Data-driven strategies for the computational design of enzyme thermal stability: trends, perspectives, and prospects
Problem
Designing thermally stable enzymes for industry traditionally requires costly, arduous experiments (directed evolution, rational design) across an enormous protein sequence space.
Why it matters
Thermal stability determines whether biocatalysts are viable for industrial applications.
What the AI did
A review proposing a data-driven architecture for enzyme thermostability engineering, summarizing widely adopted datasets and machine learning-driven design approaches, plus remaining challenges.
Results
not stated in source
Impact
The review suggests machine learning can reduce costly experiments in enzyme design, but no new results are demonstrated.
Record
| Venue | Acta Biochimica et Biophysica Sinica |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Zhixin Dou, Yuqing Sun, Xukai Jiang, Xiuyun Wu, Yingjie Li, Bin Gong, Lushan Wang |
| Citations | 28 (OpenAlex, at import time) |
| References | 140 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3724/abbs.2023033 |
| Open access | diamond |
| Keywords | machine learning, enzyme thermostability, protein engineering, directed evolution, data-driven design |
Importance rating
significant — thousands to millions affected
Thermal stability determines industrial viability of biocatalysts; abstract frames it as key enzyme property but gives no scale numbers.