(301g) Bayesian Desirability Function Optimization of Cell Culture Media for Cellular Agriculture

The emerging field of cellular agriculture, in which bioreactors are used to grow mammalian cells for human consumption in leu of carbon-intensive animal agriculture, is predicated on use of inexpensive culture media. Designing such a media is a difficult task due to the number of metabolites in use, nonlinear component-wise interactions, and the difficulty in making measurements that reflect the complex dynamics of cell growth and survival. We address these issues by using a Bayesian optimization algorithm in which a Gaussian process model explores the media design space while maximizing a desirability function to find growth/cost-optimal media component concentrations. Using this acquisition function the uncertainty in the Gaussian process model us iteratively reduced while the desirability function is maximized. Multiple cell growth assays are used in concert, increasing the quality of the model predictions. The result was a methodology that discovered a medium with a 181% improvement in growth over the industry/control medium at the same medium cost using 38% fewer experiments than a traditional design-of-experiments method.