Glycolysis-compatible urethanases for polyurethane recycling.

Recycling thermoset polyurethanes is hindered by their cross-linked structures and chemically stable urethane bonds. Although chemo-enzymatic approaches offer promise, known urethanases remain inefficient under industrial glycolysis conditions. Here, we present GRASE [graph neural network (GNN)–based recommendation of active and stable enzymes], a GNN-based framework that integrates self-supervised and supervised learning to identify efficient, glycolysis-compatible urethanases. Among these, AbPURase exhibited two orders of magnitude greater activity than previously known enzymes in 6 molar diethylene glycol, enabling near-complete depolymerization of commercial polyurethane at kilogram scale within 8 hours. Structural analysis revealed that a tightly packed hydrophobic core and proline-stabilized lid loop may confer AbPURase's stability and efficiency in harsh solvents. This work highlights how deep learning accelerates the discovery of biocatalysts with industrial potential and addresses a critical barrier in polyurethane recycling. Editor's summary: There have been major advances recently in the discovery and engineering of hydrolase enzymes for degradation of ester linkages in polymers such as polyethylene terephthalate. However, more resistant chemical linkages, such as those found in urethane polymers, present additional challenges. Chen et al. developed a computational pipeline for screening enzymes with potential activity and identified a highly active urethanase. The authors report a kilogram-scale chemo-enzymatic depolymerization of commercial polyurethane foam and show enzymatic degradation of N-aryl carbamates with nearly complete conversion within 8 hours. This discovery framework may be useful in identifying enzymes for the chemical and polymer recycling industry. —Michael A. Funk [ABSTRACT FROM AUTHOR]