Accurate prediction of protein structures and interactions using a three-track neural network

Minkyung Baek; Frank DiMaio; Ivan Anishchenko; Justas Dauparas; Sergey Ovchinnikov; Gyu Rie Lee; Jue Wang; Qian Cong; Lisa N Kinch; R Dustin Schaeffer; Claudia Millán; Hahnbeom Park; Carson Adams; Caleb R Glassman; Andy DeGiovanni; Jose H Pereira; Andria V Rodrigues; Alberdina A van Dijk; Ana C Ebrecht; Diederik J Opperman; Theo Sagmeister; Christoph Buhlheller; Tea Pavkov-Keller; Manoj K Rathinaswamy; Udit Dalwadi; Calvin K Yip; John E Burke; K Christopher Garcia; Nick V Grishin; Paul D Adams; Randy J Read; David Baker

doi:10.1126/science.abj8754

Accurate prediction of protein structures and interactions using a three-track neural network

Science. 2021 Aug 20;373(6557):871-876. doi: 10.1126/science.abj8754. Epub 2021 Jul 15.

Authors

Minkyung Baek^{1

2}, Frank DiMaio^{1

2}, Ivan Anishchenko^{1

2}, Justas Dauparas^{1

2}, Sergey Ovchinnikov^{3

4}, Gyu Rie Lee^{1

2}, Jue Wang^{1

2}, Qian Cong^{5

6}, Lisa N Kinch⁷, R Dustin Schaeffer⁶, Claudia Millán⁸, Hahnbeom Park^{1

2}, Carson Adams^{1

2}, Caleb R Glassman^{9

10

11}, Andy DeGiovanni¹², Jose H Pereira¹², Andria V Rodrigues¹², Alberdina A van Dijk¹³, Ana C Ebrecht¹³, Diederik J Opperman¹⁴, Theo Sagmeister¹⁵, Christoph Buhlheller^{15

16}, Tea Pavkov-Keller^{15

17}, Manoj K Rathinaswamy¹⁸, Udit Dalwadi¹⁹, Calvin K Yip¹⁹, John E Burke¹⁸, K Christopher Garcia^{9

10

11

20}, Nick V Grishin^{6

7

21}, Paul D Adams^{12

22}, Randy J Read⁸, David Baker^{23

2

24}

Affiliations

¹ Department of Biochemistry, University of Washington, Seattle, WA 98195, USA.
² Institute for Protein Design, University of Washington, Seattle, WA 98195, USA.
³ Faculty of Arts and Sciences, Division of Science, Harvard University, Cambridge, MA 02138, USA.
⁴ John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, MA 02138, USA.
⁵ Eugene McDermott Center for Human Growth and Development, University of Texas Southwestern Medical Center, Dallas, TX, USA.
⁶ Department of Biophysics, University of Texas Southwestern Medical Center, Dallas, TX, USA.
⁷ Howard Hughes Medical Institute, University of Texas Southwestern Medical Center, Dallas, TX, USA.
⁸ Department of Haematology, Cambridge Institute for Medical Research, University of Cambridge, Cambridge, UK.
⁹ Program in Immunology, Stanford University School of Medicine, Stanford, CA 94305, USA.
¹⁰ Department of Molecular and Cellular Physiology, Stanford University School of Medicine, Stanford, CA 94305, USA.
¹¹ Department of Structural Biology, Stanford University School of Medicine, Stanford, CA 94305, USA.
¹² Molecular Biophysics & Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
¹³ Department of Biochemistry, Focus Area Human Metabolomics, North-West University, 2531 Potchefstroom, South Africa.
¹⁴ Department of Biotechnology, University of the Free State, 205 Nelson Mandela Drive, Bloemfontein 9300, South Africa.
¹⁵ Institute of Molecular Biosciences, University of Graz, Humboldtstrasse 50, 8010 Graz, Austria.
¹⁶ Medical University of Graz, Graz, Austria.
¹⁷ BioTechMed-Graz, Graz, Austria.
¹⁸ Department of Biochemistry and Microbiology, University of Victoria, Victoria, BC, Canada.
¹⁹ Life Sciences Institute, Department of Biochemistry and Molecular Biology, The University of British Columbia, Vancouver, BC, Canada.
²⁰ Howard Hughes Medical Institute, Stanford University School of Medicine, Stanford, CA 94305, USA.
²¹ Department of Biochemistry, University of Texas Southwestern Medical Center, Dallas, TX, USA.
²² Department of Bioengineering, University of California, Berkeley, Berkeley, CA 94720, USA.
²³ Department of Biochemistry, University of Washington, Seattle, WA 98195, USA. [email protected].
²⁴ Howard Hughes Medical Institute, University of Washington, Seattle, WA 98195, USA.

Abstract

DeepMind presented notably accurate predictions at the recent 14th Critical Assessment of Structure Prediction (CASP14) conference. We explored network architectures that incorporate related ideas and obtained the best performance with a three-track network in which information at the one-dimensional (1D) sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging x-ray crystallography and cryo-electron microscopy structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate protein-protein complex models from sequence information alone, short-circuiting traditional approaches that require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

ADAM Proteins / chemistry
Amino Acid Sequence
Computer Simulation
Cryoelectron Microscopy
Crystallography, X-Ray
Databases, Protein
Deep Learning*
Membrane Proteins / chemistry
Models, Molecular
Multiprotein Complexes / chemistry
Neural Networks, Computer
Protein Conformation*
Protein Folding*
Protein Subunits / chemistry
Proteins / chemistry*
Proteins / physiology
Receptors, G-Protein-Coupled / chemistry
Sphingosine N-Acyltransferase / chemistry

Substances

Membrane Proteins
Multiprotein Complexes
Protein Subunits
Proteins
Receptors, G-Protein-Coupled
CERS1 protein, human
Sphingosine N-Acyltransferase
ADAM Proteins

Abstract

Publication types

MeSH terms

Substances

Grants and funding