Adjusting for covariates and assessing modeling fitness in machine learning using MUVR2.

Motivation: Machine learning (ML) methods are frequently used in Omics research to examine associations between molecular data and for example exposures and health conditions. ML is also used for feature selection to facilitate biological interpretation. Our previous MUVR algorithm was shown to generate predictions and variable selections at state-of-the-art performance. However, a general framework for assessing modeling fitness is still lacking. In addition, enabling to adjust for covariates is a highly desired, but largely lacking trait in ML. We aimed to address these issues in the new MUVR2 framework. Results: The MUVR2 algorithm was developed to include the regularized regression framework elastic net in addition to partial least squares and random forest modeling. Compared with other cross-validation strategies, MUVR2 consistently showed state-of-the-art performance, including variable selection, while minimizing overfitting. Testing on simulated and real-world data, we also showed that MUVR2 allows for the adjustment for covariates using elastic net modeling, but not using partial least squares or random forest. Availability and implementation: Algorithms, data, scripts, and a tutorial are open source under GPL-3 license and available in the MUVR2 R package at https://github.com/MetaboComp/MUVR2.

Differential Responders to a Mixed Meal Tolerance Test Associated with Type 2 Diabetes Risk Factors and Gut Microbiota-Data from the MEDGI-Carb Randomized Controlled Trial.

The global prevalence of type 2 diabetes mellitus (T2DM) has surged in recent decades, and the identification of differential glycemic responders can aid tailored treatment for the prevention of prediabetes and T2DM. A mixed meal tolerance test (MMTT) based on regular foods offers the potential to uncover differential responders in dynamical postprandial events. We aimed to fit a simple mathematical model on dynamic postprandial glucose data from repeated MMTTs among participants with elevated T2DM risk to identify response clusters and investigate their association with T2DM risk factors and gut microbiota. Data were used from a 12-week multi-center dietary intervention trial involving high-risk T2DM adults, comparing high- versus low-glycemic index foods within a Mediterranean diet context (MEDGICarb). Model-based analysis of MMTTs from 155 participants (81 females and 74 males) revealed two distinct plasma glucose response clusters that were associated with baseline gut microbiota. Cluster A, inversely associated with HbA1c and waist circumference and directly with insulin sensitivity, exhibited a contrasting profile to cluster B. Findings imply that a standardized breakfast MMTT using regular foods could effectively distinguish non-diabetic individuals at varying risk levels for T2DM using a simple mechanistic model.

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

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 (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 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.