Life sciences leap forward as AlphaFold shares the ‘protein universe’
29 Jul 2022
AlphaFold, the artificial intelligence programme created by AI group Deep Mind has released its predictions of the structure of most of the more than 200 million known proteins, described as ‘the protein universe’.
The company, owned by Google parent Alphabet, created a sensation last year when it made the structure of 98% of the 20,000 human proteins available, just months after the launch of AlphaFold itself, at the end of 2020.
Using an algorithm, AlphaFold was able to predict how the chains of amino acids that form proteins folded into the three dimensional shapes that determine the function of individual proteins. Understanding how amino acids interact provided the key to influencing their behaviour.
On the Deep Mind website, founder and director of the Scripps Research Translational Institute Eric Topol, described the importance of the latest breakthrough, which has seen a massive increase in the information available and its potential benefits.
Explained Topol: “AlphaFold is the singular and momentous advance in life science that demonstrates the power of AI. Determining the 3D structure of a protein used to take many months or years, it now takes seconds.
“AlphaFold has already accelerated and enabled massive discoveries, including cracking the structure of the nuclear pore complex. And with this new addition of structures illuminating nearly the entire protein universe, we can expect more biological mysteries to be solved each day."
Determining the 3D structure of a protein used to take many months or years, it now takes seconds
Eric Topol,Director of the Scripps Research Translational Institute
Its effects are likely to impact major global and environmental crises as well as the development of medicines. To date more than half a million researchers from nearly 200 countries have viewed more than 2 million protein structures on AlphaFold’s database.
Its work has already used towards finding cures for Chagas Disease and Leishmaniasis as well as combating Leprosy and Schistosomiasis.
The firm added that most pages on the UniProt protein database would now be furnished with predicted structures, while each of the more than 200 million protein structures identified can be bulk downloaded by scientists on Google Cloud Public Datasets.
