Artificial intelligence has deciphered the structure of almost all proteins known to science

The British company DeepMind Technologies Limited DeepMind, thanks to artificial intelligence, has deciphered the structure of more than 200 million proteins that are still known to science.

According to Ukrinform, this is reported by The New York Times.

DeepMind now hopes to accelerate the study of more obscure organisms and launch a new field called metaproteomics (protein identification).

“Now scientists can explore this entire database and look for patterns – correlations between species and evolutionary patterns that might not have been obvious until now,” said DeepMind CEO Demis Hassabis.

It is noted that proteins first look like chains of chemical compounds, and then fold into three-dimensional shapes that determine how these molecules bind to others.

Read also: Researchers established origin virus simian smallpoxNYT

If scientists can pinpoint the structure of a protein, they can decipher how it works.

This knowledge is often an important part in the fight against various diseases. For example, bacteria resist antibiotics by squeezing out certain proteins. If scientists can understand how these proteins work, they may be able to counteract antibiotic resistance.

Previously, determining the structure of a protein required large-scale experiments using X-rays, microscopes, and other instruments on the table in the laboratory.

As Ukrinform reported, in early February this year, the British company DeepMind Technologies Limited announced the creation of a system based on artificial intelligence AlphaCode.

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button