I'm a bioinformatician working at the Earlham Institute in Norwich, UK. My background is in plant genomics and bioinformatics, with a focus on wheat. I’ve worked extensively on generating high-quality genome assemblies from modern wheat cultivars as well as ancestral landraces, with the goal of capturing and understanding genetic diversity in this highly complex polyploid genome.
A challenge in this space is not just generating high-quality genomic data, but enabling researchers to ask integrated biological questions across structured datasets such as annotations, gene expression, and genetic variation. My current research explores how we can use large language models and agentic frameworks as a natural language interface to these data. In these systems the LLM coordinates specialised agents that query structured genomic resources, then reasons over their responses to generate transparent, biologically grounded natural language answers.
The goal is to lower the barrier to access and to allow reasoning over these datasets while maintaining rigor and reproducibility in wheat genomics research.
Coming soon.
You can reach me via email or connect with me online: