Artificial intelligence-assisted mining of polyethylene terephthalate hydrolases

Quyuan Xiong; Guangyu Liu; Shipeng Gao; Yuechuo Hao; Cheng Li; Jingwen Liu; Jiasong Huang; Anthony J Sinskey; Yan Zhang; Xiong Chen; Yafang Sun; Xueyun Zheng

doi:10.1016/j.nbt.2026.03.010

Artificial intelligence-assisted mining of polyethylene terephthalate hydrolases

N Biotechnol. 2026 Apr 3:93:246-263. doi: 10.1016/j.nbt.2026.03.010. Online ahead of print.

Authors

Quyuan Xiong¹, Guangyu Liu¹, Shipeng Gao², Yuechuo Hao³, Cheng Li⁴, Jingwen Liu¹, Jiasong Huang¹, Anthony J Sinskey⁴, Yan Zhang⁵, Xiong Chen⁶, Yafang Sun⁷, Xueyun Zheng⁸

Affiliations

¹ Key Laboratory of Fermentation Engineering (Ministry of Education), Hubei University of Technology, Wuhan 430068, China.
² School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China.
³ Guangdong Key Laboratory of Fermentation and Enzyme Engineering, South China University of Technology, Guangzhou 510006, China.
⁴ Department of Biology, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
⁵ Angel Yeast Co., Ltd, Yichang 443000, China.
⁶ Key Laboratory of Fermentation Engineering (Ministry of Education), Hubei University of Technology, Wuhan 430068, China. Electronic address: chenxiong@mail.hbut.edu.cn.
⁷ Angel Yeast Co., Ltd, Yichang 443000, China. Electronic address: sun102924@163.com.
⁸ Key Laboratory of Fermentation Engineering (Ministry of Education), Hubei University of Technology, Wuhan 430068, China. Electronic address: xueyunz@hbut.edu.cn.

PMID: 41937001
DOI: 10.1016/j.nbt.2026.03.010

Abstract

Polyethylene terephthalate (PET) hydrolases efficiently hydrolyze the ester bonds in PET, converting it into valuable monomers or oligomers, offering a sustainable biological solution to global PET plastic pollution. However, the large-scale development of high-performance PET hydrolases remains challenging due to limitations in traditional enzyme resource mining methods, including low throughput and lengthy cycles. Recent advances in artificial intelligence (AI) provide novel methodologies to overcome these challenges. This review systematically summarizes how AI empowers the high-throughput screening of PET hydrolases from massive biological databases, while allowing the accurate prediction of enzyme structures and functions. Furthermore, it critically analyzes AI-driven strategies for enzyme molecular engineering and highlights the emerging frontier of AI-assisted de novo enzyme design. By systematically evaluating the advantages and challenges of AI models in the research of PET hydrolases, this review provides an integrated technical framework and theoretical foundation to guide future innovation in enzyme mining and plastic biodegradation.

Keywords: Artificial intelligence; De novo synthesis; Engineering; High-throughput screening; PET hydrolases; Prediction.

Publication types

Review