Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy
importance 5/10
ai assisted
Enzyme Catalysis and Immobilization industrial biotech stage: research
Problem
Engineering industrial enzymes that combine high activity with thermostability is difficult due to the stability-activity trade-off.
Why it matters
Better enzymes reduce costs and enable new industrial bioprocesses.
What the AI did
The iCASE strategy uses structure-based supervised machine learning to predict enzyme function and fitness, guiding variant engineering.
Results
Robust prediction across datasets; validated on four enzyme types; no numeric metrics stated
Impact
Provides a validated ML strategy to guide future enzyme fitness evolution research.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Nan Zheng, Yongchao Cai, Zehua Zhang, Huimin Zhou, Yu Deng, Shuang Du, Mengting Tu, Wei Fang et al. |
| Citations | 75 (OpenAlex, at import time) |
| References | 68 |
| Model or method | structure-based supervised machine learning (iCASE strategy) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-025-55944-5 |
| Open access | gold |
| Keywords | machine learning, enzyme engineering, thermostability, fitness prediction, epistasis |
Importance rating
5
real but narrower advance
Abstract calls high-activity stable enzymes a grail of enzyme evolution; validated ML strategy across four enzyme types is a real but pre-application industrial biotech advance.