This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: Databases around the world contain information on millions upon millions of enzymes that have the potential to degrade pollutants like plastic. Scientists at Murdoch University's Bioplastics Innovation Hub are combining machine learning technology and biochemistry to identify which of these enzymes have the potential to break down plastic and other harmful pollutants.
Ph.D. candidate Joseph Boctor explains in his latest review, published in Nature Reviews Earth & Environment, that the key to finding the right biological fit to combat each pollutant is likely hidden within existing data. While sorting through the data would previously have been an insurmountable task, AI technology is filling the gap at a critical time for the environment. "I strongly advocate that overengineering enzymes is a bad starting point that overlooks millions of years of evolution that have already produced lots of potential solutions to these contaminants," Boctor said.
"We need to look in the right place, and by leveraging machine learning tools, we are able to mine through millions of pieces of unexplored biological data to find the right candidate for the relevant task." These pipelines designed using machine learning use knowledge from previously characterized enzymes to predict how enzyme structures might interact with target pollutants and break them down. Boctor said while scientists were working on creating bioplastic alternatives for the future, these tools were helping to more rapidly address the pollutants already in our environment and causing active harm. "PFAS, microplastics and other persistent pollutants are not only industrially favorable but biologically active," he said.
"They trick our bodies by mimicking our own hormones and causing documented disruptions to health." Last year, Boctor conducted a comprehensive review highlighting that agricultural soils contained around 23 times more microplastics than oceans. The review also discussed microplastics and nanoplastics being detected in lettuce, wheat and carrot crops—and other additives in soil such as phthalates (linked to reproductive issues) and PBDEs (neurotoxic flame retardants linked to neurodegenerative disease, increased risks of stroke and heart attack and early death). With these pollutants making their way from soil to salad to humans, finding the answer to breaking them down has never been more urgent.
While technology saves the time scientists would spend searching through existing data, Boctor said the Bioplastics Innovation Hub team is channeling its energy into testing, validating and scaling the identified enzymes for bioremediation efforts. Joseph Boctor, Using machine learning with biochemical analysis to identify suitable enzymes for bioremediation applications, Nature Reviews Earth & Environment (2026). DOI: 10.1038/s43017-026-00839-2 Journal information: Nature Reviews Earth & Environment Swati Mestri holds a bachelor's degree in Electronics Engineering and has worked as a content editor since 2019.
She has experience editing research documents across technology, health care, and materials science, and has a particular interest in technology and space. Full profile → Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language.
Extract — continue reading at the source.
