Within any living organism, there are thousands of different proteins, each with its own unique shape. For decades, the exact formation of those shapes has been a pain for scientists to figure out. How exactly does a protein, which starts as a string of amino acids, fold itself into the funky 3D shapes you might recognize from diagrams? AlphaFold, an AI from DeepMind, may have an answer. It can predict, with heretofore unseen accuracy, the shape a protein will take.

Scientists have been researching how a protein folds into a unique 3D shape for approximately 50 years. Now, thanks to the use of artificial intelligence (AI), U.K.-based AI lab, DeepMind, has helped to solve this scientific mystery, as the organizers of a scientific challenge, CASP (Critical Assessment of protein Structure Prediction) said, which kicked off in the early 1990s, reports Science Alert. Understanding a protein shape could lead to major scientific advancements, as well as environmental ones, per the BBC. The full findings have not yet been published, explains Science Alert, however, the study's abstract can be read over on CASP14, here. SEE ALSO: GOOGLE'S DEEPMIND AI BETTER AT DETECTING BREAST CANCER THAN EXPERTS Proteins are integral as they are present in all living things.

Earlier this week, the Google-owned AI development company DeepMind announced with great fanfare that it had built an algorithm capable of predicting how proteins would fold based on their molecular composition. If it holds up, it's a stunning achievement that's eluded scientists for decades. But Business Insider reports that many experts in the field remain unimpressed, instead calling DeepMind's announcement hype. While critical scientists don't diminish the importance of DeepMind's achievement, they do question whether AlphaFold 2 will actually provide a useful tool to researchers like DeepMind claims. DeepMinds' AlphaFold 2 algorithm scored higher at the Critical Assessment of Structure Prediction (CASP) competition, which tests potential solutions to the protein folding problem, than any other team in history.

Artificial intelligence (AI) has solved one of biology's grand challenges: predicting how proteins fold from a chain of amino acids into 3D shapes that carry out life's tasks. This week, organizers of a protein-folding competition announced the achievement by researchers at DeepMind, a U.K.-based AI company. They say the DeepMind method will have far-reaching effects, among them dramatically speeding the creation of new medications. “What the DeepMind team has managed to achieve is fantastic and will change the future of structural biology and protein research,” says Janet Thornton, director emeritus of the European Bioinformatics Institute. “This is a 50-year-old problem,” adds John Moult, a structural biologist at the University of Maryland, Shady Grove, and co-founder of the competition, Critical Assessment of Protein Structure Prediction (CASP). “I never thought I'd see this in my lifetime.” The body uses tens of thousands of different proteins, each a string of dozens to hundreds of amino acids. The order of the amino acids dictates how the myriad pushes and pulls between them give rise to proteins' complex 3D shapes, which, in turn, determine how they function. Knowing those shapes helps researchers devise drugs that can lodge in proteins' crevices. And being able to synthesize proteins with a desired structure could speed development of enzymes to make biofuels and degrade waste plastic. ![Figure][1] CREDITS: (GRAPH) C. BICKEL/ SCIENCE ; (DATA) CASP For decades, researchers deciphered proteins' structures using experimental techniques such as x-ray crystallography or cryo–electron microscopy (cryo-EM). But such methods can take years and don't always work. Structures have been solved for only about 170,000 of the more than 200 million proteins discovered across life forms. In the 1960s, researchers realized if they could work out all interactions within a protein's sequence, they could predict its shape. But the amino acids in any given sequence could interact in so many different ways that the number of possible structures was astronomical. Computational scientists jumped on the problem, but progress was slow. In 1994, Moult and colleagues launched CASP, which takes place every 2 years. Entrants get amino acid sequences for about 100 proteins whose structures are not known. Some groups compute a structure for each sequence, while others determine it experimentally. The organizers then compare the computational predictions with the lab results and give the predictions a global distance test (GDT) score. Scores above 90 on the 100-point scale are considered on par with experimental methods, Moult says. Even in 1994, predicted structures for small, simple proteins could match experimental results. But for larger, challenging proteins, computations' GDT scores were about 20, “a complete catastrophe,” says Andrei Lupas, a CASP judge and evolutionary biologist at the Max Planck Institute for Developmental Biology. By 2016, competing groups had reached scores of about 40 for the hardest proteins, mostly by drawing insights from known structures of proteins that were closely related to the CASP targets. When DeepMind first competed, in 2018, its algorithm, called AlphaFold, relied on this comparative strategy. But AlphaFold also incorporated a computational approach called deep learning, in which the software is trained on vast data troves—in this case, the sequences and structures of known proteins—and learns to spot patterns. DeepMind won handily, beating the competition by an average of 15% on each structure, and winning GDT scores of up to about 60 for the hardest targets. But the predictions were still too coarse, says John Jumper, who heads AlphaFold's development at DeepMind. “We knew how far we were from biological relevance.” So the team combined deep learning with an “attention algorithm” that mimics the way a person might assemble a jigsaw puzzle: connecting pieces in clumps—in this case clusters of amino acids—and then searching for ways to join the clumps in a larger whole. Working with a computer network built around 128 machine learning processors, they trained the algorithm on all 170,000 or so known protein structures. And it worked. In this year's CASP, AlphaFold achieved a median GDT score of 92.4. For the most challenging proteins, AlphaFold scored a median of 87, 25 points above the next best predictions. It even excelled at solving structures of proteins that sit wedged in cell membranes, which are central to many human diseases but notoriously difficult to solve with x-ray crystallography. Venki Ramakrishnan, a structural biologist at the Medical Research Council Laboratory of Molecular Biology, calls the result “a stunning advance on the protein folding problem.” All groups in this year's competition improved, Moult says. But with AlphaFold, Lupas says, “The game has changed.” The organizers even worried DeepMind may have cheated somehow. So Lupas set a special challenge: a membrane protein from a species of archaea, an ancient group of microbes. For 10 years, his team had tried to get its x-ray crystal structure. “We couldn't solve it.” But AlphaFold had no trouble. It returned a detailed image of a three-part protein with two helical arms in the middle. The model enabled Lupas and his team to make sense of their x-ray data; within half an hour, they had fit their experimental results to AlphaFold's predicted structure. “It's almost perfect,” Lupas says. “They could not possibly have cheated on this. I don't know how they do it.” As a condition of entering CASP, DeepMind—like all groups—agreed to reveal sufficient details about its method for other groups to re-create it. That will be a boon for experimentalists, who will be able to use structure predictions to make sense of opaque x-ray and cryo-EM data. It could also enable drug designers to work out the structure of every protein in new and dangerous pathogens like SARS-CoV-2, a key step in the hunt for molecules to block them, Moult says. Still, AlphaFold doesn't do everything well. In CASP, it faltered on one protein, an amalgam of 52 small repeating segments, which distort each others' positions as they assemble. Jumper says the team now wants to train AlphaFold to solve such structures, as well as those of complexes of proteins that work together to carry out key functions in the cell. Even though one grand challenge has fallen, others will undoubtedly emerge. “This isn't the end of something,” Thornton says. “It's the beginning of many new things.” [1]: pending:yes

