2018/01/23 by Takoua Jendoubi, Jendoubi, Takoua, Timothy M. D. Ebbels +1
Biochemistry, Genetics and Molecular Biology · #Applications (stat.AP) #FOS: Computer and information sciences #Gene Regulatory Network Analysis #Metabolomics and Mass Spectrometry Studies #Microbial Metabolic Engineering and Bioproduction
paper · pdf · doi:10.48550/arxiv.1801.07767
openalex publication_date 2018/01/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Metabonomics time-course experiments provide the opportunity to understand\nthe changes to an organism by observing the evolution of metabolic profiles in\nresponse to internal or external stimuli. Along with other omic longitudinal\nprofiling technologies, these techniques have great potential to complement the\nanalysis of complex relations between variations across diverse omic variables\nand provide unique insights into the underlying biology of the system. However,\nmany statistical methods currently used to analyse short time-series omic data\nare i) prone to overfitting or ii) do not take into account the experimental\ndesign or iii) do not make full use of the multivariate information intrinsic\nto the data or iv) unable to uncover multiple associations between different\nomic data. The model we propose is an attempt to i) overcome overfitting by\nusing a weakly informative Bayesian model, ii) capture experimental design\nconditions through a mixed-effects model, iii) model interdependencies between\nvariables by augmenting the mixed-effects model with a conditional\nauto-regressive (CAR) component and iv) identify potential associations between\nheterogeneous omic variables .\n