Clustering Association Rules to Discover Regulatory Genes from Gene Expression Data

• Main Authors: Chun-Liang Lin, 林俊良
• Other Authors: Don-Lin Yang
• Format: Others
• Language: en_US
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/63100253821198268175

碩士 === 逢甲大學 === 資訊工程所 === 93 === In the post genome era, analyzing gene expression patterns is a very important topic for the biologists. Global gene expression profiling, both at the transcript level and the protein level, can be a valuable tool in the understanding of genes, biological networks, and cellular states. As larger gene expression data sets become available, data mining techniques can be applied to identify gene expression patterns of interest in the data more easily. Association rules can reveal biologically relevant associations among different genes, and between environmental effects and gene expression. The problem of analyzing microarray data became one of the popular topics of bioinformatics over past few years. Among the important techniques, clustering has been widely implemented in this domain in order to reveal important information. Although these studies have been successful in showing that genes participating in the same biological processes have similar expression profiles, they are limited to placing genes into groups with others that share certain characteristics. While it is important to determine which genes are related, understanding the mechanism of how genes relate and how they regulate one another is needed to be comprehended. In this paper we introduce an important technique in data mining, called association rule mining, to discover the associations of the gene expressions between these genes. The mining results can provide biologists what the associations between the set of the genes are and lead researchers to look for the potent relationships between regulatory genes and co-regulated genes. Furthermore, an association rule clustering is also proposed with hierarchical clustering to establish a concept hierarchy. Using these results biologists can suggest new hypotheses that may warrant further investigation.