Can Machine Learning Revolutionize Directed Evolution of Selective Enzymes?
importance 5/10
ai assisted
Enzyme Catalysis and Immobilization enzyme engineering stage: research
Problem
Directed evolution of enzymes generates huge numbers of variants, making it slow to find enzymes with improved stereoselectivity and activity.
Why it matters
Selective enzymes are costly catalysts for industry and medicine, and faster engineering could cut development time and waste.
What the AI did
The review surveys machine learning algorithms (ASRA, Innov'SAR) that guide saturation mutagenesis at binding-pocket sites to improve stereoselectivity and activity.
Results
not stated in source
Impact
The paper argues ML can guide directed evolution, but cites no new measured results of its own.
Record
| Venue | Advanced Synthesis & Catalysis |
|---|---|
| Published | 2019 |
| Work type | article |
| Authors | Guangyue Li, Yijie Dong, Manfred T. Reetz |
| Citations | 122 (OpenAlex, at import time) |
| References | 84 |
| Model or method | ASRA, Innov'SAR |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1002/adsc.201900149 |
| Open access | bronze |
| Keywords | machine learning, directed evolution, enzymes, stereoselectivity, saturation mutagenesis |
Importance rating
5
real but narrower advance
ML-guided directed evolution of selective enzymes aids industrial and medical catalysis; abstract cites ASRA/Innov'SAR suitability but no scale, results, or impact figures.