/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Alphabet's DeepMind says it has solved the key “protein folding problem”, cutting the job down from months to hours, which could speed up drug discovery

Researchers at DeepMind say they have solved “the protein folding problem,” a task that has bedeviled scientists for more than 50 years.

New York Times Cade Metz

Discussion

  • @demishassabis Demis Hassabis on x
    Thrilled to announce our first major breakthrough in applying AI to a grand challenge in science. #AlphaFold has been validated as a solution to the ‘protein folding problem’ & we hope it will have a big impact on disease understanding and drug discovery: https://deepmind.com/...
  • @jasoncrawford Jason Crawford on x
    Today Google @DeepMind announced that their deep learning system AlphaFold has achieved unprecedented levels of accuracy on the “protein folding problem”, a grand challenge problem in computational biochemistry. What is this problem, and why is it hard? https://deepmind.com/...
  • @deepmind @deepmind on x
    Read more about #AlphaFold and #CASP14: http://deepmind.com/... https://twitter.com/...
  • @balajis @balajis on x
    DeepMind just annihilated CASP and may have solved protein folding. The graph reminds me of the curves from Kurzweil's The Singularity is Near. Sometimes, there doesn't seem to be much progress until right before it goes totally vertical. https://twitter.com/... https://twitter.c…
  • @officeforai @officeforai on x
    DeepMind's breakthrough in protein-folding could accelerate research in drug design, treating diseases, and environmental sustainability. A proud achievement for UK AI. A monumental feat for science. Well done to everyone @DeepMind. https://deepmind.com/... #AlphaFold #CASP14
  • @oriolvinyalsml Oriol Vinyals on x
    Biology's ImageNet moment has arrived: #AlphaFold2 solves Protein Folding at the #CASP14 competition! Blog: https://deepmind.com/... https://twitter.com/...
  • @quantamagazine Quanta on x
    DeepMind has moved beyond games like Go and StarCraft. A new AI developed by DeepMind called AlphaFold can predict the shape of a protein with near atomic accuracy, @strwbilly reports for @techreview. https://www.technologyreview.com/ ...
  • @bretweinstein Bret Weinstein on x
    DeepMind's apparent success in predicting tertiary protein structure from primary sequence data suggests two things: 1) A.I. has jumped a level in capacity. 2) The protein folding problem is likely simpler than we think. The latter almost has to be true. https://www.businessinsid…
  • @stevenstrogatz Steven Strogatz on x
    DeepMind's AI makes gigantic leap in solving protein structures. The “deep-learning network was head-and-shoulders above other teams and, say scientists, performed so mind-bogglingly well that it could herald a revolution in biology.” #whoa https://www.nature.com/...
  • @ninadschick Nina Schick on x
    Truly a stunning breakthrough that many did not expect to come so soon. #AlphaFold https://twitter.com/...
  • @helenczerski Helen Czerski on x
    Maybe, in 50 years time, 2020 will be remembered for this instead of Covid. At least 2020 is getting better as we go along. What are the odds it will finish with really extensive close-up video of swimming colossal squids & workable fusion power? https://www.theguardian.com/ ...
  • @bznotes Bilal Zuberi on x
    This is absolutely next level breakthrough in science. Covid vaccine took 2 days to design. It might take 2 minutes in the future. I am very long on SIMULATION. We will discover, design, engineer, test the physical world in-SILICO first. https://twitter.com/...
  • @avinash Avinash Kaushik on x
    Let us take a moment away from the distractions to appreciate what a very big deal this is... I would have expected us to be decades from being able to do this. More work to do, but #machinelearningFTW! https://twitter.com/...
  • @naturenews @naturenews on x
    The ability to accurately predict protein structures from their amino-acid sequence would vastly accelerate efforts to understand the building blocks of cells and enable quicker and more advanced drug discovery. https://go.nature.com/2JAMkMf
  • @jimwaterson Jim Waterson on x
    It's mildly cool that Demis Hassabis' company is revolutionising medicine using artificial intelligence but it's much cooler that he also coded the game Theme Park. https://www.theguardian.com/ ...
  • @brian_armstrong Brian Armstrong on x
    Congrats to @DeepMind on the incredible progress. Science and technology are are some of the most important levers to improve the world. https://twitter.com/...
