Approved Research

Investigating Food-Drug Interactions for Cardiometabolic Disease Risks Using Machine Learning, Mendelian Randomization, and PBPK Models

Lay summary

Aim:

This research project aims to understand the effects of interactions between food and drugs, as well as between different food components, on the risk of developing cardiometabolic diseases and complications by using advanced methods such as machine learning, Mendelian randomization, and physiologically based pharmacokinetic modeling. This study also aims to uncover the underlying mechanisms and provide valuable tools for clinical applications and dietary guidance for the prevention and treatment of cardiometabolic diseases.

Scientific Rationale:

Cardiometabolic diseases are a global health concern influenced by various factors, including drugs and dietary intake. However, the precise nature of interactions between food and drugs and different food components remains unclear. Conventional approaches do not account for these interactions, limiting our understanding of their effects on disease risks. This research aims to bridge this knowledge gap by employing advanced techniques to explore long-term effects and mechanisms of interactions.

Methodology:

The research will use data from the UK Biobank to investigate the impact of drugs and daily food intake on cardiometabolic diseases. Machine learning algorithms and feature selection methods will be employed to identify interactions and develop predictive models. Mendelian randomization will examine causal effects by analyzing genetic variants associated with drug use and food consumption. Additionally, physiologically based pharmacokinetic modeling will be used to explore the underlying mechanisms of interactions.

Expected Impact:

By better understanding food-drug and food-food interactions, this research project can significantly contribute to the prevention and treatment of cardiometabolic diseases. The findings would inform clinical strategies and dietary guidance by providing insights into specific interactions, mechanisms, and quantitative tools.

Our project is expected to last for about three years and has the potential to have a significant impact on public health policies and guidelines.