计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221100088-7.doi: 10.11896/jsjkx.221100088

• 人工智能 • 上一篇    下一篇

参数全局耦合的基因调控网络建模研究

马梦宇1, 孙家祥1, 胡春玲2   

  1. 1 安徽建筑大学电子与信息工程学院 合肥 230601
    2 合肥学院人工智能与大数据学院 合肥 230601
  • 发布日期:2023-11-09
  • 通讯作者: 胡春玲(huchunling@hfuu.edu.cn)
  • 作者简介:(1227554288@qq.com)
  • 基金资助:
    合肥市自然科学基金项目(2021035);国家面上基金项目(61976077)

Modeling Gene Regulatory Networks with Global Coupling Parameters

MA Mengyu1, SUN Jiaxiang1, HU Chunling2   

  1. 1 Department of Electronic Information Engineering,Anhui Jianzhu University,Hefei 230601,China
    2 Department of Artificial Intelligence and Big Data,Hefei University,Hefei 230601,China
  • Published:2023-11-09
  • About author:MA Mengyu,born in 1998,postgraduate.His main research interests include artificial intelligence and bioinformatics.
    HU Chunling,born in 1970,Ph.D,professor,M.S supervisor,is a member of China Computer Federation.Her main research interests include artificial intelligence,data mining and bioinformatics.
  • Supported by:
    Hefei Natural Science Foundation(2021035) and National Natural Science Foundation of China(61976077).

PDF (PC)

457

摘要： 系统生物学中,基于隐马尔可夫模型的非齐次动态贝叶斯网络(HMM-DBN)能够合理推断出周期性基因表达数据中的调控关系,是重构基因调控网络的重要方法之一。但其通常假设调控参数具有完全独立性(每个时间段的参数需要独立推断),而参数假设(完全独立)等于忽略了自然界生物进化过程的连续性,这会影响网络重构精度。针对上述问题,结合多变点过程,提出了参数全局耦合的HMM-DBN(GCHMM-DBN)。GCHMM-DBN模型通过在HMM-DBN的基础上增加了全局耦合超参数,在所有时间段中共享具有相似高斯分布的噪声方差超参数和信噪比超参数,实现了回归参数的全局耦合,最终提高了基因调控网络的重构精度。在酿酒酵母(酵母)数据集和合成RAF数据集上进行实验,结果表明,与经典的同类型HMM-DBN模型相比,GCHMM-DBN模型拥有更高的基因调控网络重构精度。

关键词: 动态贝叶斯网络, 基因调控网络, 全局耦合, 非齐次, MCMC

Abstract: In systems biology,the hidden Markov model non-homogeneous dynamic Bayesian network(HMM-DBN) can reasonably infer the regulatory relationships in periodic gene expression data and is one of the important methods to reconstruct gene regulatory networks.But it usually assumes complete independence of its regulatory parameters(the parameters of each time periods need to be inferred independently),and the parameter assumption(complete independence) is equivalent to ignore the continuity of biological evolutionary processes in nature,which affects the accuracy of network reconstruction.Aiming at the above problems and combining multiple changepoint processes,a hidden Markov model non-homogeneous dynamic Bayesian network with global coupling of parameters(GCHMM-DBN) is proposed.The GCHMM-DBN model achieves the global coupling of regression parameters by adding the global coupling hyperparameters,sharing the noise variance hyperparameters and signal-to-noise ratio hyperparameters of all time periods in the similarity Gaussian distribution based on the HMM-DBN,and finally improving the reconstruction accuracy of the gene regulation network.Experimental results on Saccharomyces cerevisiae(yeast) and synthetic RAF datasets show that the GCHMM-DBN model has higher accuracy of gene regulatory network reconstruction compared with the classical HMM-DBN model.

