Integration and Reduction of Microarray Gene Expressions Using an Information Theory Approach

The DNA microarray is an important technique that allows researchers to analyze many gene expression data in parallel. Although the data can be more significant if they come out of separate experiments, one of the most challenging phases in the microarray context is the integration of separate expression level datasets that have gathered through different techniques. In this paper, we present a general novel method for the integration of any collected data whose distributions have been linearly transformed. The new method is based on the information theory concepts. More than that, this article presents a new approach for checking of the linearity between two distributions as a validation technique. The validation technique assists in taking the feature reduction process in effect prior to the integration phase. The time complexity of the proposed algorithm is low and the new presented methods show good functionality. The experimental results are presented at the end of the paper.