收稿日期: 2012-09-12
修回日期: 2013-03-26
网络出版日期: 2013-11-15
基金资助
Supported by the National Nature Science Foundation of China(60702035), Nature Science Foundation of Zhejiang Province(Y6090164)
Modelling non-stationary gene regulatory networks by combining microarrys with biological knowledge
Received date: 2012-09-12
Revised date: 2013-03-26
Online published: 2013-11-15
为了构建基因调控网络,提出一个基于生物先验数据融合构建非平稳动态贝叶斯网络结构的方法.该方法基于高斯混合网络模型,改变点过程和独立的能量函数.利用可逆跳跃马尔科夫蒙特卡罗抽样算法,把整个非平稳过程分解成若干平稳子片断,推断网络结构以及先验数据对网络的影响.在仿真和生物数据上测试该方法,结果显示该方法提高了网络重构的精度.
关键词： 贝叶斯网络; 基因调控网络; 马尔科夫蒙特卡罗抽样; 改变点过程
倪小虹 , 孙应飞 . 基于生物先验数据融合构建非平稳基因调控网络[J]. 中国科学院大学学报, 2013 , 30(6) : 806 -812 . DOI: 10.7523/j.issn.2095-6134.2013.06.014
In order to construct gene regulatory network, we propose a non-stationary dynamic Bayesian networks method that systematically integrates expression data with multiple sources of prior knowledge. Our method is based on Gaussian mixture Bayesian network model, change point process, and separate energy function of prior knowledge. Using an reversible jump Markov chain Monte Carlo sampling algorithm, we divide data into disjunct compartments, infer network structures, and measure the influence of the respective prior knowledge. Finally, we apply our approach to treat both synthetic data and biological data. The results show that the proposed method improves the network reconstruction accuracy.
[1] Bernard A, Hartemink A. Informative structure priors: Joint learning of dynamic regulatiory networks from multiple types of data[C]//Pacific Symposium on Bio-computing. New Jersey:World Scientific, 2005: 459-470.
[2] Werhli A V, Husmeier D. Reconstructing gene regulatory networks with Bayesian networks by combining expression data with multiple sources of prior knowledge[J]. Stat Appl Genet Mol Biol, 2007, 6(1): Article 15.
[3] Nariai N, Kim S, Imoto S, et al. Using protein-protein interactions for refining gene networks estimated from microarray data by Bayesian networks[C]//Pacific Symposium on Biocomputing. New Jersey: World Scientific, 2004, 9:336-347.
[4] Robinson J W, Hartemink A J. Learning non-stationary dynamic Bayesian networks[J]. Journal of Machine Learning Research, 2010, 11:3 647-3 680.
[5] Grzegorczyk M, Husmeier D. Modelling non-stationary dynamic gene regulatory processes with the BGM model[J]. Comput Stat, 2011, 26:199-218.
[6] Yi J, Jun H. Constructing non-stationary dynamic Bayesian networks with a flexible lag choosing mechanism[J]. Bioinformatics, 2010, 11(6):S27.
[7] Green P. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination[J]. Biometrika, 1995, 82:711-732.
[8] Green P. Trans-dimensional Markov chain Monte Carlo[J]. Oxford Statistical Science Series, 2003, 27:179-198.
[9] Husmeier D, Dondelinger F, Lèbre S. Inter-time segment information sharing for non-homogeneous dynamic Bayesian networks[J]. Advances in Neural Information Processing Systems, 2010, 23: 901-909.
[10] Cantone I, Marucci L, Iorio F, et al. A yeast synthetic network for in vivo assessment of reverse-engineering and modeling approaches[J]. Cell, 2009, 137(1):172-181.
[11] Lee T I, Rinaldi N J, Robert F, et al. Transcriptional regulatory networks in Saccharomyces cerevisiae[J]. Science, 2002, 298(5594): 799-804.
[12] Harbison C T, Gordon B D, Lee T I, et al. Transcriptional regulatory code of a eukaryotic genome[J]. Nature, 2004, 431 (7004),:99-104.
[13] Mas P. Circadian clock function in Arabidopsis thaliana: time beyond transcription[J]. Trends Cell Biol, 2008, 18(6):273-181.
[14] Salome P A, McClung C R. The Arabidopsis thaliana clock[J]. Journal of Biological Rhythms, 2004, 19(5):425-435.
[15] Davis J, Goadrich M. The relationship between precision-recall and ROC curves[C]//Proceedings of the 23rd International Conference on Machine Learning, 2006: 240-248.
[16] Johnson C H, Elliott J A, Foster R. Entrainment of circadian programs[J]. Chronobiol Int, 2003, 20(5):741-774.
/
| 〈 |
|
〉 |