The "Techlash" that started last year and flowed steadily through 2020, paints technology and the tech giants that run the world as dark monoliths, casting broad and sometimes sinister shadows across our lives. This week's DeepMind breakthrough is a reminder that the most cutting-edge technology, even those from companies that we no longer fully trust (DeepMind is owned by Alphabet, which owns Google), can alter our lives in demonstrably positive ways. Cade Metz' New York Times piece details how the neural network based DeepMind was used to find a solution to a very difficult biochemistry problem: How to identify protein folds and use that information to figure out what the protein might do and how it could interact with other proteins and even, say, viruses. It's a stunning piece of work because, as AI's are wont to do, DeepMind's "AlphaFold" figured out how to identify a protein's shape in not years, months, or even weeks, but in under an hour. I've been watching DeepMind for years, especially its early triumphs in the game space (it beat champions at the difficult Go game).

A wide range of reinforcement learning (RL) problems -- including robustness, transfer learning, unsupervised RL, and emergent complexity -- require specifying a distribution of tasks or environments in which a policy will be trained. However, creating a useful distribution of environments is error prone, and takes a significant amount of developer time and effort. We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. Existing approaches to automatically generating environments suffer from common failure modes: domain randomization cannot generate structure or adapt the difficulty of the environment to the agent's learning progress, and minimax adversarial training leads to worst-case environments that are often unsolvable. To generate structured, solvable environments for our protagonist agent, we introduce a second, antagonist agent that is allied with the environment-generating adversary. The adversary is motivated to generate environments which maximize regret, defined as the difference between the protagonist and antagonist agent's return. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED). Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.

And there's been a long-standing more than 50-year-old grand challenge in science, which is can you go from the amino acid sequence - which is like a genetic sequence of letters that describes a protein - can you just from that one-dimensional letter sequence come up with a 3D structure?

Alexander Fleming left a petri dish of bacteria out while he went on a two-week holiday. On his return, he found that the dish had been contaminated by a fungus that produced an antibacterial substance. He named it penicillin, and it has since saved millions of lives. Even in the modern world, drug discovery still essentially relies on chance. Pharmaceutical companies often screen thousands of compounds trying to find one with the desired effect.

Proteins are essential to life, supporting practically all its functions. They are large complex molecules made from chains of amino acids. What a protein does mostly depends on its unique 3D structure. Understanding what shapes proteins fold into is known as the'protein folding problem,' and has stood as a grand challenge in biology for the past 50 years. In a significant scientific advance, the artificial intelligence group DeepMind's latest version of the AI system AlphaFold has been detected to solve this grand challenge by the organisers of the biennial Critical Assessment of Protein Structure Prediction (CASP). This breakthrough demonstrates the impact AI can have on fundamental fields that explain and shape the world.

In late January, scientists at DeepMind, Google's London-based AI unit, gathered to discuss whether there was anything they could do to help fight the brewing coronavirus pandemic. At the time, the spread of Covid-19 was still largely confined to the city of Wuhan, but as case numbers continued to grow exponentially, machine learning experts from London to San Francisco were gearing up to try and harness the power of AI to fight the Sars-CoV-2 virus. "Our first reaction was to think how we might be able to help," says Demis Hassabis, CEO and co-founder of DeepMind. "Front of mind was our system, AlphaFold, which we had shown could predict the 3D structure of proteins with unprecedented accuracy compared to other computational methods." At the start of March, DeepMind released predictions generated by AlphaFold for the structures of various proteins associated with SARS-CoV-2, to try and accelerate the process of understanding how the virus functions.