Home / Blog / A new milestone in biology: protein folding

A new milestone in biology: protein folding

Structure of the protein Pfs48/45, present in the malaria parasite. DeepMind’s AlphaFold has predicted its 3D structure. Image credit: DeepMind

Proteins are playing a key role on life of all living things, from viruses to redwood, bacteria to elephants, and of course to us, humans.

The interesting point is that proteins interact not because of the atoms that build them up but because of their shape, like Lego bricks: it doesn’t matter the material making up two Lego bricks, in order to click together they have to have a very specific shape.

Hence, discovering the shape of proteins is crucial, as an example to create drugs (we have seen the importance of the “shape” during the pandemic as everybody talked about the Spike Protein and how the vaccines are using it to block the virus, aling with the concern that a variation in that protein would render the vaccine useless).

Problem is that discovering the shape of a protein (its “folding”) is extremely difficult (watch the clip). Scientists have worked long hours to discover the protein folding (using X-ray crystallography) and only a few on them have been found. The task has become a bit easier with use of software, although this requires massive computational capacity (supercomputers have been used).

More recently, researchers have approached the problem using artificial intelligence to simulate first how a protein folding might be and then checking if that was the case. As this was done the software become ever smarter shortening the time.

Now Google has announced that his AlphaFold (do you remember AlphaGO focussing on the game GO?) has managed to find the folding of over 200 million proteins, basically all the proteins that we know of, involved in life on Earth. You should compare this number with the 190k proteins that have been described in all previous years, discovering their folding using classical methods. The first attempt of AlphaGo last year resulted in the determination of the 3D structure  of 1 million proteins, now they have released the 3D structure of all known proteins.

This is an amazing success that is opening the door to the discovery of new drugs and much more, like food, sustainability, rare diseases….

Google is sharing all data of the 3D structure of these 200+ million proteins and it is doing even more: they have released as open source the code of AlphaGO to let researchers use its capability to design new molecules (like new drugs) and experiment their effectiveness in the cyberspace, thus significantly reducing the time to market. The m-Vaccines developed for Covid-19 have been designed and tested first in the cyberspace and their success has been astounding.

It is a new world opening up.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.