Ensemble Approach for Predicting Genetic Disease through Case-Control Study

摘要

The origin of many diseases can be revealed by knowing the gene regulation. Genetic disease an abnormality in individual's genome. These abnormalities can be occurred due to mutation in single base in DNA or due to the involvement in the addition or subtraction of entire chromosomes. To measure the expression levels of bulk of genes simultaneously, DNA microarrays are used. Microarray data is set of DNA sequences representing the entire set of genes of an organism, arranged in a grid pattern so that the expression of thousands of genes can be detected at the same time. In this paper we propose an approach for diagnosing genetic disease, to accomplish this goal we need to select the most informative ones that can accurately distinguish one class of genes from another. For that the genes with high significance are iteratively extracted. The goal of this paper is to develop method, which increases the classification accuracy, for identifying significant differentially expressed clusters of genes using Recursive Cluster Elimination (RCE) that is based on an ensemble clustering approach.