We design experimental and computational models of early cancer to (i) capture mutational and transcriptional trajectories over time at single-cell resolution, and (ii) quantify how different driver mutation interactions lead to cooperation or competition amongst cells.
Population Biomedicine & Causality: We develop machine learning techniques for applications to large-scale biomedical data, such as scRNA-seq and the UK Biobank. For example, we develop (non-)parametric probabilistic and neural network approaches to (i) extract higher-order interactions from gene expression data, and (ii) quantify causal interactions amongst DNA variants leading to physiological outcomes.