computational genomics & biomedical data science
We develop and apply
computational data-driven approaches
to unravel how our genome
relates to health and disease.
We are a team of biologists, statisticians, mathematicians, physicists, engineers, and data scientists. We develop computational methods to turn big data into actionable biomedical insights.
 To gain more nuanced insights into the molecular mechanisms underlying health & disease.
 To use these insights to link an individual's genomic profiles to a precise assessment of her/his clinical traits, risks, and outcomes.
Big data collections contain valuable signals that can help fill critical gaps in our biomedical knowledge. We use statistics & machine learning to mine these data and build predictive models. These models then help us link genes & cellular mechanisms to various aspects of health & disease. Find out more about our research.
News | Posts
Some Recent Publications
Supervised-learning is an accurate method for network-based gene classification.
A Computational Framework for Genome-wide Characterization of the Human Disease Landscape.
Integrative networks illuminate biological factors underlying gene-disease associations.
Current Genetic Medicine Reports.
[ more ]