- Associate Professor, Paul G. Allen School of Computer Science & Engineering
- Associate Professor, Genome Sciences
Understanding aging through explainable machine learning
The Lee lab seeks to develop explainable AI for life sciences. Explainable in this context means understanding which features drive the prediction. The Lee lab has been collaborating with the Kaeberlein lab to develop and apply machine learning to aging biology, with the initial goal of using noisy human gene expression and neuropathology data sets to predict genetic determinants of healthy aging. Exciting preliminary results from this collaboration have resulted in two funded grants, an R01 from NIA and a Collaborative Research award from NSF to further develop application in AI to aging research.