Gene Expression Based Cancer Classification Using Evolutionary and Non-evolutionary Methods

Recent advances in DNA microarray offer the ability to monitor and measure the expression levels of thousands of genes simultaneously in an organism. These experiments consist of monitoring each gene many times under different conditions or evaluating each gene under a single environment but in different types of tissues. The first one is useful for identification of functionally related genes while the second type of experiment is helpful in classification of different types of tissues and identification of those genes whose expression levels are good diagnostic indicators. Different machine learning approaches such as supervised and some unsupervised learning have been previously applied to classify different kinds of patient samples by identifying those genes responsible for different types of cancers. However, the main challenges in this task are the availability of a smaller number of samples compared to huge number of genes and the noisy nature of biological data. Moreover, many of these genes are irrelevant to distinction of different samples and have negative impact on acquired classification accuracy. In this paper, I provide a survey on gene expression based cancer classification using evolutionary and non-evolutionary methods.