Plastic waste build-up in the environment is an enormous ecological challenge. Indeed, 40% of plastic waste goes around collection systems and ends up residing in natural environments. Polyethylene terephthalate (PET) accounts for 12% of global solid waste. Enzymes that break down PET, PET hydrolases, have been previously developed but suffer from practical limitations with slow reaction rates and specific pH and temperature ranges.

Now, researchers have used a structure-based, machine learning algorithm to engineer a robust and active PET hydrolase. The enzyme, FAST-PETase (functional, active, stable, and tolerant PETase), can break down environment-throttling plastics that typically take centuries to degrade in just a matter of hours and days.

The research is published in Nature, in the article, “Machine learning-aided engineering of hydrolases for PET depolymerization.”

This discovery could help solve one of the world’s most pressing environmental problems: what to do with the billions of tons of plastic waste piling up in landfills and polluting our natural lands and water. FAST-PETase has the potential to supercharge recycling on a large scale that would allow major industries to reduce their environmental impact by recovering and reusing plastics at the molecular level.

“The possibilities are endless across industries to leverage this leading-edge recycling process,” said Hal Alper, PhD, professor in the McKetta department of chemical engineering at the University of Texas (UT), Austin. “Beyond the obvious waste management industry, this also provides corporations from every sector the opportunity to take a lead in recycling their products. Through these more sustainable enzyme approaches, we can begin to envision a true circular plastics economy.”

The project focuses on PET, a polymer found in most consumer packaging, including cookie containers, soda bottles, fruit, and salad packaging, as well as certain fibers and textiles.

Researchers used a machine learning model to generate novel mutations to the wild-type PETase that allows bacteria to degrade PET plastics. The model predicts which mutations in these enzymes would accomplish the goal of quickly depolymerizing post-consumer waste plastic at low temperatures.

The authors noted that their mutant and scaffold combination contains five mutations compared to wild-type PETase (N233K/R224Q/S121E from prediction and D186H/R280A from scaffold) and shows superior PET-hydrolytic activity relative to both wild-type and engineered alternatives between 30°C and 50°C and a range of pH levels.

The researchers also proved the effectiveness of the enzyme. They demonstrated that untreated, postconsumer-PET from 51 different thermoformed products can all be almost completely degraded by FAST-PETase in one week.

They also demonstrated a “closed-loop PET recycling process” by using FAST-PETase and resynthesizing PET from the recovered monomers.

“This work really demonstrates the power of bringing together different disciplines, from synthetic biology to chemical engineering to artificial intelligence,” said Andrew Ellington, PhD, professor in the Center for Systems and Synthetic Biology at UT Austin, whose team led the development of the machine learning model.

Research on enzymes for plastic recycling has advanced over the past 15 years. However, until now, no one had been able to make enzymes that could operate efficiently at low temperatures to make them both portable and affordable at large industrial scale. FAST-PETase can perform the process at less than 50°C.

Up next, the team plans to work on scaling up enzyme production to prepare for industrial and environmental applications. The researchers have filed a patent application for the technology and are eying several different uses. Cleaning up landfills and greening high waste-producing industries are the most obvious. But another key potential use is environmental remediation. The team is looking at a number of ways to get the enzymes out into the field to clean up polluted sites.

“When considering environmental cleanup applications, you need an enzyme that can work in the environment at ambient temperature. This requirement is where our tech has a huge advantage in the future,” Alper said.