AI may have the answer to one of biology’s biggest challenges
AI may have the answer to one of biology’s biggest challenges | Science & technology
.Listing a protein’s amino acids is easy. Machines to do so have existed for decades. But this is only half the battle in the quest to understand how proteins work. What a protein does, and how it does it, depends also on how it folds up after its creation, into its final, intricate shape.
At the moment, molecular biologists can probe proteins’ shapes experimentally, using techniques likeX-ray crystallography. But this is fiddly and time-consuming. Now, things may be about to get much easier. On November 30th researchers from DeepMind, an artificial-intelligence (
AI) laboratory owned by Alphabet, Google’s parent company, presented results suggesting that they have made enormous progress on one of biology’s grandest challenges—how to use a computer to predict a protein’s shape from just a list of its amino-acid components. headtopics.com
Chain gangsTo non-biologists, this may sound somewhere between arcane and prosaic. In fact, it is a big achievement. Replacing months of experiments with a few hours of computing time could shed new light on the inner workings of cells. It could speed up drug development. And it could in particular suggest treatments for diseases like Alzheimer’s, in which misshapen proteins are thought to play a role.
But there is yet more to it than that. Until now, the machine-learning techniques which DeepMind’s team used to attack the protein-folding problem have been best known for powering things like face-recognition cameras and voice assistants, and for defeating human beings at tricky games like Go. But Demis Hassabis, DeepMind’s boss, who founded in 2010 what was then an independent firm, did so hoping that they could also be employed to accelerate the progress of science. This result demonstrates how that might work in practice.
The idea of using computers to predict proteins’ shapes is half a century old. Progress has been real, but slow, says Ewan Birney, deputy director of the European Molecular Biology Laboratory, a multinational endeavour with headquarters in Germany. And it has been marked by a history of wrong turns and premature declarations of victory.
These days a humbler field, protein-shape prediction now measures its progress by how well algorithms perform in something called Critical Assessment of Protein Structure Prediction (CASP). This is a biennial experiment-cum-competition which started in 1994 and is jokingly dubbed the “Olympics of protein-folding”. In it, algorithms are subjected to blind tests of their ability to predict the shapes of several proteins of known structure. headtopics.com
DeepMind’s first entry toCASP, two years ago, was dubbed AlphaFold. It made waves by performing much better than any other then-existing program. The current version, AlphaFold 2, has stretched that lead still further (see chart). One measure of success within
CASPis the global-distance test. This assigns algorithms a score between zero and 100 by comparing the predicted locations of atoms in a molecule’s structure with their location in reality. AlphaFold 2 had an average score of 92.4—an accuracy thatCASP
’s founder, John Moult, who is a biologist at the University of Maryland, says is roughly comparable with what can be obtained by techniques likeX-ray crystallography.Until now, DeepMind was probably best known for its success in teaching computers to play games—particularly Go, a pastime of deceptively simple rules but fiendish strategy that had been a totem of
AIresearchers since the field began. In 2016 a DeepMind program called AlphaGo defeated Lee Sedol, one of the world’s best players. Superficially, this may seem of little consequence. But Dr Hassabis says that more similarities exist between protein-folding and Go than might, at first, appear. headtopics.com
One is the impracticality of attacking either problem with computational brute force. There are thought to be around 10170legal arrangements of stones on a Go board. That is much greater than the number of atoms in the observable universe, and it is therefore far beyond the reach of any computer unless computational shortcuts can be devised.
Proteins are even more complicated than Go. One estimate is that a reasonably complex protein could, in principle, take any of as many as 10300different shapes. The shape which it does eventually settle into is a result of a balance of various atom-scale forces that act within its amino-acid building blocks, between those building blocks, and between the building blocks and other, surrounding, molecules, particularly those of water. These are all matters of considerable complexity which are difficult to measure. It is therefore clear that, as with playing Go, the only way to perform the trick of predicting protein-folding is to look for shortcuts.
The progress that computers have made on the problem over the years demonstrates that these shortcuts do exist. And it also turns out that even inexpert humans can learn such tricks by playing around. Dr Hassabis recalls being struck by the ability of human amateurs to achieve good results with FoldIt, a science-oriented video game launched in 2008 that invites its players to try folding proteins themselves, and which has generated a clutch of papers and discoveries.
