AI used to design a multi-step enzyme that can digest some plastics
Briefly

Researchers developed a method to design enzymes with a PLACER screening step that increased catalytic efficiency significantly. Initially, enzymes stalled after one reaction but adapting screening for a key intermediate state led to 18 percent activity efficiency. New enzymes named 'super' and 'win' could cycle through multiple reactions. This endeavor involved computer-based simulations to streamline the design process while aiming for enzymes that could digest PET plastic. This innovative method demonstrates potential for future developments in enzyme design and flexibility in tackling unknown reactions.
If that sounds like a lot of work, it clearly was-designing enzymes, especially ones where we know of similar enzymes in living things, will remain a serious challenge.
The researchers started using PLACER to screen for structures that could adopt a key intermediate state of the reaction, producing a much higher rate of reactive enzymes.
Read at Ars Technica
[
|
]