Time-Varying Gene Regulatory Networks Construction Based on Logistic Regression
NI Xiao-Hong1,2, SUN Ying-Fei1
1School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100080 2Basic Courses Department, Beijing Union University, Beijing 100101
Abstract At present, network structures derived from most gene regulatory network reconstruction methods are static, which do not change with time.However, in the cell cycle or different growth stages of an organismat, the topology of regulatory network changes significantly, which makes it difficult to understand the spatial-temporal mechanism of gene regulation. Therefore, an algorithm for the network is proposed based on time lagged Mutual Information (TLMI) and a kernel-reweighted l1-regularized logistic regression model. Two biological scenarios, the developmental stages of Drosophila melanogaster and the response of Saccharomyces cerevisiae to benomyl poisoning, are analyzed. The experimental results show that the proposed method reflects the impact of different cell states of interaction between genes and effectively acquires the dynamic effect of gene regulatory networks changing with time.
[1] Hecker M, Lambeck S, Toepfer S, et al. Gene Regulatory Network Inference: Data Integration in Dynamic Models-A Review. BioSystems, 2009, 96(1): 86-103 [2] Kim H, Lee J K, Park T. Boolean Networks Using the Chi-Square Test for Inferring Large-Scale Gene Regulatory Networks. BMC Bioinformatics, 2007.DOI:10.1186/1471-2105-8-37 [3] Zhou S H, Lafferty J, Wasserman L. Time Varying Undirected Graphs. Machine Learning, 2010, 80(2/3): 295-319 [4] Lèbre S, Becq J, Devaux F, et al. Statistical Inference of the Time-Varying Structure of Gene-Regulation Networks. BMC Systems Biology, 2010.DOI:10.1186/1752-0509-4-130 [5] Grzegorczy M, Husmeier D, Edwards K D, et al. Modelling Non-Stationary Gene Regulatory Processes with a Non-homogeneous Bayesian Network and the Allocation Sampler. Bioinformatics, 2008, 24(18): 2071-2078 [6] Robinson J W, Hartemink A J. Learning Non-Stationary Dynamic Bayesian Networks. Journal of Machine Learning Research, 2010, 11: 3647-3680 [7] Luscombe N M, Babu M M, Yu H, et al. Genomic Analysis of Regulatory Network Dynamics Reveals Large Topological Changes. Nature, 2004, 431: 308-312 [8] Más P. Circadian Clock Function in Arabidopsis Thaliana: Time beyond Transcription. Trends in Cell Biology, 2008, 18(6): 273-281 [9] Jia Y, Huan J. Constructing Non-stationary Dynamic Bayesian Networks with a Flexible Lag Choosing Mechanism. BMC Bioinformatics, 2010, 11(Supplement 6): S27 [10]Ahmed A, Xing E P. Recovering Time-Varying Networks of Dependencies in Social and Biological Studies. Proceedings of the National Academy of Sciences of the United States of America, 2009, 106(29): 11878-11883 [11] Song L, Kolar M, Xing E P. KELLER: Estimating Time-Varying Interactions between Genes. Bioinformatics, 2009, 25(12): i128-i136 [12] Zou M, Conzen S D. A New Dynamic Bayesian Network (DBN) Approach for Identifying Gene Regulatory Networks from Time Course Microarray Data. Bioinformatics, 2005, 21(1): 71-79 [13] Sacchi L, Bellazzi R, Porreca R, et al. Precedence Temporal Networks from Gene Expression Data // Proc of the 18th IEEE Symposium on Computer-Based Medical Systems. Dublin, Ireland, 2005: 109-114 [14] Xing Z Z, Wu D. Modeling Multiple Time Units Delayed Gene Regulatory Network Using Dynamic Bayesian Network // Proc of the 6th IEEE International Conference on Data Mining Workshops. Hong Kong, China, 2006: 190-195 [15] Cover T M, Thomas J A. Elements of Information Theory. New York, USA: Wiley-Interscience, 1991 [16] Chaitanker V, Ghosh P, Perkins E, et al. Time Lagged Information Theoretic Approaches to the Reverse Engineering of Gene Regulatory Networks. BMC Bioinformatics, 2010, 11(Supplement 6): S19 [17] Arbeitman M N, Furlong E E M, Imam F, et al. Gene Expression during the Life Cycle of Drosophila Melanogaster. Science, 2002, 297(5590): 2270-2275 [18] Guo F, Hanneke S, Fu W J, et al. Recovering Temporally Rewiring Networks: A Model-Based Approach // Proc of the 24th International Conference on Machine Learning. Corvallis, USA, 2007: 321-328 [19] Zhao W J, Serpedin E, Dougherty E R. Inferring Gene Regulatory Networks from Time Series Data Using the Minimum Description Length Principle. Bioinformatics, 2006, 22(17): 2129-2135 [20] Duan H, Nguyen H T. Distinct Posttranscriptional Mechanisms Regulate the Activity of the Zn Finger Transcription Factor Lame Duck during Drosophila Myogenesis. Molecular and Cellular Biology, 2006, 26(4): 1414-1423 [21] Cripps R M, Black B L, Zhao B, et al. The Myogenic Regulatory Gene Mef2 is a Direct Target for Transcriptional Activation by Twist during Drosophila Myogenesis. Genes & Development, 1998, 12(3): 422-434 [22] Sandmann T, Jensen L J, Jakobsen J S, et al. A Temporal Map of Transcription Factor Activity: Mef2 Directly Regulates Target Genes at All Stages of Muscle Development. Developmental Cell, 2006, 10(6): 797-807 [23] Elgar S J, Han J, Taylor M V. Mef2 Activity Levels Differentially Affect Gene Expression During Drosophila Muscle Development. Proceedings of the National Academy of Sciences of the United States of America, 2008, 105(3): 918-923 [24] Lucau-Danila A, Lelandais G, Kozovska Z, et al. Early Expression of Yeast Genes Affected by Chemical Stress. Molecular and Cellular Biology, 2005, 25(5): 1860-1868 [25] Salin H, Fardeau V, Piccini E, et al. Structure and Properties of Transcriptional Networks Driving Selenite Stress Response in Yeasts. BMC Genomics, 2008. DOI:10.1186/1471-2164-9-333 [26] Abdulrehman D, Monteiro P T, Teixeira M C, et al. YESTRACT: Providing a Programmatic Access to Curated Transcriptional Regulatory Associations in Saccharomyces Cerevisiae through a Web Services Interface. Nucleic Acids Research, 2011, 39(Supplement 1): D136-D140
2014, Vol. 27 
