DNA序列数据挖掘技术∗
朱扬勇1,2+, 熊赟1
1(复旦大学计算机与信息技术系,上海 200433)
2(上海生物信息技术研究中心,上海 201203)
DNA Sequence Data Mining Technique
ZHU Yang-Yong1,2+, XIONG Yun1
1(Department of Computer and Information Technology, Fudan University, Shanghai 200433, China)
2(Shanghai Center for Bioinformation Technology, Shanghai 201203, China)
+ Corresponding author: Phn: +86-21-65642831, Fax: +86-21-65642219, E-mail: yunx@fudan.edu.cn, http://www.dmgroup.org.cn
Zhu YY, Xiong Y. DNA sequence data mining technique. Journal of Software, 2007,18(11):2766−2781. http://www.jos.org.cn/1000-9825/18/2766.htm
Abstract: DNA sequence is one of the basic and important data among biological data. Researching DNA sequence data and then comprehending life essential is a necessary task in post-genomic era. At present, data mining technique is one of the most efficient data analysis means, which finds out information hidden in data. It has also become main data analysis technique adopted in Bioinformatics. It has been applied in DNA sequence analysis, which has got wide attention and rapid development. And considerable research achievements have emerged. Provides an overview of research progress in DNA sequence data mining field. In more detail, it proposes three research phases including statistics-based data mining methods application, general data mining methods application, and specialized DNA sequence-oriented data mining methods design, and then elaborates that sequence similarity is foundation of DNA sequence data mining technique. It also analyzes and comments some key techniques in this field by combining with biological background, such as DNA sequential pattern, association, clustering, classification and outlier mining. Finally, future work and open issues are given, including the research of a novel storage model and index methods, the design of data mining algorithm based on biological domain knowledge.
Key words: DNA sequence; data mining; bioinformatics; sequential pattern; sequence similarity
摘 要: DNA序列数据是一类重要的生物数据.研究DNA序列数据解读其含义是后基因组时代的主要研究任务.数据挖掘是目前最有效的数据分析手段之一,用于发现大量数据所隐含的各种规律,也是生物信息学采用的主要数据分析技术.将数据挖掘技术用于DNA序列数据分析,已得到了广泛关注和快速发展,并取得了许多研究成果.综述了DNA序列数据挖掘领域的研究状况和进展,提出了3个研究阶段:基于统计的挖掘方法应用阶段、一般化挖掘方法应用阶段和专门的DNA序列数据挖掘方法设计阶段.阐述了DNA序列数据挖掘的基础是序列相似性,评述了
∗ Supported by the National Natural Science Foundation of China under Grant No.60573093 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2006AA02Z329 (国家高技术研究发展计划(863))
Received 2007-01-23; Accepted 2007-04-25
朱扬勇 等:DNA 序列数据挖掘技术 2767
DNA序列数据挖掘领域所采用的关键技术,包括DNA序列模式、关联、聚类、分类和异常挖掘等,分析讨论了其相应的生物应用背景和意义.最后给出DNA序列数据挖掘进一步研究的热点问题,包括DNA |
|
资源大小：341.91 KB 
