[ad_1]
For decades, scientists have been trying to figure out how to quickly predict the twisted and tangled shape of proteins – and from there unravel a greater understanding of the mechanism of life itself.
This week, an artificial intelligence program created by Google’s sister company DeepMind proved to have virtually solved the challenge by predicting how proteins twist into three-dimensional structures in the results of a two-year competition that it judges hailed as a point of reference. turning point.
“In a sense, the problem is solved,” said John Moult, a computational biologist at the University of Maryland who co-founded the Critical Assessment of Techniques for Protein Structure Prediction (CASP) competition in 1994, quoted by the journal Nature.
Janet Thornton of the European Bioinformatics Institute said Monday in a statement from the contest organizers that the work to solve the problem was a “triumph of human curiosity, commitment and intelligence”.
“A better understanding of protein structures and the ability to predict them using a computer means a better understanding of life, evolution and, of course, human health and disease,” said Thornton, who is not affiliated with CASP or DeepMind.
The cells of all living things contain thousands of proteins, workhorses that catalyze most of the chemical reactions in the body.
They are essential for life – from muscle function to oxygen transport in the blood – and are also the key to diseases such as cancer and even COVID-19.
A protein begins as a strand of amino acids, which then curls up into a single three-dimensional tangle.
It is this form that directly relates to its function.
Scientists have been wondering for half a century about how to accurately and quickly predict what formation – among an unfathomably large number of possibilities – a protein might take by looking at its amino acid chain, a process that could take years in the laboratory.
The CASP contest involved around 100 teams who were given amino acid sequences for dozens of proteins and tasked with estimating their final shapes, which were known to the organizers.
DeepMind – whose AlphaGo program stunned the world in 2016 by beating an elite human player in the complex strategy game “Go” – was already in first place in the latest contest of 2018.
This time around, his AlphaFold program determined the shape of many of the proteins “to a level of accuracy comparable to that obtained in costly and time-consuming laboratory experiments,” according to CASP organizers.
Also read: Artificial intelligence has a role to play in applying the COVID-19 health protocol
“This changes medicine”
Andrei Lupas, an evolutionary biologist at the Max Planck Institute for Developmental Biology who was part of the evaluation team, told Nature that AlphaFold had helped him determine the structure of a protein his lab had been trying to define for a decade.
“This will change medicine. It will change research. It will change bioengineering. It will change everything,” he told Nature.
Derek Lowe, who writes on drug discovery and the pharmaceutical industry for Science Translational Medicine, described protein folding as “watching piles of hinged timber spontaneously reposition themselves in functional boats, wagons and tree houses.”
He said AlphaFold’s results didn’t mean the program would consistently find the right protein structure.
“But getting that level of structural accuracy on so many different proteins is something that has never been done before.”
DeepMind said it was looking into how the program could help raise awareness of certain diseases, for example to identify if a protein has worked poorly.
“These insights could enable more precise work on drug development, complementing existing experimental methods to find promising treatments faster,” a statement read.
The company added that it was working on producing a peer-reviewed document and was “exploring how best to provide wider access to the system.”
Your premium period will expires in 0 day (s)
close x
Sign up for unlimited access Get 50% discount now
.
[ad_2]
Source link
