Abstract
In this article, we propose a Bayesian criterion for the identification of differentially expressed genes by using the Kullback–Leibler divergence. The advantage of using the Kullback–Leibler divergence is that it allows measuring the influence of the treatment average on the posterior distribution of the parameters of the control distribution. To verify the performance of the proposed method and compare it with the t-test and other two Bayesian methods, we developed a simulation study. The comparison is made in terms of the true positive rate and the false discovery rate. The results obtained show a better performance of the proposed method. We also apply the four methods to a real dataset publicly available on the internet.
Acknowledgments
The authors are grateful to the editor and referees for helpful comments and suggestions which have led to an improvement of this article.