基于统计独立性度量方法的大肠杆菌基因调控网络结构辨识

doi:10.3969/j.issn.0258-8021.2013.02.03

摘要
图/表
参考文献
相关文章 (0)

全文: PDF (616 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要生物学探究的基因关联是类似于因果关系的本质联系，要解决的关键问题是寻找一种可以描述本质联系的方法。针对Dialogue for Reverse Engineering Assessments and Methods 第3次竞赛项目（DREAM3）中的大肠杆菌（E.coli）基因调控网络结构辨识问题，提出一种基于再生核希尔伯特空间（RKHS）的统计独立性度量方法—— Hilbert-Schmidt 独立性准则（HSIC）。此方法是一种基于分布的非参数独立性度量方法，并不要求数据符合某种特定分布，不以分类率、模型简单度等外部条件作为约束条件，同时非参数定量地描述变量之间的联系程度。对大肠杆菌基因表达数据的实验结果显示，尽管数据集中的时间序列数据样本很小，并且只提供了较弱的和类型复杂的调控信息，但HSIC方法仍能较好地辨识出这种较为隐含且复杂的调控关系。对比计算显示，在3种数据规模下，采用HSIC方法辨识结果的AUROC值高于Granger Causality（GC）方法23个百分点，高于参与此竞赛的第1名3.9个百分点，而且在计算效率上亦高出其所使用的微分方程法3个数量级。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	樊双喜^韩斌^厉力华^*祝磊金丽艳李颜娥王晟应南娇

关键词 ：基因调控网络, 再生核希尔伯特空间, HSIC方法, 结构辨识

Abstract：The key of genetic system modeling is to identify the causal relationships of the genes. In the third Dialogue for Reverse Engineering Assessments and Methods（DREAM3）competition, E.coli dataset was generated with a ‘true’ biological gene networks. The aim of this work is to recover gene network structure from the data. Here we presented a statistical independent measurement method based on reproducing kernel Hilbert space (RKHS) - HilbertSchmidt independence criteria (HSIC). Different from others, which either use the classification rate, or parameterized methods，the proposed measurement is a nonparametric direct measurement with independence. Comparative experiment results showed that the method was efficient in recovering the regulatory relationships between genes even with small data sample. Specifically, the HSIC achieved a better result than the classical Granger Causality (GC) method as well as the differential equations based method, which was the best in DREAM3 contest. The AUROC values obtained by HSIC is 23 percent higher than GC method, and 3.9 percent higher than the best performer of this contest. In addition, the computational efficiency of HSIC method was 3 orders higher than differential equations based method.

Key words： gene regulatory networks reproducing kernel Hilbert space Hilbert-Schmidt independence structure learning

基金资助:国家杰出青年基金（60788101）；国家自然科学基金（60801055）；浙江省自然科学基金（Z2090299）

引用本文:

樊双喜^**韩斌^**厉力华^*祝磊金丽艳李颜娥王晟应南娇. 基于统计独立性度量方法的大肠杆菌基因调控网络结构辨识[J]. 中国生物医学工程学报, 2013, 32(2): 141-148.
FAN ShuangXi^**HAN Bin^**LI Li Hua^*ZHU Lei JIN Li Yan LI YanE WANG Sheng YING NanJiao. Identifying E.coli Gene Regulatory Network Based on HilbertSchmidt Independence Criterion. journal1, 2013, 32(2): 141-148.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2013.02.03 或 http://cjbme.csbme.org/CN/Y2013/V32/I2/141

