Profile
Project Title:
Unlocking Drug Discovery Using AI to Explore use of Global Plant Diversity
Project Summary:
More than 25% of prescription medicines, such as anticancer, analgesic, and antimalarial drugs, come from plants, but fewer than 15% of plant species have been chemically studied. I utilise artificial intelligence to bridge this gap by guiding models on prioritising geographic locations, plant species, and predicting types of molecules. My research integrates global biodiversity, environmental, and phylogenetic data to pinpoint underexplored areas that probably host chemically diverse plant lineages. My models evaluate species from these regions by considering evolutionary relationships, ecological traits, and metabolite profiles to identify those most likely to generate new bioactive compounds. Additionally, by combining metabolomic and genomic data, they can predict particular molecules that either resemble existing drugs or broaden natural chemical diversity. Through this approach, I aim to move discovery from trial-and-error to strategic inference, using data to guide future laboratory collaborations. With biodiversity loss accelerating, my research offers a timely, AI-driven approach to uncovering nature’s hidden pharmacopoeias and supporting sustainable drug discovery
Supervisors:
Dr Cedric John
Dr Bob Alkin