Machine Learning & Data Science Popular

‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge

Google’s UK-based lab and research company DeepMind says its AlphaFold AI system has solved the protein folding problem, a grand challenge that has vexed the biology research community for half a century.

Google’s UK-based lab and research company DeepMind says its AlphaFold AI system has solved the protein folding problem, a grand challenge that has vexed the biology research community for half a century.

Today’s dramatic announcement follows an endorsement from organizers of the biennial Critical Assessment of Protein Structure Prediction (CASP). DeepMind says the breakthrough “demonstrates the impact AI can have on scientific discovery and its potential to dramatically accelerate progress in some of the most fundamental fields that explain and shape our world.”

Proteins are large biomolecules that consist of one or more long chains of smaller components called amino acid residues and perform a vast array of essential functions. Since the biochemist Christian Anfinsen delivered his famous acceptance speech for the 1972 Nobel Prize in Chemistry, the theory that a protein’s amino acid sequence should fully determine its structure has inspired generations of researchers to explore the protein folding problem. That long quest to computationally predict a protein’s 3D structure based solely on its 1D amino acid sequence has finally paid off.

image.png

Reaction to the announcement was swift. “This is a big deal, in some sense the problem is solved,” said John Moult, a computational biologist at the University of Maryland and CASP co-founder. Professor Andrei Lupas, Director of the Max Planck Institute for Developmental Biology and a CASP assessor, applauded AlphaFold’s progress: “This will change medicine. It will change research. It will change bioengineering. It will change everything.” Lupas says “AlphaFold’s astonishingly accurate models have allowed us to solve a protein structure we were stuck on for close to a decade, relaunching our effort to understand how signals are transmitted across cell membranes.”

Renowned Google DeepMind research scientist Oriol Vinyals meanwhile characterized the DeepMind breakthrough as “Biology’s ImageNet moment” in a nod to the image dataset that helped drive landmark computer vision and ML achievements such as AlexNet in 2012 and 2015’s ResNet.

DeepMind says AlphaFold is one of their most significant advances to date, and that the progress suggests “AI will become one of humanity’s most useful tools in expanding the frontiers of scientific knowledge.” They say future research in this area may look at how multiple proteins form complexes, how they interact with DNA, RNA, or small molecules, and how to determine the precise location of all amino acid side chains.


Reporter: Fangyu Cai | Editor: Michael Sarazen


B4.png

Synced Report | A Survey of China’s Artificial Intelligence Solutions in Response to the COVID-19 Pandemic — 87 Case Studies from 700+ AI Vendors

This report offers a look at how China has leveraged artificial intelligence technologies in the battle against COVID-19. It is also available on Amazon KindleAlong with this report, we also introduced a database covering additional 1428 artificial intelligence solutions from 12 pandemic scenarios.

Click here to find more reports from us.


AI Weekly.png

We know you don’t want to miss any news or research breakthroughs. Subscribe to our popular newsletter Synced Global AI Weekly to get weekly AI updates.

13 comments on “‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge

  1. Pingback: [N] ‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge – tensor.io

  2. Pingback: [N] ‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge – ONEO AI

  3. Pingback: ‘Biology’s ImageNet Moment’ – DeepMind Says Its AlphaFold Has Cracked a 50-Year-Old Biology Challenge – Dedes News

  4. Pingback: A short history of Deepmind – Gregory Bufithis

  5. Pingback: LONG READ: DeepMind, proteins and artificial intelligence … and the ascendance of natural language processing – Gregory Bufithis

  6. Pingback: 2020 in Review With Jürgen Schmidhuber - WaYs-2-rOcK

  7. Pingback: 2020 in Review With Sheldon Fernandez - Artificial Intelligence

  8. Pingback: 2020 in Review With Tatsuya Nagata | Global Research Syndicate

  9. Pingback: Nature Paper: Atomistic ML Models Demonstrate Amorphous Silicon States & Transitions | Synced

  10. Pingback: Nature Paper: Atomistic ML Models Demonstrate Amorphous Silicon States & Transitions | NEO Share

  11. Pingback: Nature Paper: Los modelos atomísticos de ML demuestran estados y transiciones de silicio amorfo – Editora PI9

  12. Pingback: DeepMind Introduce AlphaFold-Multimer to Predict Multi-Chain Protein Complexes with Better Accuracy | Synced DeepMind Introduce AlphaFold-Multimer to Predict Multi-Chain Protein Complexes with Better Accuracy

  13. Pingback: DeepMind Introduce AlphaFold-Multimer to Predict Multi-Chain Protein Complexes with Better Accuracy – Open Source Biology & Genetics Interest Group

Leave a Reply

Your email address will not be published.

%d bloggers like this: