Tianlu Chen

MetAgeFormer is a transformer-based model pre-trained on metabolomic data to estimate biological age and identify metabolic subtypes associated with disease risk.

This study shows that caloric restriction increases malate and related metabolites, remodels gut microbiota energy metabolism, and promotes host autophagy through a functional metabolic network.

This study shows that hyocholic acid species are associated with metabolic health and glucose homeostasis, and their levels predict diabetes risk in humans.

GSimp is a Gibbs sampler-based method for imputing left-censored missing values in metabolomics data, showing superior performance in accuracy and statistical analysis.

The paper compares imputation methods for metabolomics data with missing values and proposes a strategy with a web-tool.