  • @nature @nature on x
    An artificial intelligence network developed by Google AI offshoot DeepMind has made a gargantuan leap in solving one of biology's grandest challenges — determining a protein's 3D shape from its amino-acid sequence. https://go.nature.com/3o1UmwO
  • @mkapor Mitch Kapor on x
    This is a wonderful use for a neural network https://www.nytimes.com/...
  • @ewencallaway Ewen Callaway on x
    This won't make techniques, such as X-ray crystallography and cryo-EM obsolete, people told me. But could help structural biologists generate good models from these data more quickly and easily. It's already done so with X-ray. Keen to see how cryo-em uses it. https://twitter.com…
  • @jeffjarvis Jeff Jarvis on x
    3,2,1... until the dystopians find some reason to fear this. https://twitter.com/...
  • @fchollet Franois Chollet on x
    AlphaFold is a big breakthrough in the application of AI to scientific research. One of many to come! https://deepmind.com/...
  • @isaachasson Isaac Hasson on x
    This is absolutely bananas. AlphaFold from @DeepMind can now predict protein folding with high fidelity, including proteins scientists have been trying to understand for decades. https://www.nytimes.com/... https://twitter.com/...
  • @jimalkhalili Jim Al-Khalili on x
    Fantastic scientific breakthrough. One of the biggest problems in science (protein folding) looks like it's been cracked by artificial intelligence. Huge implications for medicine. Congratulations @DeepMind #AlphaFold https://twitter.com/...
  • @naturenews @naturenews on x
    Google's deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists. https://www.nature.com/...
  • @matthewcobb Matthew Cobb on x
    It's really a 63-year old problem going back to Crick's sequence hypothesis which he enunciated in 1957 and published in 1958, and we still don't understand how it works, but we can now predict protein structure from DNA sequence. Amazing! https://twitter.com/...
  • @marcelsalathe Marcel Salath on x
    “It's a breakthrough of the first order, certainly one of the most significant scientific results of my lifetime.” Indeed, the implications are profound. Not only for protein folding and thus drug design. This is technology changing everything. https://www.nature.com/...
  • @esyudkowsky Eliezer Yudkowsky on x
    I claim victory over everyone who doubted the step of my reasoning that went “And obviously a superintelligent AI suffices to crack protein structure prediction.” It was silly that people tried to argue with that massively overdetermined step, but they did. https://twitter.com/..…
  • @francesarnold Frances Arnold on x
    Pretty impressive! Perhaps we can now move to the protein function problem? https://twitter.com/...
  • @dcms @dcms on x
    .@DeepMind has developed a way for AI to predict protein structures — a breakthrough that could significantly speed up the design of new drugs 💊 and help scientists better understand diseases 🔬. Read more: https://deepmind.com/... https://twitter.com/...
  • @sundarpichai Sundar Pichai on x
    .@DeepMind's incredible AI-powered protein folding breakthrough will help us better understand one of life's fundamental building blocks + enable researchers to tackle new and hard problems, from fighting diseases to environmental sustainability. https://deepmind.com/...
  • @suedhellmann Sue Desmond-Hellmann on x
    Wow! As we've seen with COVID19 vaccines, we are getting much better -and faster- at solving problems. Makes a big difference. https://twitter.com/...
  • @hadip Hadi Partovi on x
    This is groundbreaking for everything from medicine to agriculture to the environment. @DeepMind AI has mastered the “impossible” computational challenge of protein folding, with accuracy jumping from 42/100 to 92/100 in 4 years, predicting protein shapes to an atom's width. http…
  • @tabithagold Tabitha Goldstaub on x
    Nice one @DeepMind Professor Dame Janet Thornton, Director Emeritus EMBL-EBI said it better than me - after decades of studying proteins, the molecules that provide the structure and functions of all living things she said “I awoke this morning feeling that progress has been made…
  • @cademetz Cade Metz on x
    DeepMind, the London A.I. lab, says it has solved “the protein folding problem.” This long-sought breakthrough could accelerate the ability to understand diseases, develop new medicines and unlock mysteries of the human body: https://www.nytimes.com/...