Alpha-helix dogsGetting players of FoldIt to explain exactly what they have been up to, though, is tricky. This is another parallel with Go. Rather than describing step by step what they are thinking, players of both games tend to talk in vaguer terms of “intuition” and “what feels right”. This is where the machine learning comes in. By feeding computers enough examples, they are able to learn and apply shortcuts and rules-of-thumb of the sort that human beings also exploit, but struggle to articulate. Sometimes, the machines come up with insights that surprise human experts. As Dr Moult observes, “In general, the detail of the backbone [the molecular scaffolding that joins amino acids together] is extraordinary. [AlphaFold 2] has decided that if you don’t get the details right, you won’t get the big things right. This is a school of thought that’s been around for some time, but I thought it wasn’t correct.”
As an achievement inAI, AlphaFold 2 is not quite so far ahead of the field as was AlphaGo. Plenty of other research groups have applied machine learning to the protein-structure problem, and have seen encouraging progress. Exactly what DeepMind has done to seize the lead remains unclear, though the firm has promised a technical paper that will delve into the details. For now, John Jumper, the project’s leader, points out that machine learning is a box which contains a variety of tools, and says the team has abandoned the system it used to build the original AlphaFold in 2018, after it became clear that it had reached the limits of its ability.
The current version, says Dr Jumper, has more room to grow. He thinks space exists to boost the software’s accuracy still further. There are also, for now, things that remain beyond its reach, such as how structures built from several proteins are joined together.
Moreover, as Ken Dill, a biologist at Stony Brook University in New York state, who is the author of a recent overview of the field, points out, what AlphaFold 2, its rivals and, indeed, techniques likeX-ray crystallography discover are static structures. Action in biology comes, by contrast, from how molecules interact with each other. “It is”, he puts it, “a bit like someone asking how a car works, so you open the hood [bonnet] and take a picture and say, ‘There, that’s how it works!’” Useful, in other words, but not quite the entire story.
Nonetheless—and depending on how DeepMind decides to license the technology—an ability to generate protein structures routinely in this way could have a big impact on the field. Around 180m amino-acid sequences are known to science. But only some 170,000 of them have had their structures determined. Dr Moult thinks that boosting this number could help screen drug candidates to see which are likely to bind well to a particular protein. It could be used to reanalyse existing drugs to see what else they might do. And it could boost synthetic biology, by speeding up the creation of human-designed proteins intended to catalyse chemical reactions.
Some promising successes have, indeed, already happened. For example, AlphaFold 2 was able to predict the structures of several of the proteins used by the new coronavirus, including spike. As for Dr Birney, he says, “We’re definitely going to want to spend some time kicking the tyres. But when I first saw these results, I nearly fell off my chair.”
Watch Debby Ryan’s Guide to Depuffing Skin Care and Day-to-Night Makeup
The 28-year-old actress shares her beauty secrets, from her favorite skin-care tools to an effortless smoky eye.
From the corners
Ford, Walmart and Argo AI team up to launch autonomous vehicle delivery serviceCustomers may soon get their Walmart orders delivered by an autonomous vehicle. Self-driving startup Argo AI, automaker Ford Motor and Walmart will together launch the service in Miami, Austin, and Washington, D.C.
Argo AI And Ford To Make Autonomous Deliveries For WalmartBy the end of 2021, Argo AI plans to begin last-mile deliveries for Walmart using automated Ford Escapes in Miami, Austin and Washington DC
Walmart partnering with Ford, Argo AI to test self-driving delivery vehiclesWalmart announced plans to launch a new delivery service using self-driving vehicles in three U.S. cities, with autonomous test vehicles expected to hit the streets later this year. What's going to keep it from being robbed, broke into or high jacked? Serious inquires only payroll needed, No experience needed We train! Bonuses! Full benefits. 5 days work per week. Contact our hiring Manager at gibsonedwin093gmail.com for more information Ha! They can't even get my own self checkout right....so let's trust this.
5 Perfectly Spiced Protein Shakes That Will Make This Fall Even More SatisfyingThese protein-packed shakes include all your favorite fall flavors, from pumpkin spice to apple pie. I love that the ingredients are so simple- I already have most of them at home. Goodbye, pumpkin spice latte! 😜
Love Island's Millie sacrifices beauty sleep as she goes on 4am hike with LiamLove Island winners Liam Reardon and Millie Court are going from strength to strength on the outside world and doing so by spending their time doing pre-fame activities
101-Year-Old Maine Woman Has No Plans To Stop Hauling Lobsters“I’ve done it all my life, so I might as well keep doing it,” Virginia Oliver said.