We have a broad interest in building data resources and developing computational algorithms and software for biomedical big data mining. Specifically, we focus on:
Dissecting fine-grained regulatory circuits and how they are perturbed in different diseases.
Predicting the impact and mechanisms of genome variations relevant to phenotypes and diseases at scale using computational simulations.
Estimating disease susceptibility risk by integrating vast amounts of individual genomic and phenotypic data.
Establishing genome foundation AI models for the early warning and prevention of respiratory and blood diseases.
Currently, we are most excited about developing advanced deep learning architectures and foundational models for genomics that are trained on extensive datasets and designed to be versatile enough to handle a wide range of specific applications.