Research Project Title:
Alzheimer's Disease Prediction by Cell-Free DNA Methylation
abstract:Alzheimer's disease (AD) is one of the leading causes of death worldwide for people over 65 years old because of its complex pathology and latent symptoms at its early stage. To date, early diagnosis of AD requires invasive and complicated methods, which have low sensitivity and are not readily perceptible with current technologies. This project will tackle this problem by seeking to develop a noninvasive blood-based diagnosis for early detection of AD. We will apply the current technologies and research in cell-free DNA (cfDNA) to identify predictive biomarkers for AD. Two types of statistical models, marker-based and tissue-proportion-based models, will use these selected biomarkers as predictors to infer the disease status of an individual. These models are trained using various machine learning algorithms on a cohort of 50 individuals with cfDNA methylation proles. We perform simulation to evaluate the choice of markers and cross-validation to evaluate the accuracy and precision of different disease-prediction models.
"Through SuperUROP, I want to apply my background in computer and data science, and molecular biology in conducting independent research. I hope to broaden my knowledge in life science and I am excited to contribute to the development of Alzheimer’s disease research."