Data-driven analysis and prediction of dynamic postprandial metabolic response to multiple dietary challenges using dynamic mode decomposition

Viktor Skantze; Mats Jirstrand; Carl Brunius; Ann-Sofie Sandberg; Rikard Landberg; Mikael Wallman

doi:10.3389/fnut.2023.1304540

Data-driven analysis and prediction of dynamic postprandial metabolic response to multiple dietary challenges using dynamic mode decomposition

Front Nutr. 2024 Jan 12:10:1304540. doi: 10.3389/fnut.2023.1304540. eCollection 2023.

Authors

Viktor Skantze^{1

2}, Mats Jirstrand¹, Carl Brunius², Ann-Sofie Sandberg², Rikard Landberg², Mikael Wallman¹

Affiliations

¹ Fraunhofer-Chalmers Research Centre for Industrial Mathematics, Gothenburg, Sweden.
² Department of Life Sciences, Division of Food and Nutrition Science, Chalmers University of Technology, Gothenburg, Sweden.

Abstract

Motivation: In the field of precision nutrition, predicting metabolic response to diet and identifying groups of differential responders are two highly desirable steps toward developing tailored dietary strategies. However, data analysis tools are currently lacking, especially for complex settings such as crossover studies with repeated measures.Current methods of analysis often rely on matrix or tensor decompositions, which are well suited for identifying differential responders but lacking in predictive power, or on dynamical systems modeling, which may be used for prediction but typically requires detailed mechanistic knowledge of the system under study. To remedy these shortcomings, we explored dynamic mode decomposition (DMD), which is a recent, data-driven method for deriving low-rank linear dynamical systems from high dimensional data.Combining the two recent developments "parametric DMD" (pDMD) and "DMD with control" (DMDc) enabled us to (i) integrate multiple dietary challenges, (ii) predict the dynamic response in all measured metabolites to new diets from only the metabolite baseline and dietary input, and (iii) identify inter-individual metabolic differences, i.e., metabotypes. To our knowledge, this is the first time DMD has been applied to analyze time-resolved metabolomics data.

Results: We demonstrate the potential of pDMDc in a crossover study setting. We could predict the metabolite response to unseen dietary exposures on both measured (R² = 0.40) and simulated data of increasing size ( $R_{max}^{2}$ = 0.65), as well as recover clusters of dynamic metabolite responses. We conclude that this method has potential for applications in personalized nutrition and could be useful in guiding metabolite response to target levels.

Availability and implementation: The measured data analyzed in this study can be provided upon reasonable request. The simulated data along with a MATLAB implementation of pDMDc is available at https://github.com/FraunhoferChalmersCentre/pDMDc.

Keywords: differential responders; dynamic mode decomposition; metabotypes; personalized nutrition; precision nutrition.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work has been supported by the Swedish Foundation for Strategic Research (SSF, FID17-0020) and the Swedish Research Council for Sustainable Development (FORMAS, 2016-00314), and has been developed as part of the FORMAS project “Diet × gut microbiome-based metabotypes to determine cardio-metabolic risk and tailor intervention strategies for improved health” (2017-02003) funded by the European Joint Programming Initiative “A Healthy Diet for a Healthy Life” (www.healthydietforhealthylife.eu) (RL, CB). All funders are gratefully acknowledged.