[ad_1]
Protein is essential for life, supporting virtually all of its functions. They are large, complex molecules made up of chains of amino acids. What a protein does depends primarily on its unique 3D structure. Understanding the forms in which proteins fold is known as the “protein folding problem” and has been a major challenge in biology for 50 years. In a significant scientific breakthrough, the latest version of the DeepMind artificial intelligence group of the AlphaFold AI system has been detected to solve this great challenge by the organizers of the biennial Critical Assessment of Protein Structure Prediction (CASP). This breakthrough demonstrates the impact AI can have on fundamental areas that explain and shape the world.
The shape of a protein is closely associated with its function, and the ability to predict this structure allows us to better understand what it does and how it works. Many of the world’s biggest challenges – developing treatments for diseases or finding enzymes that break down industrial waste – are fundamentally linked to proteins and their role.
It has been the subject of intensive scientific research for many years, using various experimental techniques to examine and determine the structures of proteins, such as nuclear magnetic resonance and X-ray crystallography. These methods and the latest techniques such as cryo- Electron microscopy depend on extensive trial and error that can take years of painstaking and painstaking work per structure and require the use of specialized multi-million dollar equipment.
“This is a very substantial step forward,” says Mohammed AlQuraishi, a systems biologist at Columbia University who developed his software for predicting protein structure. “This is something that I wasn’t expecting so quickly. It’s shocking, in a way.
“It’s a big deal,” says David Baker, director of the Institute for Protein Design at the University of Washington and team leader behind Rosetta, a family of protein analysis tools. “It’s an incredible achievement, like what they did with Go.”
Astronomical numbers
Recognizing the structure of a protein is very difficult. Researchers have the amino acid sequence in the ribbon but not the twisted shape they fold into for most proteins. And there are usually an astronomical number of possible shapes for each sequence. Researchers have grappled with the problem since the 1970s, when Christian Anfinsen won the Nobel Prize for showing that sequences determine structure.
The launch of CASP in 1994 revitalized the field. Every two years, the organizers release around a hundred amino acid sequences for proteins whose forms have been identified in the laboratory but not yet made public. Many teams around the world then compete to find the right way to fold them using the software. Medical researchers are already using much of the tools developed for CASP. But progress has been slow, with two decades of incremental advances that have failed to shorten detailed lab work.
CASP got the shock it was looking for when DeepMind entered the competition in 2018 with its first release of AlphaFold. It still couldn’t match the precision of a lab, but it left other computational techniques in the dust. Many researchers took note and quickly adapted their systems to work more like AlphaFold.
In 2020, more than half of entries use some form of deep learning, says Moult. As a result, the precision was higher. Baker’s new system called trRosetta uses some of DeepMind’s ideas from 2018, though it’s still a “very distant second,” he adds.
DeepMind says he plans to study leishmaniasis, sleeping sickness and malaria, all tropical diseases caused by parasites linked to many unknown protein structures.
One drawback of AlphaFold is that it is slow compared to competing techniques. AlQuraishi’s system uses an algorithm called a recurrent geometric network (RGN). It can find protein structures a million times faster, giving results in seconds rather than days. Although his predictions are less accurate, speed is more critical for some applications, he says.
Researchers are now trying to find out how exactly AlphaFold works. Once they describe to the world how they do it, a thousand flowers will bloom, ”says Baker. “People will use it for all kinds of different things that we can’t imagine now.”
Share this article
Share
[ad_2]
Source link