Murdoch University researchers use AI to find plastic-degrading enzymes

Researchers at Murdoch University in Australia are utilizing artificial intelligence and machine learning to identify enzymes capable of breaking down plastic and other hazardous pollutants. By combining biochemistry with machine learning, the team can filter through millions of enzymes in global biological databases to find candidates that can interact with and degrade specific pollutants.

Joseph Boctor, a PhD candidate at Murdoch University, noted in a review published in ‘Nature Reviews: Earth & Environment’ that the necessary biological solutions may already exist within unexplored data. The machine-learning pipelines use information from previously characterized enzymes to predict how new structures might interact with target pollutants like microplastics and PFAS.

The project is being conducted through the Bioplastics Innovation Hub, a collaboration between Murdoch University and the Commonwealth Scientific and Industrial Research Organisation (CSIRO). The team is currently focused on testing, validating, and scaling these identified enzymes for use in bioremediation efforts to address environmental contamination.