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

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. 

DeepMind has introduced AlphaFold1 and AlphaFold2 and, more recently, AlphaFold-Multimer for predicting the structures of known protein complexes. A collaboration between the European Molecular Biology Laboratory and DeepMind has predicted structures for over 350,000 proteins for 21 model organisms and made them freely available at the AlphaFold Protein Structure Database — with plans for expanding predictions to millions of structures in 2022.

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.