Article complete

Leading journal Nature applauds Deepmind’s AlphaFold, announces method of the year

DeepMind has introduced AlphaFold1 and AlphaFold2 and, more recently, AlphaFold-Multimer for predicting the structures of known protein complexes.

3D molecular structure illustrating protein folding, showcasing the advancements of DeepMind's AlphaFold.

Key takeaways

  • DeepMind's AlphaFold has revolutionised protein structure prediction, achieving significant milestones in computational biology.
  • AlphaFold2 outperformed competitors in the 2020 CASP competition, showcasing its advanced predictive capabilities.
  • The collaboration between DeepMind and the European Molecular Biology Laboratory has led to the prediction of over 350,000 protein structures.
  • AlphaFold-Multimer extends the ability to predict structures of known protein complexes, further enhancing research potential.
  • RoseTTAFold, developed by the University of Washington, employs a unique architecture to model protein structures and complexes.

Takeaways drafted with AI from the article text.

The potential to predict protein three-dimensional (3D) structures given a linear sequence of amino acids has been the holy grail of computational biologists for years. In the past year, the deep-learning-based methods AlphaFold2 and RoseTTAfold have achieved this feat over a range of targets. In the light of these major milestones, Nature Methods has chosen protein structure prediction as their Method of the Year 2021.

In Critical Assessment of Protein Structure Prediction (CASP) competition, scientists test the prowess of their methods that computationally predict the intricate three-dimensional (3D) structure of a protein from a sequence of amino acids. At the14th CASP in 2020, AlphaFold2 blew away its competitors. 

RoseTTAFold is a method with a ‘three-track’ network architecture developed in the lab of David Baker and colleagues at the University of Washington along with academic teams around the world. The method is used to predict protein structures and generate models of protein-protein complexes.

Published

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

DeepMind · 5 stories
  1. DeepMind Releases Acme - A Framework To Decrease Complexities In AI Workflows
  2. You are here: Leading journal Nature applauds Deepmind’s AlphaFold, announces method of the year
  3. What is up with AlphaFold?
  4. Google DeepMind Launches AlphaProteo , an AI Model for Generating Proteins 
  5. While We Grapple With Geometry, Google DeepMind's AI Model Beats Math Olympiad Gold Medalists
About the author

Contributor

All stories
Belamy · Daily

The day’s AI news, before your first meeting.