Karl E. Burgess

This paper introduces gsMOBO, a computational method that uses genome-scale metabolic models and Bayesian optimization to design cost-effective and productive culture media by optimizing nutrient combinations across high-dimensional spaces.

The paper uses active learning and metabolomics to optimise surfactin yield in Bacillus, achieving a 160% increase over a baseline.

PALS ranks significantly changing metabolite sets across conditions, showing robustness to missing data in metabolomics analyses.