Association Analysis Techniques for Discovering Functional Modules from Microarray Data

DNA microarray technology is one of the major recent advances in biotechnology [1]. In particular, their ability to measure the expression of thousands of genes simultaneously under a certain condition makes them suitable for several biological applications, such as the functional analysis of genes and identification of significantly overor under-expressed genes in complex diseases like cancer. An application of great interest in microarray data analysis is the identification of a group of genes that show very similar patterns of expression in a data set, and are expected to represent groups of genes that perform common/similar functions, also known as functional modules [2]. Although clustering offers a natural solution to this problem, it suffers from the limitation that it uses all the conditions to compare two genes, whereas only a subset of them may be relevant.