My research sits at the intersection of computational biology, artificial intelligence and gene regulation. I develop computational and AI approaches to understand how cells acquire and change their identities, and how these processes are controlled by the transcriptome and epigenome.

A major focus of my research has been developing statistical and machine-learning methods for single-cell and spatial-omics, where increasingly large and complex datasets provide unprecedented views of cellular states and tissue organisation. My work aims to turn these data into interpretable biological knowledge by developing methods that identify cellular neighbourhoods, tissue organisation, regulatory programs and changes in cell state. 

My current research is increasingly focused on AI for regulatory and developmental biology. I am interested in building foundation models that integrate gene expression with multiple layers of epigenetic regulation and learn how cellular states change across developmental time and tissue space. Rather than simply cataloguing cell types, my goal is to develop predictive models that can uncover the regulatory logic underlying cell-fate decisions and generate experimentally testable hypotheses about how cells develop, transition between states and organise into tissues. 

Across my research, I place a strong emphasis on open and reusable computational methods, making software, models and analytical resources accessible to the broader research community.