Understanding how proteins essential to life are made is one of the “grand challenges” in biology, and scientists have spent decades trying to understand how they are made.

Starting today, it’s easier to determine the 3D shape of any protein known to science, as a new tool has identified the structures of some 200 million proteins, after the “DeepMind” company unveiled a revolutionary artificial intelligence network to predict the structures of 3D proteins. , includes almost all proteins, known to all living organisms, and will give scientists instant access to deep information about the fundamental building blocks of life.

Alphafold and DeepMind

According to the newspaper,Daily Mail(Daily Mail) British, adopted artificial intelligence projectAlphafold(Alpha folding) Scientists spend months or even years trying to understand the structure of proteins, and researchers often use tools like X-rays, but alpha folding software developed by Alpha Fold.deep mindGoogle’s DeepMind is capable of performing deep learning to predict the structure of proteins.

The first version of this project was released in 2018, with a second version released in late 2020, and it is available for searching protein complex (proteome) databases of species and organisms through open source software.

More than 500,000 researchers from 190 countries have used the “AlphaFold” database to show more than two million protein structures, and this complex information is now available at the same speed as a Google search, and the program now predicts the structure of almost all proteins known to science in animals or plants or humans, bacteria or other organisms. .

DeepMind is a British artificial intelligence company founded in 2010, and renamed after being acquired by Google in 2014. The company has developed “neural network software” that can learn how to play video games like a human. A neural network that can access external memory, so the computer can simulate the short-term memory of the human brain.

An important resource for scientists

The ability to quickly view a protein’s structure in three dimensions is valuable to scientists looking to treat diseases and to researchers who want instant access to deep information about the building blocks of life.

Since its introduction in 2020, researchers have already used AlphaFold to understand proteins that affect bee health and develop an effective malaria vaccine. An expanded database will serve as an important resource for scientists to better understand diseases, and can accelerate drug discovery and innovation in biology.

Demis Hassabis, founder and CEO of DeepMind, says the database allows researchers to search for 3D structures of proteins “as easily as searching Google with keywords.”

Explained in Article On the company’s website, the latest version of the data gives the database a boost, and the update includes structures for “plants, bacteria, animals and many other species,” opening up big opportunities for the Alphafold program to influence. “Sustainability, Fuel and Food Insecurity.” and important issues such as neglected diseases.

A starting point

Jian Ping, a professor of computer science at the University of Illinois Urbana-Champaign who specializes in computational biology, told E magazine.MIT Technology Review(MIT Technology Review), said that “AlphaFold may be the AI ​​community’s greatest contribution to the scientific community,” and that it “may help scientists reinterpret previous research to better understand how diseases occur.”

Muhammad Al Quraishi, a systems biologist at Columbia University who is not involved in deep-mind research, told the paper.MIT Technology Review“Predicting protein structures takes a long time, and having a tool with 200 million protein structures readily available will save researchers a lot of time.” However, for many proteins, “we are interested in understanding how their structure is altered by mutations and natural allelic diversity, and this is not addressed by this database.”

Others use protein structure predictions to develop vaccines and to explore fundamental biological questions, such as investigating the evolution of proteins when life first arose. However, the researchers warned in an article published in the journal “ScienceStarting a (scientific) database is a starting point, “and it’s clear that there’s still a lot of biology and a lot of chemistry to be done.”