Despite synthetic biology’s remarkable potential to tackle important societal problems (e.g. produce renewable biofuels), its full potential is held back by our inability to engineer biological systems predictably. While novel tools allow us to edit a cell’s genome more efficiently than ever, the effect of these edits on cell biology are challenging to predict, highlighting the need for new design strategies.
In the Data Science and Modeling group, we use a combination of machine learning and mechanistic modeling to guide metabolic engineering and make synthetic biology a predictable endeavor. Our tools allow researchers to e.g. choose promoter combinations, genetic edits, DNA parts, and media to optimize production and enable commercially viable biofuels. We work very closely with other teams in JBEI to merge our predictive capabilities with new molecular biology tools and automation capabilities, such as microfluidics.
Projects
- Polyketide synthase (PKS) design.
- Development of Machine Learning algorithms for active learning.
- Machine Learning-guided semi automated media optimization.
- Machine Learning-guided metabolism optimization through CRISPRi.
- Combining Artificial Intelligence with microfluidics for DTBL cycle automation.
- BayFlux: Bayesian inference of metabolic flux.
Featured Media
- Machine Learning Takes on Synthetic Biology: Algorithms Can Bioengineer Cells for You
- Machine learning takes on synthetic biology
- Could Synthetic Biology Stop Global Warming? (NPR)
- New Machine Learning Approach Could Accelerate Bioengineering
- Synthetic Biology: Designing Life to Specifications | Using AI to Design Novel Cells
- Underbug: An Obsessive Tale of Termites and Technology
Featured Publications
- Biological research and self-driving labs in deep space supported by artificial intelligence. Nature Machine Intelligence (2023).
- Perspectives for self-driving labs in synthetic biology. Current Opinion in Biotechnology (2023).
- Scalable and automated CRISPR-based strain engineering using droplet microfluidics. Microsystems & Nanoengineering (2022).
- ClusterCAD 2.0: an updated computational platform for chimeric type I polyketide synthase and nonribosomal peptide synthetase design. Nucleic Acids Research, (2022).
- Microbial production of advanced biofuels. Nature Reviews Microbiology (2021).
- Machine learning for metabolic engineering: A review. Metabolic Engineering (2021)
- A machine learning Automated Recommendation Tool for synthetic biology. Nature Communications (2020)
- Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism. Nature Communications (2020)
- Chemoinformatic-guided engineering of polyketide synthases. Journal of the American Chemical Society (2020).
- “A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data.” Npj Systems Biology & Applications (2018)
- “ClusterCAD: a computational platform for type I modular polyketide synthase design.” Nucleic acids research 46.D1 (2017).