Accelerating engineered microbe optimization through machine learning and multi-omics datasets
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
This project demonstrated the use of a combination of multi-omics data with deep learning and a high-throughput Design- Build-Test-Learn (DBTL) cycle to improve the production of malonic acid, a versatile product with a large market. The project leveraged the unique capabilities of both Lygos and the Agile BioFoundry (ABF): Lygos provided its expertise efficiently designing, building, and cultivating P. kudriavzevii strains; LBNL, PNNL, and NTESS provided multi-omics analysis in the Test phase, LBNL provided machine learning techniques in the Learn phase to analyze the -omics datasets and make recommendations so as to increase malonic acid production in the next DBTL cycle. This project is the first to use large amounts of multi-omics time-series data to feed deep learning models, creating around 80,000 data points in a single DBTL cycle. This project has 1) demonstrated the utility of combining deep learning and multi-omics data sets by improving the production of malonic acid two fold, 2) created a large time-series datasets to be released publicly for external development of new machine learning algorithms, and 3) shown that supply chain problems, strain building bottlenecks, and adaptation times for new ML approaches are key obstacles for fast DBTL cycle times.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Teselagen Biotechnology, San Francisco, CA (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Office of Sustainable Transportation. Bioenergy Technologies Office (BETO)
- DOE Contract Number:
- AC02-05CH11231
- OSTI ID:
- 2324610
- Report Number(s):
- LBNL-2001552; AWD00003239; FP00006785
- Country of Publication:
- United States
- Language:
- English
Similar Records
Developing Multi-Gene CRISPRa/I Programs to Accelerate DBTL Cycles in ABF Hosts Engineered for Chemical Production (CRADA 468)
Application of Machine Learning to Improve Biobased Glucaric Acid Production (CRADA 504)