NIDA IRP Technology Development Initiative Featured Paper

Highly accurate protein structure prediction for the human proteome

Published in Nature (2021)

Image copyright: Nature

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

Paper presented by Dr. Joshua Hinkle and selected by the NIDA TDI Paper of the Month Committee

Publication Brief Description

Determining complete protein structures is difficult as sufficient quantities need to be purified; protein size, transmembrane domains, and susceptibility to conformational changes create inconsistencies; and the work can take months to years. While protein sequence prediction is not new, increases in computation and artificial intelligence have enhanced accuracy and scale allowing for AlphaFold’s 3D machine learning to predict protein structure more accurately from primary sequence. Tunyasuvunakool et al. applied AlphaFold to predict full-length structures with detailed chemical components of nearly the entire human proteome (98.5%) as well as ~20 other organisms and provided this data in a public database. Since publication, the authors updated AlphaFold (version 2) shortening days-long prediction computation to minutes/hours and the database now has over 200 million protein structures. As current methods are used in conjunction with AlphaFold to validate predicted structures and improve machine learning, structure prediction accuracy will increase allowing for structures of proteins to be predicted in different molecular and cellular environments. The AlphaFold database is an invaluable resource for providing new insight into protein interactions, functions, and therapeutic drug development.

Tunyasuvunakool, Kathryn; Adler, Jonas; Wu, Zachary; Green, Tim; Zielinski, Michal; Žídek, Augustin; Bridgland, Alex; Cowie, Andrew; Meyer, Clemens; Laydon, Agata; Velankar, Sameer; Kleywegt, Gerard J; Bateman, Alex; Evans, Richard; Pritzel, Alexander; Figurnov, Michael; Ronneberger, Olaf; Bates, Russ; Kohl, Simon A A; Potapenko, Anna; Ballard, Andrew J; Romera-Paredes, Bernardino; Nikolov, Stanislav; Jain, Rishub; Clancy, Ellen; Reiman, David; Petersen, Stig; Senior, Andrew W; Kavukcuoglu, Koray; Birney, Ewan; Kohli, Pushmeet; Jumper, John; Hassabis, Demis

Highly accurate protein structure prediction for the human proteome Journal Article

In: Nature, vol. 596, no. 7873, pp. 590–596, 2021, ISSN: 1476-4687.

Abstract | Links

@article{pmid34293799,

title = {Highly accurate protein structure prediction for the human proteome},

author = {Kathryn Tunyasuvunakool and Jonas Adler and Zachary Wu and Tim Green and Michal Zielinski and Augustin Žídek and Alex Bridgland and Andrew Cowie and Clemens Meyer and Agata Laydon and Sameer Velankar and Gerard J Kleywegt and Alex Bateman and Richard Evans and Alexander Pritzel and Michael Figurnov and Olaf Ronneberger and Russ Bates and Simon A A Kohl and Anna Potapenko and Andrew J Ballard and Bernardino Romera-Paredes and Stanislav Nikolov and Rishub Jain and Ellen Clancy and David Reiman and Stig Petersen and Andrew W Senior and Koray Kavukcuoglu and Ewan Birney and Pushmeet Kohli and John Jumper and Demis Hassabis},

url = {https://pubmed.ncbi.nlm.nih.gov/34293799/},

doi = {10.1038/s41586-021-03828-1},

issn = {1476-4687},

year  = {2021},

date = {2021-08-01},

urldate = {2021-08-01},

journal = {Nature},

volume = {596},

number = {7873},

pages = {590--596},

abstract = {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. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold, 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.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}