Quantitative

Metabolic Modeling

Our goal

We create the tools necessary to predict biological behavior, in order to produce renewable biofuels and bioproducts, and unlock the full potential of bioengineering. To this end, we combine machine learning, synthetic biology and automation with mathematical modeling.

You can find more detailed information on our research here (or click on the figures below for examples).

Machine Learning


Synthetic Biology


Automation


News

Hector Garcia Martin featured in National Public Radio (NPR) interview talking about synthetic biology, climate change and machine learning.

New paper about the opportunities in the intersection of synthetic biology, machine learning and automation

New paper measuring metabolic fluxes in R. opacus

You will develop machine-learning algorithms tailored to the needs of synthetic biology, enabling the production of renewable bioproducts through predictive bioengineering. The incumbent will focus on the development of “Explainable AI” (XAI) technologies, leveraging Deep Learning and other ensemble strategies in collaboration with Ben Brown. You will work as part of a collaborative team to integrate microbial phenotypic data (e.g. fluxomics, transcriptomics, proteomics, and metabolomics) into quantitative computational models able to predict and explain the outcomes of bioengineering interventions.

New paper leveraging machine learning to facilitate metabolic engineering.

Last updated April 29th 2019

Programs/grants: