How A.I. Just Designed An Enzyme That Eats Plastic ?

A.I. Just Designed An Enzyme That Eats Plastic


over many decades plastic waste has

become a major problem not just for the

environment but to us as humans as well

in fact, recently plastic has been detected in human organs, and this year

for the first time, it’s been detected in

human blood many are sleeping on the issue but maybe

something can be done if you are watching cold fusion tv

in 2016 Japanese scientists were sifting

through the debris of a plastic bottle recycling plant, they were in search of a

the bacterium that could degrade plastic the type of plastic that the scientists

were looking for was polyethylene pteraphophthalate or p-e-t for short 

this type of plastic accounts for 12 of all global solid waste.



if you’ve ever used a water bottle

that’s p-e-t it’s found in a lot of

other modern products including clothing

and packaging estimates say about 50

a million tonnes are produced every year

globally by 2025, this could be 100

million tons as the demand for the

As the material grows so does the mountain of plastic waste in  

landfills as pet-based products are notoriously difficult to recycle

the goal of the Japanese scientist trash hunt was to find a bacterium 

that could use the pet as its energy source after bringing 

plastic samples back to a lab what they found was a video Nella

cyanosis is a bacteria that amazingly eats



plastic and converts it to carbon dioxide from here the team discovered

that the organism has two enzymes that break down the plastic into basic

components we’ll talk about the importance of the enzyme soon

so in short the bacteria completely

digested the plastic and used it to power its

what’s left is carbon dioxide and the monomers usually ethyl glycol and

heterophilic acid these components can make new plastic

plastics like pets are made from little

chemicals joined in a chain the enzyme unlinks that chain

and then you get a bunch of components you can

then use these components and recycle them into another chain

so basically this enzyme could be used in the recycling process without any

extra energy input well you might be thinking that’s great

why haven’t we used this everywhere well there’s one problem


In the real world the bacteria and even

the isolated enzymes weren’t very

practical it did the job but it was very

fussy about it if the temperature was too low or too

high or the ph wasn’t just right it wouldn’t work effectively there had 

to be a way to improve this knowing that an enzyme consists of amino

acids linked together to form proteins if these amino acids 

could be tweaked perhaps the enzyme would perform better

but how could this be done enter ai



In May of 2022 a team from the University of Texas at Austin in the

united states used a neural network to

engineer and improve the performance and

stability of the plastic destroying Enzyme a machine learning

the algorithm was in charge of modifying the amino acids in

The enzyme the neural network called mute

compute studied a diverse range of 19 proteins of a similar size

it was to learn the patterns of what makes a protein stable

according to hal alpha who was the principal investigator of the study

amino acids that fit well within the protein are the key to stability

an amino acid that isn’t a good fit may be a source of instability

when this happens the performance of the enzyme falls off

when the algorithm saw that an amino acid might not fit well 


it suggested a

the different amino acids in its place for each of the 290 amino acids the

program checks to see if it fits well within its immediate structural

environment compared to other proteins within its knowledge base

this means that it can balance the evolutionary trade-off between activity

and stability which now when I think about it is insane

we’re observing nature and then hacking

it to do our bidding out of the millions and millions of

combinations the ai suggested three amino acid substitutions


The team decided to go with the ai’s

design the result was quoted highly

highly active especially at lower

temperatures compared to anything else

that’s out there

the ai-designed enzyme broke down an

entire plastic tray within 48 hours

It breaks down the plastic at over twice the

speed and at lower temperatures compared

to the next best-engineered enzyme they

demonstrated that untreated consumer pet

plastics could almost completely be

degraded in one week they tested 51

different products including whole

plastic containers and bottles they were

also able to make new recycled plastic

objects that consumed much less energy

than traditionally would be required 


The team managed to retrieve 94.9 percent of

the raw materials needed to make new plastic

since the plastic degradation is being

done by an enzyme and not the whole

bacteria it has the added benefit of not

being able to reproduce uncontrollably

other experts in the field are impressed.


Sarah cacadilus studies the plastics bioeconomy at the

imperial college of London in the UK comet quote it’s a 

the drastic improvement compared to other

enzymes that have been developed so far

the great advantage of enzymes is that

they can be much more specific than chemical catalysts

it could be easier in theory to degrade much more diverse 

waste using enzymes what I really liked

about the study is the fact that they took it outside the lab to some extent

she’s referring to trying the enzyme on

real plastic products bought at a local supermarket instead of a lab



Buy-in wu from the Chinese Academy of science states quote this study proved the machine learning method is useful in enzyme engineering


he goes on to state that the ai managed

to uncover certain modifications that

were ignored by other methods the texas team is continuing to

investigate the practical aspects of

enzyme recycling as well as expanding the range of materials

so what are some drawbacks it should be

noted that the enzyme’s optimal working

temperature is 50 degrees celsius which is too high to work in ambient

Conditions but perhaps with better neural networks

we could take this optimal operating

temperature down to ambient room temperature



So in conclusion there are still massive 

amounts of work to be done to solve the

plastic waste problem but this is the

start really it is actually early days seeing that the enzyme itself was only

found in 2016 but this latest news about

ai making it much more practical I think is a bright spot to watch.

Leave a Comment