Paper
Highly accurate protein structure prediction for the human proteome
Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure<sup>1</sup>. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold<sup>2</sup>, at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.
Authors: Kathryn Tunyasuvunakool · Jonas Adler · Zachary Wu · Tim Green · Michal Zielinski · Augustin Žídek · Alex Bridgland · Andrew Cowie · Clemens Meyer · Agata Laydon · Sameer Velankar · Gerard J. Kleywegt · Alex Bateman · Richard Evans · Alexander Pritzel · Michael Figurnov · Olaf Ronneberger · Russ Bates · Simon A. A. Kohl · Anna Potapenko · Andrew J. Ballard · Bernardino Romera-Paredes · Stanislav Nikolov · Rishub Jain · Ellen Clancy · David Reiman · Stig Petersen · Andrew W. Senior · Koray Kavukcuoglu · Ewan Birney · Pushmeet Kohli · John Jumper · Demis Hassabis