Scientists Utilise AI to Identify Enzymes for Plastic Pollutant Degradation

Sydney (ANTARA) - Scientists in Australia are utilising artificial intelligence (AI)-based biotechnology to identify enzymes with the potential to degrade plastics and other harmful pollutants.

Researchers are combining machine learning technology with biochemistry to screen millions of enzymes stored in biological databases worldwide to identify candidates capable of decomposing hazardous pollutants, according to a recent statement from Murdoch University, Australia.

Joseph Boctor, a PhD candidate at Murdoch University, stated in a review published in the journal Nature Reviews: Earth & Environment that the key to finding the precise biological match to tackle each type of pollutant is likely hidden within existing data.

Machine learning tools can delve into millions of unexplored biological data points to find suitable enzyme candidates, Boetcor said. He added that the machine learning workflow utilises knowledge from previously characterised enzymes to predict how enzyme structures might interact with and degrade target pollutants.

Boctor noted that this approach could assist more rapidly in addressing pollutants that have already contaminated the environment, even as scientists develop bioplastic alternatives.

He stated that persistent pollutants, such as PFAS and microplastics, can cause health problems, with agricultural soil now reported to contain approximately 23 times more microplastics than the oceans.

The team at the Bioplastics Innovation Hub, under the auspices of Murdoch University—a collaboration with the Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia’s national science agency—is now focusing on testing, validating, and scaling up the identified enzymes for bioremediation efforts.