The Tansey lab focuses on solving frontier problems in cancer data science through the development of innovative statistical machine learning methods. Our work answers fundamental statistical and computing questions raised in both clinical and pre-clinical cancer research. The methods we develop are motivated by open problems in cancer research. How do we discover effective combination therapies when the search space of possible combinations is vast? Can we identify new biomarkers of therapeutic sensitivity or resistance from observational electronic health records? How do we build powerful-yet-interpretable multimodal models of medical images, laboratory tests, and clinical records that can inform and improve treatment decisions in the clinic? The goal of our lab is to distill these kinds of important scientific questions into precise mathematical statements, then derive answers in the form of computationally efficient and statistically principled methods. We are interested in a number of areas in statistics and computer science, including graphical models, Bayesian methods, deep learning, hypothesis testing, conditional density estimation, spatial smoothing, active learning, and causal inference. Ultimately, we seek to lay the statistical and computational foundations necessary to deliver on the promise of precision medicine: delivering the right treatment, for the right patient, at the right moment, and at the right dose.

View available career opportunities in the lab here.