[ad_1]
Some scientists spend their lives trying to find the shape of tiny proteins in the human body.
Proteins are the microscopic mechanisms that guide the behavior of viruses, bacteria, the human body and all living things. They begin as strings of chemical compounds, before twisting and folding into three-dimensional shapes that define what they can do and what they can’t.
For biologists, identifying the precise shape of a protein often takes months, years, or even decades of experimentation. It requires skill, intelligence and more than a little elbow grease. Sometimes they never succeed.
Now, an artificial intelligence lab in London has built a computer system that can do the job in hours, perhaps even minutes.
DeepMind, a lab owned by the same parent company as Google, said on Monday that its system, called AlphaFold, had solved what is known as “the protein folding problem.” Given the array of amino acids that make up a protein, the system can quickly and reliably predict its three-dimensional shape.
This long-sought breakthrough could accelerate the ability to understand disease, develop new drugs and unravel the mysteries of the human body.
Computer scientists have struggled to build such a system for more than 50 years. Over the past 25, they have measured and compared their efforts through a global competition called Critical Assessment of Structure Prediction, or CASP. Until now, no competitor had even come close to solving the problem.
DeepMind solved the problem with a wide range of proteins, achieving a level of accuracy that rivaled physical experiments. Many scientists had assumed that that moment was still years, if not decades away.
“I’ve always hoped to see this day,” said John Moult, a professor at the University of Maryland who helped create CASP in 1994 and continues to oversee the two-year competition. “But it wasn’t always obvious that I was going to make it.”
As part of this year’s CASP, DeepMind’s technology was reviewed by Dr. Moult and other researchers overseeing the competition.
If DeepMind’s methods can be refined, he and other researchers said, they could accelerate the development of new drugs and efforts to apply existing drugs to new viruses and diseases.
The breakthrough comes too late to have a significant impact on the coronavirus. But the researchers believe DeepMind’s methods could accelerate the response to future pandemics. Some believe it could also help scientists gain a better understanding of genetic diseases along the lines of Alzheimer’s or cystic fibrosis.
However, experts warned that this technology would affect only a small part of the lengthy process by which scientists identify new drugs and analyze diseases. It also wasn’t clear when or how DeepMind would share its technology with other researchers.
DeepMind is one of the key players in a radical change that has spread across academia, the tech industry and the medical community over the past 10 years. Thanks to an artificial intelligence technology called a neural network, machines can now learn to perform many tasks that were once beyond their reach and sometimes beyond the reach of humans.
A neural network is a mathematical system loosely modeled on the network of neurons in the human brain. He learns skills by analyzing large amounts of data. By identifying patterns in thousands of cat photos, for example, he can learn to recognize a cat.
This is the technology that recognizes faces in photos you post on Facebook, identifies commands that bark on your smartphone, and translates one language into another on Skype and other services. DeepMind uses this technology to predict the shape of proteins.
If scientists can predict the shape of a protein in the human body, they can determine how other molecules will bind or physically bind to it. This is one of the ways drugs are developed: a drug binds to particular proteins in the body and alters their behavior.
By analyzing thousands of known proteins and their physical shapes, a neural network can learn to predict the shapes of others. In 2018, using this method, DeepMind entered the CASP contest for the first time and its system outperformed all other competitors, signaling a significant change. But his team of biologists, physicists and computer scientists, led by a researcher named John Jumper, was nowhere near solving the final problem.
Over the next two years, Dr. Jumper and his team designed an entirely new type of neural network specifically for protein folding, and this led to a huge leap in accuracy. Their latest version provides a powerful, albeit imperfect, solution to the protein folding problem, said DeepMind researcher Kathryn Tunyasuvunakool.
The system can accurately predict the shape of a protein about two-thirds of the time, according to the results of the CASP competition. And its errors with these proteins are less than the width of an atom, an error rate that rivals physical experiments.
“Most of the atoms are within an atomic diameter of where they are in the experimental facility,” said Dr Moult, the organizer of the competition. “And with those that aren’t, there are other possible explanations for the differences.”
Andrei Lupas, director of the protein evolution department at the Max Planck Institute for Developmental Biology in Germany, is among those who have worked with AlphaFold. He is part of a team that has spent a decade trying to determine the physical form of a particular protein in a tiny bacterium-like organism called archaon.
This protein straddles the membrane of individual cells – part is inside the cell, part is outside – making it difficult for scientists like Dr. Lupas to determine the shape of the protein in the laboratory. Even after a decade, he couldn’t pinpoint the shape.
With AlphaFold, he solved the problem in half an hour.
If these methods continue to improve, he said, they could be a particularly useful way to determine if a new virus can be treated with a cocktail of existing drugs.
“We could begin screening for any compound authorized for use in humans,” said Dr. Lupas. “We could tackle the next pandemic with the drugs we already have.”
During the current pandemic, a simpler form of artificial intelligence has proved useful in some cases. A system built by another London company, BenevolentAI, helped pinpoint an existing drug, baricitinib, that could be used to treat seriously ill Covid-19 patients. The researchers have now completed a clinical trial, although the results have not yet been released.
As researchers continue to improve the technology, AlphaFold could further accelerate this kind of drug repurposing, as well as the development of entirely new vaccines, especially if we encounter a virus that’s even less understood than Covid-19.
David Baker, director of the University of Washington’s Institute for Protein Design, which used similar computer technology to design coronavirus drugs, said DeepMind’s methods could accelerate that work.
“We have been able to design coronavirus neutralizing proteins over several months,” he said. “But our goal is to do this kind of thing in a couple of weeks.”
However, the speed of development has to contend with other problems, such as massive clinical trials, said Dr. Vincent Marconi, a researcher at Emory University in Atlanta, who helped lead the baricitinib study. “It takes time,” he said.
But DeepMind’s methods could be a way to determine if a clinical trial will fail due to toxic reactions or other problems, at least in some cases.
Demis Hassabis, CEO and co-founder of DeepMind, said the company plans to publish details describing its work, but that is unlikely to happen until next year. He also said the company is exploring ways to share the technology itself with other scientists.
DeepMind is a research laboratory. It does not sell products directly to other laboratories or companies. But it could partner with other companies to share access to its technology on the Internet.
The lab’s most important discoveries in the past have involved games. He built systems that surpassed human performance on the ancient strategy game Go and the popular video game StarCraft – extremely technical results without practical applications. Now, the DeepMind team can’t wait to push their AI technology into the real world.
“We don’t want to be a leading company on board,” said Dr. Jumper. “We want real biological relevance.”
Source link
