The artificial intelligence company DeepMind has announced a major medical scientific breakthrough in determining the structures of almost 200 million proteins.
Proteins are not two dimensional molecules, but have chemical properties that are determined by their three-dimensional shape — but figuring out these shapes is an intensive process.
The breakthrough has significant repercussions for medicine, and the new research by Google-backed DeepMind is hailed as having “the potential to dramatically increase our understanding of biology”.
A protein is created by a chain of amino acids, but without knowing how these chains are connected it isn’t possible to know how they interact with human cells and can be modified.
Last year DeepMind, which is owned by Google’s parent company Alphabet, shared the fruits of an AI system called AlphaFold which could predict the 3D structure of a protein from its single-dimensional amino acid sequence.
A year earlier, PC gamers had been asked to donate some of their computing power to an international effort researching diseases including COVID-19 and Alzheimer’s to simulate the molecular dynamics of protein folding.
It’s such a crucial topic for medical science because the structure of proteins determine chemical reactions in human cells, and by extension and in aggregate, the whole human body – but, until now, only a fraction of protein structures were known.
DeepMind’s announcement and protein structure database – which is being shared freely – dramatically increases the number of known protein structures from nearly one million to more than 200 million.
It was created alongside EMBL’s European Bioinformatics Institute (EMBL-EBI) whose director general Edith Heard said: “AlphaFold now offers a 3D view of the protein universe.”
“We’ve been amazed by the rate at which AlphaFold has already become an essential tool for hundreds of thousands of scientists in labs and universities across the world,” said Demis Hassabis, the founder and chief executive of DeepMind.
“From fighting disease to tackling plastic pollution, AlphaFold has already enabled incredible impact on some of our biggest global challenges,” Mr Hassabis added.
“Our hope is that this expanded database will aid countless more scientists in their important work and open up completely new avenues of scientific discovery.”
The research has been hailed by scientists who have been using AlphaFold models to develop malaria antibodies and even special enzymes that could break down plastics.
More than 1,000 scientific papers have been published since its launch and over 500,000 researchers from over 190 countries have accessed the database.
Additional areas of research enabled by the database include the health of honey bees, understanding how ice forms, and neglected diseases such as Chugs disease and Leishmaniasis.
“This is just the impact of one million predictions; imagine the impact of having over 200 million protein structure predictions openly accessible in the AlphaFold Database,” said Sameer Velankar, who leads EMBL-EBI’s protein data bank team in Europe.
