My research concerns how to use artificial intelligence for protein engineering — the design of protein variants with desirable properties. For example, in therapeutic discovery, after a promising antibody candidate has been found, it is often necessary to reduce immunogenicity, eliminate aggregation or increase plasma half-life while preserving binding affinity. These pursuits have traditionally been carried out experimentally, which has limited exploration to a small number of tested variants. In recent years, novel computational tools have arisen that can screen hundreds of thousands or millions of variants in short times.

My primary focus is in integrating biological perspectives into deep learning structures, a strategy to extract the maximum amount of value from the typically small datasets found in life sciences. I work closely with Prof. Charlotte M. Deane and Prof. Yee Whye Teh.

Some topics of interest where I would welcome collaborations or scientific discussions:

• Protein stability and solubility engineering
• Protein expression optimization
• Scaffold and binder design
• Enzyme design and optimization
• Models of protein folding and dynamics

As an interdisciplinary researcher, I have previously explored some other areas of work. Some of my previous work has explored how to use generative AI to optimise molecular properties, how quantum computing can be applied to drug discovery, whether deep learning methods used to predict protein structures can also predict protein folding, or how to model weak interactions in molecular systems.