ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties

Abstract The UniProt database is a valuable resource for biocatalyst discovery, yet predicting enzymatic functions remains challenging, especially for low-similarity sequences. Identifying superior enzymes with enhanced catalytic properties is even harder. To overcome these challenges, we develop ES...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Qian, Yuxuan Wang, Xibin Zhou, Tao Gu, Hui Wang, Hao Lyu, Zhikai Li, Xiuxu Li, Huan Zhou, Chengchen Guo, Fajie Yuan, Yajie Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-58521-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849734734923431936
author Hui Qian
Yuxuan Wang
Xibin Zhou
Tao Gu
Hui Wang
Hao Lyu
Zhikai Li
Xiuxu Li
Huan Zhou
Chengchen Guo
Fajie Yuan
Yajie Wang
author_facet Hui Qian
Yuxuan Wang
Xibin Zhou
Tao Gu
Hui Wang
Hao Lyu
Zhikai Li
Xiuxu Li
Huan Zhou
Chengchen Guo
Fajie Yuan
Yajie Wang
author_sort Hui Qian
collection DOAJ
description Abstract The UniProt database is a valuable resource for biocatalyst discovery, yet predicting enzymatic functions remains challenging, especially for low-similarity sequences. Identifying superior enzymes with enhanced catalytic properties is even harder. To overcome these challenges, we develop ESM-Ezy, an enzyme mining strategy leveraging the ESM-1b protein language model and similarity calculations in semantic space. Using ESM-Ezy, we identify novel multicopper oxidases (MCOs) with superior catalytic properties, achieving a 44% success rate in outperforming query enzymes (QEs) in at least one property, including catalytic efficiency, heat and organic solvent tolerance, and pH stability. Notably, 51% of the MCOs excel in environmental remediation applications, and some exhibited unique structural motifs and unique active centers enhancing their functions. Beyond MCOs, 40% of L-asparaginases identified show higher specific activity and catalytic efficiency than QEs. ESM-Ezy thus provides a promising approach for discovering high-performance biocatalysts with low sequence similarity, accelerating enzyme discovery for industrial applications.
format Article
id doaj-art-5a08a31d772a4dec8a99b43ebe5a15df
institution DOAJ
issn 2041-1723
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-5a08a31d772a4dec8a99b43ebe5a15df2025-08-20T03:07:43ZengNature PortfolioNature Communications2041-17232025-04-0116111110.1038/s41467-025-58521-yESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior propertiesHui Qian0Yuxuan Wang1Xibin Zhou2Tao Gu3Hui Wang4Hao Lyu5Zhikai Li6Xiuxu Li7Huan Zhou8Chengchen Guo9Fajie Yuan10Yajie Wang11School of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversityBeijing Academy of Artificial IntelligenceSchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversityWestlake Laboratory of Life Sciences and Biomedicine, Xihu DistrictSchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversitySchool of Engineering, Westlake UniversityAbstract The UniProt database is a valuable resource for biocatalyst discovery, yet predicting enzymatic functions remains challenging, especially for low-similarity sequences. Identifying superior enzymes with enhanced catalytic properties is even harder. To overcome these challenges, we develop ESM-Ezy, an enzyme mining strategy leveraging the ESM-1b protein language model and similarity calculations in semantic space. Using ESM-Ezy, we identify novel multicopper oxidases (MCOs) with superior catalytic properties, achieving a 44% success rate in outperforming query enzymes (QEs) in at least one property, including catalytic efficiency, heat and organic solvent tolerance, and pH stability. Notably, 51% of the MCOs excel in environmental remediation applications, and some exhibited unique structural motifs and unique active centers enhancing their functions. Beyond MCOs, 40% of L-asparaginases identified show higher specific activity and catalytic efficiency than QEs. ESM-Ezy thus provides a promising approach for discovering high-performance biocatalysts with low sequence similarity, accelerating enzyme discovery for industrial applications.https://doi.org/10.1038/s41467-025-58521-y
spellingShingle Hui Qian
Yuxuan Wang
Xibin Zhou
Tao Gu
Hui Wang
Hao Lyu
Zhikai Li
Xiuxu Li
Huan Zhou
Chengchen Guo
Fajie Yuan
Yajie Wang
ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
Nature Communications
title ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
title_full ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
title_fullStr ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
title_full_unstemmed ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
title_short ESM-Ezy: a deep learning strategy for the mining of novel multicopper oxidases with superior properties
title_sort esm ezy a deep learning strategy for the mining of novel multicopper oxidases with superior properties
url https://doi.org/10.1038/s41467-025-58521-y
work_keys_str_mv AT huiqian esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT yuxuanwang esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT xibinzhou esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT taogu esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT huiwang esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT haolyu esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT zhikaili esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT xiuxuli esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT huanzhou esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT chengchenguo esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT fajieyuan esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties
AT yajiewang esmezyadeeplearningstrategyfortheminingofnovelmulticopperoxidaseswithsuperiorproperties