The development of machine learning approaches in two-dimensional NMR data interpretation for metabolomics applications.

Metabolomics has been widely applied in human diseases and environmental science to study the systematic changes of metabolites over diverse types of stimuli. NMR-based metabolomics has been widely used, but the peak overlap problems in the one-dimensional (1D) NMR spectrum could limit the accuracy of quantitative analysis for metabolomics applications. Two-dimensional (2D) NMR has been applied to solve the 1D NMR overlap problem, but the data processing is still challenging. In this study, we built an automatic approach to process the 2D NMR data for quantitative applications using machine learning approaches. Partial least square discriminant analysis (PLS-DA), artificial neural network classification (ANN-DA), gradient boosted trees classification (XGBoost-DA), and artificial deep learning neural network classification (ANNDL-DA) were applied in combination with an automatic peak selection approach. Standard mixtures, sea anemone extracts, and mouse fecal samples were tested to demonstrate the approach. Our results showed that ANN-DA and ANNDL-DA have high accuracy in selecting 2D NMR peaks (around 90 %), which have a high potential application in 2D NMR-based metabolomics quantitively study, while PLS-DA and XGBoost-DA showed limitations in either data variation or overfitting. Our study built an automatic approach to applying 2D NMR data to routine quantitative analysis in metabolomics.

A modified Mediterranean-style diet enhances brain function via specific gut-microbiome-brain mechanisms.

Alzheimer's disease (AD) is a debilitating brain disorder with rapidly mounting prevalence worldwide, yet no proven AD cure has been discovered. Using a multi-omics approach in a transgenic AD mouse model, the current study demonstrated the efficacy of a modified Mediterranean-ketogenic diet (MkD) on AD-related neurocognitive pathophysiology and underlying mechanisms related to the gut-microbiome-brain axis. The findings revealed that MkD induces profound shifts in the gut microbiome community and microbial metabolites. Most notably, MkD promoted growth of the Lactobacillus population, resulting in increased bacteria-derived lactate production. We discovered elevated levels of microbiome- and diet-derived metabolites in the serum as well, signaling their influence on the brain. Importantly, these changes in serum metabolites upregulated specific receptors that have neuroprotective effects and induced alternations in neuroinflammatory-associated pathway profiles in hippocampus. Additionally, these metabolites displayed strong favorable co-regulation relationship with gut-brain integrity and inflammatory markers, as well as neurobehavioral outcomes. The findings underscore the ameliorative effects of MkD on AD-related neurological function and the underlying gut-brain communication via modulation of the gut microbiome-metabolome arrays.

Abnormalities in microbiota/butyrate/FFAR3 signaling in aging gut impair brain function.

Aging-related abnormalities in gut microbiota are associated with cognitive decline, depression, and anxiety, but underlying mechanisms remain unstudied. Here, our study demonstrated that transplanting old gut microbiota to young mice induced inflammation in the gut and brain coupled with cognitive decline, depression, and anxiety. We observed diminished mucin formation and increased gut permeability ("leaky gut") with a reduction in beneficial metabolites like butyrate because of decline in butyrate-producing bacteria in the aged gut microbiota. This led to suppressed expression of butyrate receptors, free fatty acid receptors 2 and 3 (FFAR2/3). Administering butyrate alleviated inflammation, restored mucin expression and gut barriers, and corrected brain dysfunction. Furthermore, young mice with intestine-specific loss of FFAR2/3 exhibited gut and brain abnormalities akin to those in older mice. Our results demonstrate that reduced butyrate-producing bacteria in aged gut microbiota result in low butyrate levels and reduced FFAR2/3 signaling, leading to suppressed mucin formation that increases gut permeability, inflammation, and brain abnormalities. These findings underscore the significance of butyrate-FFAR2/3 agonism as a potential strategy to mitigate aged gut microbiota-induced detrimental effects on gut and brain health in older adults.