The enzymatic degradation of poly(ethylene terephthalate) (PET) offers a sustainable route for plastic recycling but is often hindered by limited enzyme adsorption on hydrophobic surfaces. Inspired by carbohydrate-binding modules (CBMs), which enhance enzyme performance on insoluble substrates, we developed a machine-learning-assisted pipeline to discover PET-binding modules from natural protein architectures. Integration of profile hidden Markov model-based homology searching with a supervised PET hydrolase machine-learning model (PETML) revealed that CBMs belonging to family 13, typically known for glycan recognition, were the most abundant CBMs associated with putative PET hydrolase homologs in the screened dataset. From 197 non-redundant candidates, high-throughput docking and molecular dynamics simulations prioritized tCBM13-1 (WP_357125140.1), which exhibited stable interfacial binding via cooperative aromatic and polar interactions. When fused to sfGFP, tCBM13-1 demonstrated superior adsorption (∼70%) and surface retention (∼90%) on PET powder at 37 °C and 45 °C, outperforming a benchmark CBM2. Co-displayed with FAST-PETase on the Escherichia coli (E. coli) surface using a dual-anchor system (OmpA and EhaA), tCBM13-1 enhanced PET film depolymerization by ∼ 43%, achieving a rate of 2793 μg/(d·cm2). The whole-cell catalyst retained > 64% of its initial activity after 10 cycles, indicating robust recyclability. This work integrates machine-learning-guided module mining with synthetic biology to engineer efficient, reusable biocatalysts for PET degradation, offering a scalable strategy for polymer biorecycling.
This study systematically compares molecular representations (Mordred, ECFP, ChemBERTa, UniMol2, etc.) across several machine learning architectures to predict CD-PFAS binding energies, demonstrating that molecular representation choice is critical for small-data host-guest binding prediction.
Cole Brzakala, O. Moultos, J. P. van der Hoek et al.· Journal of Chemical Informat...· 1 citation
The rapid emergence of metallo-b-lactamase-mediated antibiotic resistance has created an urgent need for new inhibitor discovery strategies. In this work, a machine-learning-guided workflow was developed to generate and prioritize potential inhibitors targeting NDM-1. A SMILES-based variational autoencoder was first pretrained on a broad molecular dataset to learn general chemical syntax and latent molecular representations. The model was then fine-tuned on an 8-hydroxyquinoline-enriched dataset to bias molecular generation toward zinc-binding chemical space relevant to metallo-β-lactamase inhibition. Generated compounds were processed through structural filtering and docking-based evaluation to create training data for downstream predictive modeling. Molecular fingerprints and physicochemical descriptors were then used to train XGBoost models for docking score prediction and classification of potential binders. Classification proved especially useful for prescreening because it avoided overinterpreting small differences in noisy docking scores while still enriching for compounds likely to perform well in docking. The resulting workflow demonstrates how generative modeling and supervised machine learning can be combined to reduce chemical search space, prioritize candidate inhibitors, and guide computational drug discovery. Although experimental validation remains necessary, this approach provides a scalable framework for identifying promising zinc-binding compounds for further molecular simulation and inhibitor development that can be expanded in future studies.
Anthony M. Baudino, Kari L. Stone· AI Chemistry· 0 citations
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.
Chaofeng Shao, Xiaowei Shen, Jianyu Long et al.· Synthetic and Systems Biotec...· 0 citations
Mycosporine-like amino acids (MAAs) are functional secondary metabolites renowned for their exceptional UV protection, antioxidant properties, and environmental resilience. In the MAA biosynthetic pathway, MysD is the pivotal enzyme mediating the chemical transition of the cyclohexenone core into a cyclohexenimine-type scaffold. This MysD-catalyzed secondary amino acid modification not only dictates the chemical diversity of MAAs but also facilitates a crucial bathochromic shift, moving the UV absorption maximum from the UVB range into the high-penetration UVA region. Despite its significance, MysD remains the rate-limiting step in the biosynthesis of iminomycosporine-like amino acids. To date, only eight MysD enzymes have been heterologously validated, with even fewer subjected to biochemical characterization, which severely restricts the use of conventional supervised machine learning for enzyme discovery. In this study, we developed an integrated, data-driven screening framework combining Sequence Similarity Networks (SSN), deep representation learning (UniRep), and Positive-Unlabeled Bagging (PU Bagging) to explore the MysD functional landscape. This pipeline effectively compressed the search space from approximately 951 unannotated homologues to a prioritized 42 candidates. Experimental validation led to the discovery of AdMysD from Aphanothece hegewaldii, which exhibited a 3-fold increase in catalytic efficiency for porphyra-334 production relative to the previously established benchmark, NlMysD. Notably, while demonstrating a primary preference for l-Thr, AdMysD displayed significant substrate promiscuity by accepting l-Ser, l-Ala, and l-Cys to produce iminomycosporine derivatives. Our findings provide a biocatalytic tool for the efficient production of MAAs and demonstrate the potential of a PU-learning-based prioritization strategy for identifying rare enzyme families with sparse functional annotations.
Results indicate that supervised machine learning can help guide the construction of high-value enzyme libraries with expanded catalytic scope, and suggest that supervised machine learning can help guide the construction of high-value enzyme libraries with expanded catalytic scope.
Ravi G. Lal, Jason Yang, Ziyan Zhang et al.· bioRxiv· 0 citations
Poly(ethylene terephthalate) (PET) hydrolases have emerged as promising biocatalysts for closed-loop plastic recycling. Among the most efficient enzymes reported to date, LCC-ICCG exhibits exceptional PET-depolymerization performance under industrially relevant conditions. However, the molecular basis for its superior activity relative to engineered PETases such as FAST-PETase and HotPETase remains incompletely understood. Here, we combine microsecond-scale molecular dynamics simulations, quantum mechanical cluster calculations, pre-reaction-state analysis, noncovalent-interaction mapping, and distortion/interaction activation strain analysis to compare LCC-ICCG with FAST-PETase and HotPETase. The simulations show that LCC-ICCG samples catalytically competent pre-reaction-state geometries more frequently, mainly because V212 reshapes the local environment around the scissile ester. This residue relieves steric congestion, supports weak C–H···O guided substrate preorganization, and reinforces both the Asp-His catalytic dyad and the W190-associated pocket architecture. Density functional theory calculations further indicate that this preorganized active site lowers the acylation barrier to 15.5 kcal/mol by reducing substrate distortion and strengthening transition-state interactions. High-temperature simulations show that LCC-ICCG better preserves near-attack geometries at 350 K, linking thermal robustness to sustained catalytic preorganization. Moreover, reciprocal I208V mutations in IsPETase-derived enzymes enrich pre-reaction-state populations, supporting the transferability of the V212-centered design principle. Overall, these results establish pre-reaction-state stabilization as a key determinant of PET-hydrolase efficiency and provide mechanistic design rules for engineering next-generation PET depolymerases.