Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production
Problem
Fatty acyl reductase enzymes were a bottleneck to high-flux microbial production of fatty alcohols, limiting bioproduction yields.
Why it matters
Fatty alcohols are industrial chemicals; better enzymes could enable sustainable microbial manufacturing of them.
What the AI did
A machine learning-driven approach iteratively searched the protein fitness landscape over ten design-test-learn rounds to engineer improved FAR enzymes.
Results
Engineered enzymes produced over twofold more fatty alcohols than starting natural sequences; top sequence showed enhanced catalytic rate on palmitoyl-ACP.
Impact
Peer-reviewed Nature Communications paper with 96 citations reporting a twofold production improvement via ML-guided engineering.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Jonathan C. Greenhalgh, Sarah A. Fahlberg, Brian F. Pfleger, Philip A. Romero |
| Citations | 96 (OpenAlex, at import time) |
| References | 49 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-021-25831-w |
| Open access | gold |
| Keywords | machine learning, enzyme engineering, fatty alcohols, protein fitness landscape, metabolic engineering |
Importance rating
real but narrower advance
Removing enzyme bottleneck for microbial fatty alcohol production, an industrial chemical; twofold yield gain stated but market/problem scale not quantified.