SYDNEY, Oct. 5 — Scientists in Australia are using artificial intelligence biotechnology to identify enzymes that could potentially break down plastic and other harmful pollutants.
Researchers are combining machine learning technology and biochemistry to filter millions of enzymes stored in biological databases around the world and identify candidates that could degrade harmful pollutants, according to a recent statement from Australia’s Murdoch University.
Murdoch University PhD candidate Joseph Boctor said in his review published in Nature Reviews: Earth & Environment that the key to finding the right biological fit to combat each pollutant was likely hidden within existing data.
Machine-learning tools could mine millions of unexplored biological data to find suitable enzyme candidates, Boctor said, adding the machine-learning pipelines use knowledge from previously characterized enzymes to predict how enzyme structures could interact with target pollutants and break them down.
Boctor said the approach could help to more rapidly address pollutants already present in the environment while scientists develop bioplastic alternatives.
He said persistent pollutants such as PFAS and microplastics could cause health problems, with agricultural soils now containing around 23 times more microplastics than oceans.
The team at Murdoch University’s Bioplastics Innovation Hub, a collaboration with the Commonwealth Scientific and Industrial Research Organization, Australia’s national science agency, is now focusing on testing, validating and scaling the identified enzymes for bioremediation efforts. (Namibia Daily News/Xinhua)
