Artificial intelligence will 'transform' the functioning of life

According to a new study, artificial intelligence was used to predict the structures of almost all proteins produced by the human body. The breakthrough could drive the discovery of new drugs to treat diseases, in addition to other applications.

Inteligencia artificial transformará el funcionamiento de la vida

Proteins are essential components of living organisms. Each of our cells is filled with these "essential bricks" of life. Understanding the forms of proteins is fundamental to the advancement of medicine, but it had only been possible to elucidate the structure of a fraction of them until now. Now the researchers used a program called AlphaFold to predict the structures of 350 thousand proteins of humans and other organisms.

The instructions for producing human proteins are contained in our genomes, the DNA in the nuclei of human cells. There are about 20 thousand of these proteins expressed by the human genome. Taken together, biologists refer to the entire set of these proteins as the "proteome."

"We believe it's the most complete and accurate picture of the human proteome to date," said Demis Hassabis, chief executive officer and co-founder of artificial intelligence company DeepMind, which developed AlphaFold.

"We believe that this work represents the most significant contribution of artificial intelligence to the advancement of scientific knowledge to date. And I think it's a great illustration and example of the kind of benefits that artificial intelligence can bring to society. We are very excited to see what the scientific community is going to do with this information," Hassabis added.


Proteins are made up of smaller building blockchains called amino acids. These chains fold in countless different shapes, forming a unique 3D shape. The shape or folding of a protein determines its function in the human body.

The 350 thousand protein structures predicted by AlphaFold include not only the 20 thousand contained in the human proteome but also those of so-called model organisms frequently used in scientific research, such as E. coli bacteria, yeast, fruit flies, and mice.

This giant leap in capacity is described in a new study by researchers at DeepMind and the European Molecular Biology Laboratory.

AlphaFold was able to make a safe prediction of folds for 58% of the amino acids in the human proteome.

Positions of 35.7% were predicted with a very high degree of confidence, double the number confirmed by experiments.

Traditional techniques for elucidating protein structures include X-ray crystallography and electronic cryomicroscopy (Cryo-EM), among others. But none of these methods are simple.

"It takes a lot of money and resources to decipher the structures," said Professor John McGeehan, a structural biologist at the University of Portsmouth in England.

Post a Comment