Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06) (2006)
Hong Kong, China
Dec. 18, 2006 to Dec. 22, 2006
Zhengzheng Xing , University of Windsor
Dan Wu , University of Windsor
Most of the current applications which use dynamic Bayesian network to model gene regulatory network assume that the time delay between regulators and their targets is one time unit in a time series gene expression dataset. In fact, multiple time units delay is indicated to exist in a gene regulation process. In this paper, we propose using higherorder Markov dynamic Bayesian network(DBN) to model multiple time units delayed gene regulatory network. A two steps heuristic learning framework is designed to learn higher-order Markov DBN from time series gene expression data. We apply the learning framework to a yeast cell cycle gene expression dataset. The predicted gene regulatory network is strongly supported by biological evidence and consistent with the yeast cell cycle phase information.
Z. Xing and D. Wu, "Modeling Multiple Time Units Delayed Gene Regulatory Network Using Dynamic Bayesian Network," Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06)(ICDMW), Hong Kong, China, 2006, pp. 190-195.