APPLICATIONS OF TECHNOLOGY:
Companies performing synthetic biology/metabolic engineering
- Unique uncertainty quantification approach
- High predictive accuracy
- Shorter development times
Researchers at Berkeley Lab’s Joint BioEnergy Institute and the Agile BioFoundry have developed a tool that uses machine learning to make further advancements in the field of synthetic biology. The patent-pending Automated Recommendation Tool (ART) uses probabilistic modeling techniques to guide metabolic engineering systematically without requiring a full mechanistic understanding of the biological system. Using sampling-based optimization, ART provides a set of recommended strains to be built in the next engineering cycle, alongside probabilistic predictions of their production levels. ART is built around a unique uncertainty quantification approach and has been demonstrated to have high predictive accuracy.
DEVELOPMENT STAGE: Proven principle
FOR MORE INFORMATION:
Zhang, J., Petersen, S.D., Radivojevic, T. et al. “Combining mechanistic and machine learning models for predictive engineering and optimization of tryptophan metabolism.” Nat Commun 11, 4880 (2020). https://doi.org/10.1038/s41467-020-17910-1
Radivojević, T., Costello, Z., Workman, K. Martin, H.G. (2020) “A Machine Learning Automated Recommendation Tool for Synthetic Biology.” Nature Communications 11, 4879 doi: 10.1038/s41467-020-18008-4
STATUS: Patent pending. Available for licensing or collaborative research.