Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy
Abstract The pursuit of obtaining enzymes with high activity and stability remains a grail in enzyme evolution due to the stability-activity trade-off. Here, we develop an isothermal compressibility-assisted dynamic squeezing index perturbation engineering (iCASE) strategy to construct hierarchical...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-55944-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544405912125440 |
|---|---|
| author | Nan Zheng Yongchao Cai Zehua Zhang Huimin Zhou Yu Deng Shuang Du Mai Tu Wei Fang Xiaole Xia |
| author_facet | Nan Zheng Yongchao Cai Zehua Zhang Huimin Zhou Yu Deng Shuang Du Mai Tu Wei Fang Xiaole Xia |
| author_sort | Nan Zheng |
| collection | DOAJ |
| description | Abstract The pursuit of obtaining enzymes with high activity and stability remains a grail in enzyme evolution due to the stability-activity trade-off. Here, we develop an isothermal compressibility-assisted dynamic squeezing index perturbation engineering (iCASE) strategy to construct hierarchical modular networks for enzymes of varying complexity. Molecular mechanism analysis elucidates that the peak of adaptive evolution is reached through a structural response mechanism among variants. Furthermore, this dynamic response predictive model using structure-based supervised machine learning is established to predict enzyme function and fitness, demonstrating robust performance across different datasets and reliable prediction for epistasis. The universality of the iCASE strategy is validated by four sorts of enzymes with different structures and catalytic types. This machine learning-based iCASE strategy provides guidance for future research on the fitness evolution of enzymes. |
| format | Article |
| id | doaj-art-004e08625df84535837746ee979792d3 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-004e08625df84535837746ee979792d32025-01-12T12:30:41ZengNature PortfolioNature Communications2041-17232025-01-0116111310.1038/s41467-025-55944-5Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategyNan Zheng0Yongchao Cai1Zehua Zhang2Huimin Zhou3Yu Deng4Shuang Du5Mai Tu6Wei Fang7Xiaole Xia8Key Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversitySchool of Artificial Intelligence and Computer Science, Jiangnan UniversitySchool of Artificial Intelligence and Computer Science, Jiangnan UniversityKey Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan UniversityAbstract The pursuit of obtaining enzymes with high activity and stability remains a grail in enzyme evolution due to the stability-activity trade-off. Here, we develop an isothermal compressibility-assisted dynamic squeezing index perturbation engineering (iCASE) strategy to construct hierarchical modular networks for enzymes of varying complexity. Molecular mechanism analysis elucidates that the peak of adaptive evolution is reached through a structural response mechanism among variants. Furthermore, this dynamic response predictive model using structure-based supervised machine learning is established to predict enzyme function and fitness, demonstrating robust performance across different datasets and reliable prediction for epistasis. The universality of the iCASE strategy is validated by four sorts of enzymes with different structures and catalytic types. This machine learning-based iCASE strategy provides guidance for future research on the fitness evolution of enzymes.https://doi.org/10.1038/s41467-025-55944-5 |
| spellingShingle | Nan Zheng Yongchao Cai Zehua Zhang Huimin Zhou Yu Deng Shuang Du Mai Tu Wei Fang Xiaole Xia Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy Nature Communications |
| title | Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy |
| title_full | Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy |
| title_fullStr | Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy |
| title_full_unstemmed | Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy |
| title_short | Tailoring industrial enzymes for thermostability and activity evolution by the machine learning-based iCASE strategy |
| title_sort | tailoring industrial enzymes for thermostability and activity evolution by the machine learning based icase strategy |
| url | https://doi.org/10.1038/s41467-025-55944-5 |
| work_keys_str_mv | AT nanzheng tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT yongchaocai tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT zehuazhang tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT huiminzhou tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT yudeng tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT shuangdu tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT maitu tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT weifang tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy AT xiaolexia tailoringindustrialenzymesforthermostabilityandactivityevolutionbythemachinelearningbasedicasestrategy |