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

被引:3
作者
Skantze, Viktor [1 ,2 ]
Jirstrand, Mats [1 ]
Brunius, Carl [2 ]
Sandberg, Ann-Sofie [2 ]
Landberg, Rikard [2 ]
Wallman, Mikael [1 ]
机构
[1] Fraunhofer Chalmers Res Ctr Ind Math, Gothenburg, Sweden
[2] Chalmers Univ Technol, Dept Life Sci, Div Food & Nutr Sci, Gothenburg, Sweden
基金
瑞典研究理事会;
关键词
personalized nutrition; differential responders; metabotypes; dynamic mode decomposition; precision nutrition; PERSONALIZED NUTRITION;
D O I
10.3389/fnut.2023.1304540
中图分类号
R15 [营养卫生、食品卫生]; TS201 [基础科学];
学科分类号
100403 ;
摘要
MotivationIn 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.MotivationIn 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.MotivationIn 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.ResultsWe 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 (Rmax2= 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 implementationThe 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.
引用
收藏
页数:17
相关论文
共 50 条
[41]   Data-Driven Modeling & Analysis of Dynamic Wake for Wind Farm Control: A Comparison Study [J].
Chen, Zhenyu ;
Doekemeijer, Bart M. ;
Lin, Zhongwei ;
Xie, Zhen ;
Si, Zongming ;
Liu, Jizhen ;
Van Wingerden, Jan-Willem .
2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, :5326-5331
[42]   Multi-Resolution Analysis of Dynamical Systems using Dynamic Mode Decomposition [J].
Kutz, J. Nathan ;
Brunton, Steve ;
Fu, Xing .
WORLD CONGRESS ON ENGINEERING, WCE 2015, VOL I, 2015, :90-93
[43]   Modal analysis and interface tracking of multiphase flows using Dynamic Mode Decomposition [J].
Sashittal, Palash ;
Chiodi, Robert ;
Morgan, Timothy B. ;
Desjardins, Olivier ;
Heindel, Theodore J. ;
Bodony, Daniel J. .
INTERNATIONAL JOURNAL OF MULTIPHASE FLOW, 2022, 157
[44]   Modal analysis and interface tracking of multiphase flows using Dynamic Mode Decomposition [J].
Sashittal, Palash ;
Chiodi, Robert ;
Morgan, Timothy B. ;
Desjardins, Olivier ;
Heindel, Theodore J. ;
Bodony, Daniel J. .
International Journal of Multiphase Flow, 2022, 157
[45]   A dynamic mode decomposition technique for the analysis of non-uniformly sampled flow data [J].
Li, Binghua ;
Garicano-Mena, Jesus ;
Valero, Eusebio .
JOURNAL OF COMPUTATIONAL PHYSICS, 2022, 468
[46]   Camera-Based Dynamic Vibration Analysis Using Transformer-Based Model CoTracker and Dynamic Mode Decomposition [J].
Cheng, Liangliang ;
de Groot, Justin ;
Xie, Kun ;
Si, Yanxin ;
Han, Xiaodong .
SENSORS, 2024, 24 (11)
[47]   A path planning strategy for marine vehicles based on deep reinforcement learning and data-driven dynamic flow fields prediction [J].
Sang, Qiming ;
Tian, Yu ;
Jin, Qianlong ;
Yu, Jiancheng .
2021 6TH INTERNATIONAL CONFERENCE ON AUTOMATION, CONTROL AND ROBOTICS ENGINEERING, CACRE, 2021, :466-471
[48]   Analysis, Forecasting, and System Identification of a Floating Offshore Wind Turbine Using Dynamic Mode Decomposition [J].
Palma, Giorgio ;
Bardazzi, Andrea ;
Lucarelli, Alessia ;
Pilloton, Chiara ;
Serani, Andrea ;
Lugni, Claudio ;
Diez, Matteo .
JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2025, 13 (04)
[49]   Analysis of unsteady tip leakage flow in an axial compressor rotor using dynamic mode decomposition [J].
Wei, Xindi ;
Tang, Yumeng ;
Hou, Jiexuan ;
Liu, Yangwei .
JOURNAL OF THE GLOBAL POWER AND PROPULSION SOCIETY, 2024, 8 :405-420
[50]   Seizure Onset Localization From Ictal Intracranial EEG Data Using Online Dynamic Mode Decomposition [J].
McCumber, Matthew ;
Tyner, Kevin ;
Das, Srijita ;
Stacey, William C. ;
Smith, Garnett C. ;
Alfatlawi, Mustaffa ;
Gliske, Stephen V. .
2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,