Key words: Dynamic Bayesian networks, Gene regulatory networks, Global coupling, Non-homogeneous, Markov chain Monte Carlo

中图分类号: 

  • TP311
[1]FRIDEMAN N,LINIAL M,NACHMAN I,et al.Using Bayesian networks to analyze expression data[J].Journal of Computational Biology,2000,7(3/4):601-620.
[2]SACHS K,PEREZ O,PE’ER D,et al.Causal protein-signaling networks derived from multiparameter single-cell data[J].Science,2005,308(5721):523-529.
[3]GRZEGORCYK M,HUSMEIER D.A non-homogeneous dy-namic Bayesian network with sequentially coupled interaction parameters for applications in systems and synthetic biology[J].Statistical Applications in Genetics and Molecular Biology,2012,11(4).
[4]GRZEGORCYK M,HUSMEIER D.Bayesian Regularization of Non-homogeneous Dynamic Bayesian Networks by Globally Coupling Interaction Parameters[C]//Artificial Intelligence and Statistics.PMLR,2012:467-476.
[5]LEBRE S,BECQ J,DEVAUX F,et al.Statistical inference of the time-varying structure of gene-regulation networks[J].BMC Systems Biology,2010,4(1):1-16.
[6]GRZEGORCYK M,HUSMEIER D.Non-homogeneous dynamic Bayesian networks for continuous data[J].Machine Learning,2011,83(3):355-419.
[7]DONDELINGER F,LEBRE S,HUSMEIER D.Non-homogeneous dynamic Bayesian networks with Bayesian regularization for inferring gene regulatory networks with gradually time-varying structure[J].Machine Learning,2013,90(2):191-230.
[8]DONDELINGER F,LEBRE S,HUSMEIER D.Heterogeneous continuous dynamic Bayesian networks with flexible structure and inter-time segment information sharing[C]//International Conference on Machine Learning.DBLP,2010:303-310.
[9]GRZEGORCYK M,HUSMEIER D.Improving the structureMCMC sampler for Bayesian networks by introducing a new edge reversal move[J].Machine Learning,2008,71(2):265-305.
[10]GRZEGORCYKM.A non-homogeneous dynamic Bayesian network with a hidden Markov model dependency structure among the temporal data points[J].Machine Learning,2016,102(2):155-207.
[11]GRZEGORCYKM,HUSMEIER D.Regularization of non-homogeneous dynamic Bayesian networks with global information-coupling based on hierarchical Bayesian models[J].Machine Learning,2013,91(1):105-154.
[12]KAMALABAD M S,GRZEGORCYK M.A new Bayesian piecewise linear regression model for dynamic network reconstruction[J].BMC Bioinformatics,2021,22(2):1-24.
[13]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.
[14]EDWARDS K D,ANDERSON P E,HALL A,et al.FLOWERING LOCUS C mediates natural variation in the high-temperature response of the Arabidopsis circadian clock[J].The Plant Cell,2006,18(3):639-650.
[15]MOCKLER T C,MICHAEL T P,PRIEST H D,et al.The DIURNAL Project:DIURNAL and Circadian Expression Profiling,Model-based Pattern Matching,and Promoter Analysis[C]//Cold Spring Harbor Symposia on Quantitative Biology.Cold Spring Harbor Laboratory Press,2007,72:353-363.
[16]HUNG F Y,CHEN F F,LI C,et al.The arabidopsis LDL1/2-HDA6 histone modification complex is functionally associated with CCA1/LHY in regulation of circadian clock genes[J].Nucleic acids Research,2018,46(20):10669-10681.
[17]ALABADI D,OYAMA T,YANOVSKY M J,et al.Reciprocal regulation between TOC1 and LHY/CCA1 within the Arabidopsis circadian clock[J].Science,2001,293(5531):880-883.
[18]KIKIS E A,KHANNA R,QUAIL P H.ELF4 is a phyto-chrome-regulated component of a negative-feedback loop involving the central oscillator components CCA1 and LHY[J].The Plant Journal,2005,44(2):300-313.
[19]HERRERO E,KOLMOS E,BUJDOSO N,et al.EARLYFLOWERING4 recruitment of EARLY FLOWERING3 in the nucleus sustains the Arabidopsis circadian clock[J].The Plant Cell,2012,24(2):428-443.
[20]ALEXANDRE MORAES T,MENGIN V,PEIXOTO B,et al.The circadian clock mutant lhy cca1 elf3 paces starch mobilization to dawn despite severely disrupted circadian clock function[J].Plant Physiology,2022,189(4):2332-2356.
[21]KAMALABAD M S,GRZEGORCYK M.Non-homogeneous dynamic Bayesian networks with edge-wise sequentially coupled parameters[J].Bioinformatics,2020,36(4):1198-1207.
[22]KAMALABAD M S,GRZEGORCYK M.A new Bayesian piecewise linear regression model for dynamic network reconstruction[J].BMC Bioinformatics,2021,22(2):1-24.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发