系数,则该样本被分类到对应的类中去.利用一组DNA序列样本做了试验,结果表明,这种方法适合于任何DNA序列的结构分析而不需要先念的生物信息,对发掘人类基因隐藏信息的研究大有用处。

Analysis of DNA Sequences Using Feature Correlation of Probability Density Function

Propose an unbiased method of feature extraction and classification for DNAsequenceanalysis.In the method,statistical and correlationfeatures are extractedfromraw DNAsequencedata and the mean correlationfeatures of a sample DNAsequence to all given classes are calculat-ed.If the maxi mal mean correlation feature exceeds the mean correlation feature of an existingclass,the sampleis groupedintothe corresponding class.Otherwise,it is groupinto a newclass.Using a set of sample DNAsequences,we demonstrate that t...