Missing Enzyme Identification Using Reversible-Jump Markov-Chain-Monte-Carlo Learning Approach

摘要：

Computational identification of missing enzymes plays a significant role in reconstruction of metabolic network. For a metabolic reaction, given a set of candidate enzymes identified by certain biological evidences, there is a need to develop a powerful mathematical model to predict the actual enzyme (s) catalyzing the reaction. In this study, a regression model is proposed to solve the problem, in which a reversible jump Markov-chain-Monte-Carlo learning technique is used to estimate the model parameters. We evaluate the model using known reactions in Escherichia coli, Mycobacterium tuberculosis, Vibrio cholerae, and Caulobacter cresentus. It is demonstrated that the model obtains favorable results compared with several other approaches.

关键词： Metabolic network missing enzymes identification regression model Markov chain Monte Carlo.

作者: Bo Geng Xiaobo Zhou Jinmin Zhu Y.S. Hung Stephen Wong

作者单位: HCNR-CBI, Harvard Medical School and Brigham & Womens Hospital, Boston, MA 02215 Department of Elec HCNR-CBI, Harvard Medical School and Brigham & Womens Hospital, Boston, MA 02215 Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong

会议类型: 国际会议

会议名称: 首届伏化合系统生物学国际会议(The First International Symposium OSB07)

会议地点: 北京

会议语种:英文

页码: 178-188

在线出版日期: 2007-08-08（万方平台首次上网日期，不代表论文的发表时间）