Joep P. J. Schmitz

This paper applies a machine learning-assisted recommendation strategy with exploration-exploitation balance to optimize p-coumaric acid production in yeast, achieving a 137% increase over parent strains.

The paper introduces a framework for training metabolic kinetic models using neural ODEs, demonstrating efficient parameterization on SBML models and glycolysis data.

The paper uses machine learning to optimize p-coumaric acid production in yeast through DBTL cycles, achieving a 68% increase in production.

This study optimizes p-coumaric acid production in Saccharomyces cerevisiae by combining statistical experimental design with process and genetic factors, achieving a 168-fold increase in titer.

The paper develops a physiologically informed kinetic model of yeast glycolysis connected to central metabolism, showing it captures experimental dynamics and explains pathway contributions under glucose perturbations.