Building gene networks with time-delayed regulations

3 We propose a method to build gene regulatory networks (GRN) capable of 4 representing time-delayed regulations. The gene expression data is repre5 sented in a linear model using a dynamic Bayesian network (DBN) and a 6 skip-chain model using a hidden Markov model. The method therefore finds 7 both shortand long-term regulatory interactions. The algorithm was tested 8 on time-series data of the yeast cell-cycle. We compare the accuracy of GRN 9 built by the present method with those built by using a higher-order DBN. 10 The proposed method better fits the expression data and found core genes 11 that are crucial in cell-cycle regulation. 12