A Non-Homogeneous Dynamic Bayesian Network with Sequentially Coupled Interaction Parameters for Applications in Systems and Synthetic Biology

In this paper, the authors introduce a Bayesian regularization scheme that addresses the problem of over-fitting or inflated inference uncertainty in time varying dynamic Bayesian networks (TV-DBNs). Following testing of the regularized TV-DBN model on synthetic data, the method was applied to real-world gene expression time series, measured during the life cycle of Drosophila melanogaster, under artificially generated constant light condition in Arabidopsis thaliana, and from a synthetically designed strain of Saccharomyces cerevisiae exposed to a changing environment.

Grzegorczyk M. and Husmeier D. (2012). Statistical Applications in Genetics and Molecular Biology, volume 11, issue 4.