Network reconstruction based on grouped sparse nonlinear graphical granger causality

The ability to reconstruct complex networks plays an important role in our understanding of how nodes interact with each other and how information flows coordinate node's dynamic behaviors. Many similarity-based methods usually prefer steady-state data to time-series and perform poorly with the latter, such as pearson correlation and mutual information. Meanwhile, these similarity-based methods result in networks of non-directional structure. Moreover, various methods have been proposed based on linear dynamic models. One of the most representative methods is graphical granger causality. In this paper,we consider the problem of discovering network structure from time-series and introduce a novel method for reconstructing nonlinear causal interactions among nodes in complex networks, termed as grouped sparse nonlinear graphical granger causality, which is particularly fit for directionality and nonlinearity of real network systems. The performance of our proposed method is evaluated on synthetic datasets and the benchmark datasets of Dream3 Challenge4. Both the result of them demonstrate that our proposed method outperforms other methods.

[1]  Marco Grzegorczyk,et al.  Comparative evaluation of reverse engineering gene regulatory networks with relevance networks, graphical gaussian models and bayesian networks , 2006, Bioinform..

[2]  Naoki Abe,et al.  Grouped graphical Granger modeling for gene expression regulatory networks discovery , 2009, Bioinform..

[3]  Diogo M. Camacho,et al.  Wisdom of crowds for robust gene network inference , 2012, Nature Methods.

[4]  Xing-Ming Zhao,et al.  NARROMI: a noise and redundancy reduction technique improves accuracy of gene regulatory network inference , 2013, Bioinform..

[5]  Claudio Altafini,et al.  Comparing association network algorithms for reverse engineering of large-scale gene regulatory networks: synthetic versus real data , 2007, Bioinform..

[6]  Korbinian Strimmer,et al.  Learning causal networks from systems biology time course data: an effective model selection procedure for the vector autoregressive process , 2007, BMC Bioinformatics.

[7]  S. Frenzel,et al.  Partial mutual information for coupling analysis of multivariate time series. , 2007, Physical review letters.

[8]  Julio R. Banga,et al.  Reverse Engineering Cellular Networks with Information Theoretic Methods , 2013, Cells.

[9]  Nizamettin Aydin,et al.  A comprehensive comparison of association estimators for gene network inference algorithms , 2014, Bioinform..

[10]  G. Michailidis,et al.  Autoregressive models for gene regulatory network inference: sparsity, stability and causality issues. , 2013, Mathematical biosciences.

[11]  Jianfeng Feng,et al.  Granger causality vs. dynamic Bayesian network inference: a comparative study , 2009, BMC Bioinformatics.

[12]  Zalmiyah Zakaria,et al.  A review on the computational approaches for gene regulatory network construction , 2014, Comput. Biol. Medicine.

[13]  J. Collins,et al.  Inferring Genetic Networks and Identifying Compound Mode of Action via Expression Profiling , 2003, Science.

[14]  Jesper Tegnér,et al.  Reverse engineering gene networks using singular value decomposition and robust regression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Adam A. Margolin,et al.  Reverse engineering cellular networks , 2006, Nature Protocols.

[16]  Mariano J. Alvarez,et al.  Genome-wide Identification of Post-translational Modulators of Transcription Factor Activity in Human B-Cells , 2009, Nature Biotechnology.

[17]  Ali Shojaie,et al.  Discovering graphical Granger causality using the truncating lasso penalty , 2010, Bioinform..

[18]  Alberto de la Fuente,et al.  Discovery of meaningful associations in genomic data using partial correlation coefficients , 2004, Bioinform..

[19]  Gianluca Bontempi,et al.  Experimental assessment of static and dynamic algorithms for gene regulation inference from time series expression data , 2013, Front. Genet..

[20]  Alfonso Valencia,et al.  Emerging methods in protein co-evolution , 2013 .

[21]  João Ricardo Sato,et al.  Modeling gene expression regulatory networks with the sparse vector autoregressive model , 2007, BMC Systems Biology.

[22]  Martin A. Nowak,et al.  Inferring Cellular Networks Using Probabilistic Graphical Models , 2004 .

[23]  Daniele Marinazzo,et al.  Radial basis function approach to nonlinear Granger causality of time series. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.