隐马尔可夫模型用于蛋白质序列分析  

Hidden Markov Model Used in Protein Sequence Analysis

作　　者：吴晓明[1] 宋长新[1] 王波[1] 程敬之[2] 

机构地区：[1]西安交通大学生命科学与技术学院生物信息学研究中心,西安710049 [2]西安交通大学生命科学与技术学院生物医学工程系,西安710049

出　　处：《生物医学工程学杂志》2002年第3期455-458,共4页Journal of Biomedical Engineering

摘　　要：隐马尔可夫模型 (Hidden Markov model,HMM)用于蛋白质研究是生物信息学研究的新领域。目前 ,人们已经得到大量的蛋白质序列和结构数据 ,传统研究蛋白质的方法已经不再实用 ,生物学家已经转向能够处理大量数据的统计方法来进行研究。隐马尔可夫模型可以通过训练 ,识别同一特征的蛋白质序列。从 SCOP数据库中选择了一个蛋白质族 ,由它得到了能够代表该族特征的隐马尔可夫模型 ,并用该模型对一些蛋白质序列进行分析。结果表明 ,HMM能够较好的表示同一族的蛋白质 。Hidden Markov model (HMM) used in the research of protein is a new field of bioinformatics. Nowadays large amount of data about protein sequences and structures have been obtained. Traditional methods of protein analysis are no longer used. Biologists have updated their research methods with computer technology and statistics, which can deal with large amount of data. HMM can be used to distinguish protein sequence with the same characterstics. A family of protein from SCOP database was selected, through which a HMM model representing the family was obtained, and then the model was utilized to analyze protein sequences. Results indicate that HMM can express particular family of protein,and recognize the given protein sequences of the family from many sequences.

关 键 词：隐马尔可夫模型 SCOP数据库 蛋白质分类 序列分析 

分 类 号：Q51[生物学—生物化学]