Deep Learning–driven synergistic engineering of PET hydrolase for post-consumer PET depolymerization
Abstract
Enzymatic depolymerization of polyethylene terephthalate (PET) offers a promising route to mitigate the increasingly severe problem of plastic pollution. However, the development of highly efficient PET hydrolases capable of processing post-consumer PET remains a critical challenge. Recent advances in artificial intelligence (AI) provide new opportunities to accelerate the enzyme engineering of PET hydrolases. Here, we report a systematic computational redesign of the PET hydrolase NI (ThcCut1-AICCG-H185N/F189I) using the deep-learning framework, EITLEM-Kinetics. By integrating mutation free-energy constraints with kinetic parameter prediction, the framework enables simultaneous optimization of catalytic activity and thermostability. A total of nine beneficial substitution sites were identified and experimentally validated that overcoming the activity–stability trade-off. Combinatorial iteration yielded an optimal variant, NI-E65K/H107Y/A2R/L33F (NI-KYRF), which exhibited an 80% and 90% increase in depolymerization activity toward Gf-PET film and one-step pretreated post-consumer PET (pc-PET powder), respectively, along with a 2.61 °C increase in melting temperature (Tm). NI-KYRF displayed a specific activity of 665 μmolTPAeq h−1 mgenzyme−1, representing 2.0- and 1.48-fold improvements over representative high-performance PET hydrolases ICCG and TurboPETase. The depolymerization performance of NI-KYRF towards various post-consumer PET wastes and polyester plastics was significantly improved. At 70 °C, it achieved a 95.5% depolymerization conversion of pc-PET powder within 24 h, and for untreated post-consumer PET film, the conversion reached 80.1%, representing a 2.1-fold improvement in depolymerization efficiency over the parental NI. In addition, enhanced activity toward polyesters plastics, including PBAT and PBT, indicates an expanded substrate scope. Molecular dynamics simulations and structural analysis reveal that these mutations enhance enzyme performance through synergistic mechanisms. Overall, this study establishes a deep learning–guided computational design framework based on EITLEM-Kinetics and demonstrates its effectiveness and broad potential for engineering high-performance PET hydrolases.