Our research interests are in the area of machine learning, biology and medicine. We are developing machine learning algorithms that will enable the use of an individual’s comprehensive biological information to predict or diagnose diseases, and to find or develop the best therapy for that individual.

Our research focuses on the following areas:

  • Systems biology of human diseases, concerned with the inference of molecular networks underlying diseases to define disease subtypes, investigate the disease-associated genes and disease pathways, which may in turn identify novel therapeutic targets. Understanding these principles will help us tailor treatment strategies for individual patients. Particularly, we focus on Alzheimer's disease, Acute Myeloid Leukemia, cardiovascular diseases, and type 2 diabetes.
  • Fundamental machine learning research, focused on topics related to robustly learning the structure of probabilistic graphical models, sparse feature selection and feature learning.
  • Predictive medicine, data-driven predictive modeling of various disease conditions for early detection, for instance, incidence of Pneumonia in the patients at ICU and diagnosis based on medical image data.
  • Systems genetics, with the goal of gaining a systems-level understanding of how genetic variation leads to phenotypic changes in complex molecular networks. To accomplish this, we have turned to the yeast, plant and mouse system.

We have close collaborations with UW Medicine, UW Genome Sciences, UW Medical Center, Fred Hutchinson Cancer Research Center, UW Cardiovascular Health Research Unit, Institute for Systems Biology, UCLA Medicine, and Stanford. This enables us to access various types of high-throughput data. The short-distance collaborations also facilitate experimental or clinical validation of the hypotheses generated by our computational models, which will amplify the impact of our approaches.