变长度Motif识别中的Gibbs抽样算法(英文)  

A Gibbs Sampling Algorithm for Variable-Length Motif Discovery

作　　者：陈晓林[1] 汪四水[2] 

机构地区：[1]中国科学院数学与系统科学研究院,北京100190 [2]苏州大学数学科学学院,江苏苏州215006

出　　处：《生物数学学报》2010年第3期442-448,共7页Journal of Biomathematics

摘　　要：Motif识别是计算生物学中的重要问题.处理缺失数据的方法被大家广泛应用于生物序列中的Motif识别,例如EM算法,Gibbs抽样等等.现在识别Motif的方法都是首先假定Motif的长度是给的,但是,事实上Motif的长度是未知的,在这篇文章中,我们用Gibbs抽样算法在寻找Motif的位置的同时确定Motif的长度.Discovery of motif is very important in computational biology.Missingdata methodologies have been applied to discover conserved motifs of biological sequences, such as EM algorithm,Gibbs sampling algorithm and so on.During discovering the conserved motif,most of the current algorithms assume that the length of the motif is known in advance.But in fact we don＇t know the motif width in advance.Here we propose to use the Gibbs sampling algorithm to discover motif with variable length, while fixing the locations of the motif.

关 键 词：GIBBS抽样 MOTIF 变长度 

分 类 号：O212[理学—概率论与数理统计]