Researchers Use AI to Design Plastic-Eating Enzyme

Researchers Use AI to Design Plastic-Eating Enzyme

The accumulation of plastics in the environment is a problem that won’t solve itself, at least not on any time scale relevant to humanity. These materials are designed to be durable and long-lasting, and current methods of recycling barely put a dent in the mountains of plastic produced every year. Researchers from the University of Texas at Austin may have discovered a new way to deal with plastic waste — an enzyme that breaks down plastics in days that would otherwise persist for centuries.

The team used a machine learning system to identify potentially useful proteins in decomposing plastic, which led them to FAST-PETase (functional, active, stable, and tolerant PETase), reports Vice. This enzyme works on a plastic called polyethylene terephthalate (PET), a synthetic resin used in clothing, packaging, and electrical waterproofing. It’s the easiest category of plastics to recycle, but the process is one of diminishing returns. Eventually, the material simply ends up in a landfill, and PET accounts for about 12 percent of global waste.

FAST-PETase is a more elegant solution than melting and reforming plastic into less recyclable forms. It digests the polymer, breaking it down into building block molecules through a process known as depolymerization. The resulting monomers can be reassembled into new or “virgin” plastic without consuming additional petroleum resources. In the experiments, researchers were able to completely dissolve PET packaging in just a few days.

Scientists have been working with plastic-eating enzymes since 2005, but naturally occurring proteins come with major shortcomings. They might work fine under narrow ranges of temperature and pH, but that makes them much harder to use in recycling facilities. FAST-PETase was one of 19,000 protein structures fed into an AI algorithm, which predicted it would be able to decompose plastic quickly without strict control of conditions. And sure enough, the researchers report FAST-PETase is very flexible. It has 2.4 times the activity of natural PETase molecules at 40 degrees Celsius and 38 times more activity at 50 degrees Celsius.

So, we know that FAST-PETase works in a laboratory setting, but now the team has to contend with a hurdle that many similar experiments fail to clear: scalability. They need to show that we can produce and utilize FAST-PETase at an industrial scale. Despite the importance of reducing plastic in the environment, new technologies will only catch on if the materials are cheap and easy to transport.

Feature image by Tony Webster, Flickr

Continue reading

New MIT AI Designs Robots On Its Own
New MIT AI Designs Robots On Its Own

The team believes RoboGrammar could point researchers in new directions, leading to more efficient and inventive designs.

Leak Shows Off Samsung’s Redesigned Galaxy S21 Family
Leak Shows Off Samsung’s Redesigned Galaxy S21 Family

Based on some new teaser videos, you can look forward to a whole bunch of cameras.

Comparison of Apple M1, A14 Shows Differences in SoC Design
Comparison of Apple M1, A14 Shows Differences in SoC Design

A new analysis of the M1 breaks down the die design versus the smartphone-class A14 SoC.

Rocket Lab’s Upcoming Reusable Rocket Is Designed for Deploying Mega-Constellations
Rocket Lab’s Upcoming Reusable Rocket Is Designed for Deploying Mega-Constellations

The company says its upcoming Neutron rocket will be ideal for deploying mega-constellations, and it'll have a reusable first-stage a la the Falcon 9.