DeepMind, an AI research lab that was bought by Google and is now an independent part of Google\u2019s parent company Alphabet, announced a major breakthrough this week that one evolutionary biologist called \u201ca game changer.\u201d<\/p>\n
\u201cThis will change medicine,\u201d the biologist, Andrei Lupas, told Nature<\/em>. \u201cIt will change research. It will change bioengineering. It will change everything.\u201d <\/p>\n The breakthrough: DeepMind says its AI system, AlphaFold, has solved the \u201cprotein folding problem\u201d \u2014 a grand challenge of biology that has vexed scientists for 50 years.<\/p>\n Proteins are the basic machines that get work done in your cells. They start out as strings of amino acids (imagine the beads on a necklace) but they soon fold up into a unique three-dimensional shape (imagine scrunching up the beaded necklace in your hand). <\/p>\n That 3D shape is crucial because it determines how the protein works. If you\u2019re a scientist developing a new drug, you want to know the protein\u2019s shape because that will help you come up with a molecule that can bind to it, fitting into it to alter its behavior. The trouble is, predicting which shape a protein will take is incredibly hard. <\/p>\n Every two years, researchers who work on this problem try to prove how good their predictive powers are by submitting a prediction about the shapes that certain proteins will take. Their entries are judged at the Critical Assessment of Structure Prediction (CASP) conference, which is basically a fancy science contest for grown-ups.<\/p>\n By 2018, DeepMind\u2019s AI was already outperforming everyone at CASP, provoking some melancholic feelings among the human researchers. DeepMind took home the win that year, but it still hadn\u2019t solved the protein folding problem. Not even close.<\/p>\n This year, though, its AlphaFold system was able to predict \u2014 with impressive speed and accuracy \u2014 what shapes given strings of amino acids would fold up into. The AI is not perfect, but it\u2019s pretty great: When it makes mistakes, it\u2019s generally only off by the width of an atom. That\u2019s comparable to the mistakes you get when you do physical experiments in a lab, except that those experiments are much slower and much more expensive. <\/p>\n \u201cThis is a big deal,\u201d John Moult, who co-founded and oversees CASP, told Nature<\/em>. \u201cIn some sense the problem is solved.\u201d<\/p>\n Why this is a big deal for biology<\/p>\n The AlphaFold technology still needs to be refined, but assuming the researchers can pull that off, this breakthrough will likely speed up and improve our ability to develop new drugs.<\/p>\n Let\u2019s start with the speed. To get a sense of how much AlphaFold can accelerate scientists\u2019 work, consider the experience of Andrei Lupas, an evolutionary biologist at the Max Planck Institute in Germany. He spent a decade \u2014 a decade! \u2014 trying to figure out the shape of one protein. But no matter what he tried in the lab, the answer eluded him. Then he tried out AlphaFold and he had the answer in half an hour. <\/p>\n AlphaFold has implications for everything from Alzheimer\u2019s disease to future pandemics. It can help us understand diseases, since many (like Alzheimer\u2019s) are caused by misfolded proteins. It can help us find new treatments, and also help us quickly determine which existing drugs can be usefully applied to, for example, a new virus. When another pandemic comes along, it could be very helpful to have a system like AlphaFold in our back pocket.<\/p>\n \u201cWe could start screening every compound that is licensed for use in humans,\u201d Lupas told the New York Times. \u201cWe could face the next pandemic with the drugs we already have.\u201d<\/p>\n But for this to be possible, DeepMind would have to share its technology with scientists. The lab says it\u2019s exploring ways to do that. <\/p>\n Why this is a big deal for artificial intelligence <\/p>\n Over the past few years, DeepMind has made a name for itself by playing games. It has built AI systems that crushed pro gamers at strategy games like StarCraft and Go. Much like the chess matches between IBM\u2019s Deep Blue and Garry Kasparov, these matches mostly served to prove that DeepMind can make an AI that surpasses human abilities.<\/p>\n Now, DeepMind is proving that it has grown up. It has graduated from playing video games to addressing scientific problems with real-world significance \u2014 problems that can be life-or-death. <\/p>\n The protein folding problem was a perfect thing to tackle. DeepMind is a world leader in building neural networks, a type of artificial intelligence loosely inspired by the neurons in a human brain. The beauty of this type of AI is that it doesn\u2019t require you to preprogram it with a lot of rules. Just feed a neural network enough examples of something, and it can learn to detect patterns in the data, then draw inferences based on that. <\/p>\n So, for example, you can present it with many thousands of strings of amino acids and show it what shape they folded into. Gradually, it detects patterns in the way given strings tend to shape up \u2014 patterns that human experts may not have detected. From there, it can make predictions about how other strings will fold. <\/p>\n This is exactly the sort of problem at which neural networks excel, and DeepMind recognized that, marrying the right type of AI to the right type of puzzle. (It also integrated some more complex knowledge \u2014 about physics and evolutionarily related amino acid sequences, for example \u2014 though the details remain scant as DeepMind is still preparing a peer-reviewed paper for publication.)<\/p>\n Other labs have already harnessed the power of neural networks to make breakthroughs in biology. At the beginning of this year, AI researchers trained a neural network by feeding it data on 2,335 molecules known to have antibacterial properties. Then they used it to predict which other molecules \u2014 out of 107 million possibilities \u2014 would also have these properties. In this way, they managed to identify brand-new types of antibiotics. <\/p>\n DeepMind researchers are capping the year with another achievement that shows just how much AI has matured. It\u2019s genuinely great news for a generally terrible 2020. <\/p>\n Sign up for the Future Perfect newsletter<\/em> and we\u2019ll send you a roundup of ideas and solutions for tackling the world\u2019s biggest challenges \u2014 and how to get better at doing good.<\/em><\/p>\n \n