Exploring the Metabolic Engineering Design Space with Laboratory Automation and Machine Learning

The use of living cells as microfactories for the production of desired biomolecules offers great promise, but the optimization of these processes is a high-dimensional problem. Genetic, metabolic, and environmental factors all influence the titer of the target molecule, leading to a vast design space. While important successes have been made in the field of industrial metabolic engineering, a rigorous framework to methodically explore the design space and identify truly optimal conditions is lacking.


People

Paul
Jensen

BME, ChE
Engineering

Ryan
Wyllie

BME
Engineering


Funding

Funding: $30K (2023)
Goal: Combine laboratory automation and machine learning to engineer a riboflavin-overproducing strain of the Gram-positive bacterium Streptococcus mutans.
Token Investors: Paul Jensen and Ryan Wyllie


Project ID: 1125