A company from the Google universe has unraveled one of the great mysteries of science. By discovering how proteins develop in three dimensions (3D), DeepMind has created the conditions for a revolution in medicine, as potential cures for any and all diseases, from hereditary to infectious.
Researchers used an artificial intelligence (AI) program called AlphaFold to identify the 3D structures of 350,000 proteins from humans and other organisms, such as viruses or insects. A scientific advance that shortened a fundamental process of microbiology from months to minutes and could mean a revolution in science and, in particular, in people’s lives.
This development can help accelerate the discovery of new drugs to treat various types of diseases, contribute to the destruction of plastics that threaten the planet, or create agricultural crops resistant to pests and climate change.
A historic moment in the world of molecular structural research. #AlphaFold structure predictions for 22 species made freely available by @deepmind, access through @uniprot and @PDBeurope. Learn more at https://t.co/CFOFytruww pic.twitter.com/4nlCirj0Ai
— UniProt (@uniprot) July 22, 2021
How proteins develop “into truly unique and rare three-dimensional structures” is one of the great mysteries of biology, said Professor Jane Thornton of the European Institute of Bioinformatics (EMBL in its original acronym) in Hinxton, UK, in statements to the BBC.
“A better understanding of the structure of proteins and the ability to predict how they unfold using a computer means a better understanding of life, evolution, and, of course, human health and disease,” added Jane Thorton, to whom the Queen awarded the Lady title.
“The way proteins work depends on their three-dimensional structure. The functioning of proteins is relevant in everything that concerns health and disease,” said Andrew Martin, from the prestigious University College of London (UCL, in its original acronym), in statements to the BBC.
Knowing the proteins to fight diseases and create new drugs
Proteins are fundamental “bricks” in the structure of any living thing whose cells are full of proteins.
These “bricks” that makeup proteins, the amino acids, evolve through a myriad of pathways into a unique 3D shape. It is this unique form of each protein that determines its function in the human body.
“By knowing the three-dimensional structures of proteins, we can help design new drugs and intervene in health problems, whether infectious or hereditary”, argued Andrew Martin.
Many diseases are linked to the role of proteins as catalysts for chemical reactions, enzymes, combating the offending agent (antibodies), or acting as messengers (in the case of hormones such as insulin).
“Even small changes in these vital molecules can have catastrophic effects on our health, so one of the most effective ways to understand diseases and find new treatments is to study proteins,” argues John Moult, from the University of Maryland, USA.
A mystery with more than 50 years
The instructions for making human proteins are in our genome, the DNA contained in the nuclei of human cells. There are about 20,000 of these proteins in the human genome, known among scientists as the “proteome”.
For nearly 50 years, scientists have been trying to decipher this mystery of biology using conventional, expensive and time-consuming tactics. “A process that used to take six months now can be done in minutes,” rejoiced John McGeehan, a structural biologist at the University of Portsmouth, UK, who is already using data from the AlphaFold project to develop enzymes that break down plastic more quickly.
“The possible applications with this project are only limited by our knowledge”, added Professor Edith Heard, from EMBL. Technological advances achieved through the AlphaFold project may open the way for the discovery of new ways and treatment of diseases, in the production of agricultural crops that resist climate change or such enzymes that destroy the plastic that persists in the environment.
“It’s an excellent example of what AI can bring to society,” said Demis Hassabis, co-founder of Artificial Intelligence firm Deep Mind. “We believe that this work represents the most significant contribution of Artificial Intelligence to the advancement of scientific knowledge to date,” he added.
“We are excited to see what the scientific community will do with this,” said Hassabis, arguing that the ambition is to expand the database’s coverage to all of the proteins known to science, some 100 million structures.
The project will not stay closed. Deep Mind, a company in the Google universe, joined EMBl to make AlphaFold available to the entire scientific community.
Source: with Agencies