基因微阵列数据的聚类分析算法研究  

The Research of Clustering in Microarray Expression Data Analysis

作　　者：马煜[1] 陈莉[1] 欧立奇[1] 

机构地区：[1]西北大学计算机科学系,西安710069

出　　处：《计算机工程与应用》2006年第5期176-178,206,共4页Computer Engineering and Applications

基　　金：陕西省自然科学基金资助项目(编号:98X11);陕西省教育厅重点科研计划资助项目(编号:00JK015)

摘　　要：微阵列技术是后基因组时代功能基因组研究的主要工具。基因表达谱数据的聚类分析对于研究基因功能和基因调控机制有重要意义。针对聚类算法要求事先确定簇的个数、对噪声敏感和可伸缩性差的问题,基于密度聚类算法DBSCAN和共享近邻SharedNearestNeighbors(SNN)的不同的特点,提出了一种新的最近邻先吸收的聚类算法,将其应用于一个公开的酵母细胞同期数据集,并用评价方法FOM将聚类结果与K-means聚类方法的结果进行了比较。结果表明,该文的聚类算法优于其他聚类算法,聚类结果具有明显的生物学意义,并能对数据的类别数作出较好的预测和评估。Microarray technology is used as the chief tool for functional genomics research in the And then gene era. The cluster analysis of gene expression data is an important means for discovering gene functions and regular to mechanisms.To address the requirements of clustering that input the number of cluster,very sensitive to noises or outliers,not scalable with the large number of genes and dimensions.A novel nearest neighbors absorbed firstly clustering algorithm based on DBSCAN and SNN has been used to analyze a yeast cell cycle dataset.The algorithm provides more useful information than other methods,and has obvious biological meanings.The optimal cluster number can also be estimated by the method.

关 键 词：微阵列 基因表达谱 聚类 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]