Clustering Analysis of Gene Expression Time Series Data

Microarray is used to generate large amount of gene expression data and observing the differences among gene expression levels. Gene expression time series data represents the trend of gene behaviors. Clustering is a popular analysis for gene expression time series data. Genes in the same cluster have similar behavior. Cluster analysis helps people investigate the relativity among genes. We propose a similarity measurement, named LCSS (Longest Common Subseries Similarity), to overcome the influence of “shift-effect,” which is not well handled in commonly used similarity measurements. Also, we use the sequential pattern mining technique to decide the number of clusters for partitioning-based clustering algorithm. A mechanism based on nearest neighbor is used as the criteria for objects relocation in the clustering algorithm. Keyword: Microarray, Gene Expression, Time series, Clustering, Similarity Measurement