Cluster Attention for Graph Machine Learning

arXiv:2604.07492v1 Announce Type: cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field

Accelerating the development of enzymatic degradation of polyesters such as poly(ethylene terephthalate) (PET) and poly(butylene terephthalate) (PBT) requires a rapid and parallelizable detection method. We developed a protein-based biosensor for the fast and accurate quantification of the PET and PBT degradation product, terephthalate (TPA), which we named TPAsense. Engineering TPAsense required overcoming low thermal stability and aggregation of the initial construct by introducing stabilizing mutations without disrupting the binding affinity to TPA. The sensor performance was validated by screening for the PBT degrading activity of a Leaf-branch Compost Cutinase (LCC) mutant library and comparing with liquid chromatography data. TPAsense detects nanomolar concentrations of TPA enabling shorter incubation times for screening workflows. In addition, a comparative analysis of PETase and PBTase kinetics was performed with TPAsense. Finally, we demonstrated the detection of PET microplastic in samples from a wastewater treatment plant by combining the biosensor and a PETase. TPAsense offers a platform to accelerate PETase and PBTase development for plastic waste recycling and detection of microplastic in the environment.

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd.   dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844