[ad_1]
A artificial intelligence A company that gained fame for designing computer systems that could beat humans in games has now made a breakthrough in biological science.
The company, DeepMind, which is owned by the same parent company as Google, has created an artificial intelligence system that can quickly and accurately predict how proteins fold into their 3D shapes, a surprisingly complex problem that has plagued researchers for decades, according to The New York Times.
Discovering the structure of a protein can take years or even decades of painstaking experimentation, and current computer simulations of protein folding are not accurate. But DeepMind’s system, known as AlphaFold, required only a few hours to accurately predict the structure of a protein, the Times reported.
Related: Why does artificial intelligence scare us so much?
Proteins are large molecules that are essential for life. They are made up of a series of chemical compounds known as amino acids. These “threads” are folded in intricate ways to create unique structures that determine what the protein can do. (For example, him “spike” protein in the new coronavirus it allows the virus to bind and invade human cells).
Nearly 50 years ago, scientists hypothesized that the structure of a protein could be predicted by knowing only its amino acid sequence. But solving this “protein folding problem” has proven to be a huge challenge because there are a staggering number of ways that the same protein could theoretically fold into a 3D structure. according to a statement from DeepMind.
Twenty-five years ago, scientists created an international competition to compare various protein structure prediction methods, somewhat like a “protein Olympiad” known as CASP, which stands for Critical Evaluation of Protein Structure Prediction , according The Guardian.
In this year’s challenge, AlphaFold performed well above its competitors. It achieved a level of precision that researchers did not expect to see for years.
“This computational work represents an astonishing advance on the problem of protein folding, a great 50-year challenge in biology,” said Venki Ramakrishnan, president of the Royal Society in the UK, who was not involved in the work. said in a statement. “It has happened decades before many people in the field would have predicted it. It will be exciting to see the many ways that biological research will fundamentally change.”
For the competition, teams receive the amino acid sequences of about 100 proteins, the structures of which are known but not published, according to Nature news. The predictions are scored from zero to 100, with 90 considered on par with the precision of the experimental methods.
AlphaFold was trained to recognize the relationship between amino acid sequence and protein structure using existing databases. Next, he used a neural network, a computer algorithm based on the way the human brain processes information, to iteratively improve his prediction of unpublished protein structures.
Overall, AlphaFold had a mean score of 92.5. That’s more than a score of less than 60 the system achieved in its first CASP competition in 2018.
The system is not perfect; in particular, AlphaFold did not perform well in modeling groups of proteins that interact with each other, Nature News reported.
But the advance is a game changer.
“I think it’s fair to say that this will be very detrimental to the field of protein structure prediction. I suspect that many will leave the field as the core problem has possibly been solved,” Mohammed AlQuraishi, computational biologist, told Nature News. from Columbia University. . “It is a breakthrough of the first order, without a doubt one of the most important scientific results of my life.”
DeepMind previously made headlines when it created an artificial intelligence program, known as AlphaGo, that beat the humans in the ancient game of Go.
The researchers hope that AlphaFold may have many real-world applications. For example, it could help identify the protein structures involved in certain diseases and speed up drug development.
DeepMind is currently working on a peer-reviewed article about its work at AlphaFold, the Times reported.
Originally posted on Live Science.
