Discussion

• @calebwatney Caleb Watney on x

  Shaping up to be a very big decade for biology https://www.technologyreview.com/ ... https://twitter.com/...

• @magda_skipper Magdalena Skipper on x

  A transformative moment for biology & beyond - Highly accurate protein structure prediction for the human proteome; with predictions freely available via a public database hosted by @emblebi https://alphafold.ebi.ac.uk/ @DeepMind https://www.nature.com/...

• @techreview @techreview on x

  The breakthrough could allow biologists from around the world to understand diseases better and develop new drugs. https://www.technologyreview.com/ ...

• @ichaydon Ian Haydon on x

  Here's how a close friend who is a brilliant scientist reacted to this news: “I see people in the streets, going about their lives, and I think 'they don't know how the world just changed.'” Has there ever been a bigger, more impactful data drop in the history of biology? https:/…

• @synbiobeta @synbiobeta on x

  DeepMind has used its AI to predict the shapes of nearly every protein in the human body, as well as the shapes of hundreds of thousands of other proteins found in 20 of the most widely studied organisms, including yeast, fruit flies, and mice. https://ow.ly/...

• @erictopol Eric Topol on x

  One of the most important advances in the history of life science today combines deep learning #AI, the human proteome, #openscience: accurately determining 3D structure of human proteins and organisms via amino acid sequence https://www.nature.com/... @Nature https://twitter.com…

• @natbullard Nat Bullard on x

  My jaw just keeps dropping the more of this article I read https://www.technologyreview.com/ ...

• @demishassabis Demis Hassabis on x

  This is a day I've dreamed of my whole life, this is the reason @DeepMind was founded, to build AI and use it accomplish extraordinary scientific breakthroughs like #AlphaFold 2, to advance science and benefit humanity. I could not be more proud of the incredible team! https://tw…

• @gasca @gasca on x

  I think the average person is completely unprepared for how much biology is going to transform their lives and their kids lives over the coming decades... the pace of progress here is exponential and we are just starting to get beyond the basics... https://twitter.com/...

• @alfonslopeztena @alfonslopeztena on x

  An artificial intelligence lab has given 3-D structure to 350,000 proteins, including every one made by humans, in hours, a task that takes scientists years. A technology to greatly accelerate medical and scientific research, a boon for drug design https://www.nytimes.com/...

• @strwbilly Will Douglas Heaven on x

  Demis Hassabis: “I would say this is the biggest thing we've done so far.” https://www.technologyreview.com/ ...

• @neontaster Noam Blum on x

  DeepMind are amazing. I highly recommend AlphaGo, a documentary about their Go-playing AI. It's available on their YouTube channel for free. Really great watch. https://www.youtube.com/... https://twitter.com/...

• @freerangekids Lenore Skenazy on x

  This is fantastic! So many new avenues opened!!! A.I. Predicts the Shapes of Molecules to Come https://www.nytimes.com/...

• @erictopol Eric Topol on x

  It's a BFD. Coverage https://www.sciencemag.org/... by @RobertFService @ScienceMagazine https://www.nature.com/... @nature by @ewencallaway https://www.statnews.com/... by @KatieMPalmer @statnews https://www.nytimes.com/... by @CadeMetz https://twitter.com/...

• @ryanbethencourt Ryan Bethencourt on x

  This is so incredibly exciting, we have our genome but the structure and function of proteins usually require decades of painstaking work, Deepmind gets us much closer, decades faster 🧬 https://arstechnica-com.cdn.ampproject. org/ ...

• @techreview @techreview on x

  Back in December 2020, DeepMind took the world of biology by surprise when it solved a 50-year grand challenge with an AI tool that predicts the structure of proteins. Last week the company published full details of that tool and released its source code. https://www.technologyre…

• @stearnslab Tim Stearns on x

  This is astounding. Enter your protein (human and some other organisms) and get predetermined structures predicted by AlphaFold2. https://www.nature.com/... https://twitter.com/...

• @amcafee Andrew McAfee on x

  Wait, aren't big greedy tech companies and the privatization of research the antitheses of open science and the public good? https://www.technologyreview.com/ ... https://twitter.com/...

• @70sbachchan Albert Pinto on x

  7/ LFG!! “So far the trove consists of 350,000 newly predicted protein structures. DeepMind says it will predict and release the structures for more than 100 million more in the next few months—more or less all proteins known to science.” https://www.technologyreview.com/ ...

• @synbiobeta @synbiobeta on x

  Proteins belonging to a fruit fly are given shape by DeepMind's A.I. technology. The company's new database includes the 3-D structures for all proteins expressed by the human genome as well as those appearing in 20 other organisms. https://ow.ly/...

• @lifebiomedguru James Lyons-Weiler on x

  That'll be a neat trick, especially since proteins change function when they bind with other proteins. Also there are sliceoforms but we know very little about. https://www.technologyreview.com/ ...

• @briantheligman Brian Heligman on x

  I feel like this is both a huge accomplishment but also likely hard to utilize. My gut feeling is this will be like recreation of the first synthetic genome for a cell - being able to produce it doesn't mean we understand why or how it works Still an amazing accomplishment https:…

• @deepmind @deepmind on x

  Completing the sprint to deliver on the commitments we made at #CASP14 last Dec, we've published 2 papers in @Nature, open-sourced #AlphaFold's code and provided a colab. 4/ https://dpmd.ai/... https://dpmd.ai/... https://dpmd.ai/... https://dpmd.ai/... https://twitter.com/...

• @rincon_p Paul Rincon on x

  Only a fraction of proteins expressed by the human genome have had their structures determined. In work carried out by DeepMind and EMBL, AI was used to predict the structures of virtually the entire complement of human proteins. https://www.bbc.co.uk/...

• @kent_walker Kent Walker on x

  Another amazing achievement by the team at @DeepMind — predicting the structure of the human “proteome”. Great to see these scientific breakthroughs advancing the state of medicine and drug discovery. https://twitter.com/...

• @jjvincent James Vincent on x

  “I see this as the culmination of the entire 10-year-plus lifetime of DeepMind” — @demishassabis on DeepMind's latest work in protein-folding: publishing the entire human proteome online, with 100 million more protein structures to come. Full story here: https://www.theverge.com/…