［1］Gibbs RA, Belmont JW, Hardenbol P, et al. The international HapMap project ［J］. Nature, 2003, 426(6968): 789-796.
［2］Zhang Y, AbuKhzam FN, Baldwin NE et al. Genomescale computational approaches to memoryintensive applications in systems biology ［C］ // William Kramer, eds. Proceedings of the 2005 ACM/IEEE Conference on Supercomputing.Washington: IEEE ,2005:12.
［3］Kamiński M, Mingzhou D, Wilson A ,et al. Evaluating causal relations in neural systems: Granger causality, directed transfer function and statistical assessment of significance ［J］. Biological Cybernetics, 2001, 85(2): 145-157.
［4］Granger CWJ. Investigating causal relations by econometric models and crossspectral methods ［J］. Econometrica: Journal of the Econometric Society, 1969: 424-438.
［5］JirapechUmpai T, Aitken S. Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes ［J］. BMC Bioinformatics, 2005 6(1): 148.
［6］Zheng P,Griswold MD,Hassold TJ, et al.Predicting meiotic pathways in human fetal oogenesis ［J］. Biology of Reproduction, 2010, 82(3):543-551.
［7］Silvescu A, Honavar V. Temporal boolean network models of genetic networks and their inference from gene expression time series ［J］. Complex Systems, 2001, 13(1): 61-78.［8］Xiong H, Choe Y. Structural systems identification of genetic regulatory networks ［J］. Bioinformatics, 2008 24(4): 553-560.
［9］Murphy K, Mian S. Modelling gene expression data using dynamic Bayesian networks ［J］. Bioinformatics, 2008 24 (4): 553-560.
［10］Chen T, He HL, Church GM. Modeling gene expression with differential equations ［C］// Lauderdale K, eds.Pacific Symposium on Biocomputing.Singapore:World Scientific, 1999:29-40.
［11］Fukumizu K, Bach FR, Jordan MI. Dimensionality reduction for supervised learning with reproducing kernel Hilbert spaces ［J］. Journal of Machine Learning Research, 2004: 73-99.
［12］Fukumizu K, Bach FR, Jordan MI. Kernel dimension reduction in regression ［J］. Annals of Statistics,2009,37(4):1871-1905. 
［13］Li KC. Sliced inverse regression for dimension reduction ［J］. Journal of the American Statistical Association, 1991 86(414): 316-327.
［14］Li KC. On principal Hessian directions for data visualization and dimension reduction: another application of Stein's lemma ［J］. Journal of the American Statistical Association, 1992, 87(420): 1025-1039.
［15］Everitt B, Howell D. Encyclopedia of statistics in behavioral science［M］//Thompson B. Canonical Correlation Analysis. Hoboken:Wiley Online Library,2005.
［16］Marbach D, Schaffter T, Mattiussi C, et al. Generating realistic in silico gene networks for performance assessment of reverse engineering methods ［J］. Journal of Computational Biology, 2009, 16(2): 229-239.
［17］Gretton A, Bousquet O, Smola A. Measuring statistical dependence with HilbertSchmidt norms ［M］// Jain S, Simon HU, Tomita E. Algorithmic Learning Theory. Berlin:Springer Berlin Heidelberg,2005:63-77
［18］Gretton A, Fukumizu K, Teo CH, et al. A kernel statistical test of independence ［C］ //Schlkopf B. Advances in Neural Information Processing Systems 20: Proceedings of the 2007 Conference (2008). Seattle: MIT Press, 2008:585-592. 
［19］Kankainen A, Ushakov NG. Consistent testing of total independence based on the empirical characteristic function ［J］. Journal of Mathematical Sciences,1998:1486-1494
［20］Yip KY, Alexander RP, Yan KK, et al. Improved reconstruction of in silico gene regulatory networks by integrating knockout and perturbation data ［J］. PloS One, 2010, 5(1): e8121.
［21］Gretton A. A kernel method for the twosample problem ［J］. Journal of Machine Learning Research 1,2008.
［22］Prill RJ, Marbach D, SaezRodriguez J, et al. Towards a rigorous assessment of systems biology models: the DREAM3 challenges ［J］. PloS One, 2010, 5(2): e9202.［23］Acharya LR, Judeh T, Wang G, et al. Optimal structural inference of signaling pathways from unordered and overlapping gene sets ［J］. Bioinformatics, 2012,28(4): 546-556.