Parametric and non-parametric gradient matching for network inference: a comparison

BMC Bioinformatics

  ^{1    2    3} 

[1] 0000 0001 2113 8111, grid.7445.2, Centre for Integrative Systems Biology and Bioinformatics, Department of Life Sciences, Imperial College London, SW7 2AZ, London, UK;0000 0001 2179 088X, grid.1008.9, Melbourne Integrative Genomics, School of BioScience & School of Mathematics and Statistics, University of Melbourne, 3010, Parkville Melbourne, Australia;0000 0001 2113 8111, grid.7445.2, Centre for Integrative Systems Biology and Bioinformatics, Department of Life Sciences, Imperial College London, SW7 2AZ, London, UK;0000 0004 0483 2525, grid.4567.0, Institute of Computational Biology, Helmholtz Center Munich, German Research Center for Environmental Health, 85764, Neuherberg, Germany;0000 0000 9497 5095, grid.419548.5, Max Planck Institute of Psychiatry, Kraepelinstr. 2-10, 80804, Munich, Germany;0000 0001 2113 8111, grid.7445.2, Centre for Integrative Systems Biology and Bioinformatics, Department of Life Sciences, Imperial College London, SW7 2AZ, London, UK;0000000106754565, grid.8096.7, School of Computing, Electronics, and Mathematics, Coventry University, CV1 2JH, Coventry, UK;

关键词: Systems biology;    Gradient matching;    Gene regulation;    Network inference;   

DOI  :  10.1186/s12859-018-2590-7

来源: publisher

【 摘 要 】

BackgroundReverse engineering of gene regulatory networks from time series gene-expression data is a challenging problem, not only because of the vast sets of candidate interactions but also due to the stochastic nature of gene expression. We limit our analysis to nonlinear differential equation based inference methods. In order to avoid the computational cost of large-scale simulations, a two-step Gaussian process interpolation based gradient matching approach has been proposed to solve differential equations approximately.ResultsWe apply a gradient matching inference approach to a large number of candidate models, including parametric differential equations or their corresponding non-parametric representations, we evaluate the network inference performance under various settings for different inference objectives. We use model averaging, based on the Bayesian Information Criterion (BIC), to combine the different inferences. The performance of different inference approaches is evaluated using area under the precision-recall curves.ConclusionsWe found that parametric methods can provide comparable, and often improved inference compared to non-parametric methods; the latter, however, require no kinetic information and are computationally more efficient.

【 授权许可】

CC BY