Revision of the variational Bayesian method for uncovering genes regulatory network

We have revised the Markov model used in the analysis of microarray time-series data to uncover the gene regulatory network. Previous linear models establishes genetic relations between the microarray data which are assumed to have noise. We propose a new model to distinguish between observed data and real expression levels. The new model does not overestimate the noise and fits better the nature of the problem. We have also studied how the variational Bayesian algorithm can be modified to solve this problem. Finally, we have performed a prior analysis to include objective knowledge into the Bayesian methodology.