A simpler Bayesian network model for genetic regulatory network inference

We use Bayesian networks and a nonparametric regression model for inferring genetic regulatory networks. We have used a combination of the Bayesian information criterion (BIC) and a ´voting´ method to pick out the edges of the output graph. Using BIC makes the model simpler than previous ones, still obtaining, however, good results, as shown in our experiments with synthetic data and Saccharomyces cerevisiae cell cycle microarray gene expression data.