Microarray time-series data classification via multiple alignment of gene expression profiles

Pairwise alignment approaches for time-varying gene expression profiles have been recently developed for the detection of co-expressions in time-series microarray data sets. In this paper, we analyze multiple expression profile alignment (MEPA) methods for classifying microarray time-course data. We apply a nearest centroid classification technique, in which the centroid of each class is computed by means of a MEPA algorithm. MEPA aligns the expression profiles in such a way to minimize the total area between all aligned profiles. We propose four MEPA approaches whose effectiveness are demonstrated on the well-known budding yeast, S. cerevisiae, data set. PRIB 2008 proceedings found at: http://dx.doi.org/10.1007/978-3-540-88436-1

Contributors: Monash University. Faculty of Information Technology. Gippsland School of Information Technology ;
Chetty, Madhu ;
Ahmad, Shandar ;
Ngom, Alioune ;
Teng, Shyh Wei ;
Third IAPR International Conference on Pattern Recognition in Bioinformatics (PRIB) (3rd : 2008 : Melbourne, Australia) ;
Coverage:
Rights: Copyright by Third IAPR International Conference on Pattern Recognition in Bioinformatics. All rights reserved.

近年来，针对时变基因表达谱的成对对齐方法已被开发，用于在时间序列微阵列数据集中检测共表达现象。本文中，我们分析了多种表达谱对齐（MEPA）方法，以对微阵列时间序列数据进行分类。我们应用了一种最近质心分类技术，其中每个类别的质心是通过MEPA算法计算得出的。MEPA通过对齐表达谱，以最小化所有对齐谱之间的总面积。我们提出了四种MEPA方法，其有效性在著名的酵母菌，酿酒酵母（S. cerevisiae）数据集上得到了验证。PRIB 2008会议论文集可在以下链接找到：http://dx.doi.org/10.1007/978-3-540-88436-1