Machine Learning of Designed Translational Control Allows Predictive Pathway Optimization in Escherichia coli
Problem
Optimizing multigene production pathways in microbes requires screening huge combinatorial ribosome binding site (RBS) libraries, and methods to predict optimal RBS combinations were lacking.
Why it matters
Microbial cell factories could produce valuable chemicals, but exhaustive library screening is slow and costly.
What the AI did
Machine learning algorithms modeled the RBS sequence-phenotype relationship from small representative subsets of large combinatorial libraries to accurately predict optimal high-producers.
Results
Boosted recombinant monoterpenoid production titers in E. coli by over 60% while screening under 3% of the library.
Impact
Peer-reviewed demonstration that ML can drastically cut screening effort in pathway optimization.
Record
| Venue | ACS Synthetic Biology |
|---|---|
| Published | 2018 |
| Work type | article |
| Authors | Adrian J. Jervis, Pablo Carbonell, María Vinaixa, Mark S. Dunstan, Katherine A. Hollywood, Christopher Robinson, Nicholas J. W. Rattray, Cunyu Yan et al. |
| Citations | 118 (OpenAlex, at import time) |
| References | 46 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1021/acssynbio.8b00398 |
| Open access | hybrid |
| Keywords | machine learning, RBS libraries, E. coli, pathway optimization, monoterpenoid production |
Importance rating
real but narrower advance
ML cuts combinatorial library screening to under 3% and boosts titers 60% in E. coli; a real but narrow advance for microbial cell factories, no scale stated.