Millions of years of evolution guide AI search for pollution-fighting enzymes
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.
Millions of years of evolution have equipped enzymes with the potential to break down pollutants like plastic, according to scientists at Murdoch University's Bioplastics Innovation Hub. Ph.D. candidate Joseph Boctor explains that AI technology is crucial in identifying these enzymes within vast databases of biological information, a task that would otherwise be impossible.
Boctor argues that focusing on overengineering enzymes overlooks the millions of years of evolution already producing potential solutions. Using machine learning, researchers can predict how enzyme structures might interact with specific pollutants and break them down. This approach not only addresses existing environmental harm but also aids in developing bioplastic alternatives.
PFAS, microplastics, and other persistent pollutants are particularly concerning due to their bioactivity and the disruption they cause to human health. While technology accelerates the search for solutions, Boctor emphasizes the need for experimental testing, validation, and scaling of identified enzymes for effective bioremediation.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
