I build machine learning models that decode immune receptor sequences into biologically meaningful patterns.

I lead the Computational Autoimmunity group, a bioinformatics research group focused on building machine learning models that decode immune receptor sequences into biologically meaningful patterns. Our work centres on uncovering hidden structure in adaptive immune repertoires, with a particular emphasis on T-cell receptor (TCR) sequences and their role in immune-mediated disease.

My research is organised around three interconnected themes:

1. Immune Repertoire Modelling and T-cell Specificity We develop computational approaches to identify and characterise patterns in T-cell receptor repertoires, aiming to understand how sequence-level variation encodes immune recognition, specificity, and dysfunction in autoimmune and inflammatory disease.

2. High-Dimensional Immune Profiling We integrate single-cell and multi-omics data, including single-cell RNA sequencing (scRNA-seq), to contextualise immune receptor patterns within cellular states and population dynamics, enabling a systems-level view of immune behaviour.

3. Machine Learning for Biological Structure Discovery We design and implement machine learning frameworks, including deep learning, generative models, and probabilistic approaches, to extract interpretable structure from complex immunological data, transforming high-dimensional measurements into usable biological representations.

My work is highly collaborative and closely connected to clinical and translational partners. By combining computational modelling with real-world data, we aim to contribute to a more precise understanding of immune function and dysfunction across disease contexts.

If you are interested in collaborating, please do not hesitate to reach out.