Data-driven decision making: Genetically tailored dietary recommendation for preventing metabolic and digestive disorders
With the concern of increasing incidence of metabolic and digestive disorders caused by unhealthy diet, this study aims to (1) identify risk factors that affect pathogenesis, (2) build mathematical models that can explain the processes involved in (1), and (3) develop dietary recommendation models/systems based on the models built in (2).
Using computational tools like machine learning, Mendelian randomization, and other statistical analyses, we can find out which genetic, environmental, and dietary factors play important roles in or associate with disease onset. Focusing on a few identified key factors, we will then investigate whether and how these factors work together in the process of disease pathogenesis. Based on all these findings, we will try to develop clinical biomarkers and build dietary recommendation models/systems tailored to the different needs of patients.
We anticipate that the project will take three years to accomplish above goals. Data pre-processing and series of association studies with genetics and environmental factors will be conducted in the first year. Then, finding the pattern with different data-driven approaches and retrospective cohort studies will be performed later on.
This research shall advance our understandings about the interplay of genetic and environmental factors that could explain the pathogenesis of metabolic and digestive disorders. We will develop an open web-based tool to differentiate the patients with metabolic and digestive disorders and then to recommend different diet patterns accordingly.