PT  - JOURNAL ARTICLE
AU  - Minkyung Baek
AU  - Frank DiMaio
AU  - Ivan Anishchenko
AU  - Justas Dauparas
AU  - Sergey Ovchinnikov
AU  - Gyu Rie Lee
AU  - Jue Wang
AU  - Qian Cong
AU  - Lisa N. Kinch
AU  - R. Dustin Schaeffer
AU  - Claudia Millán
AU  - Hahnbeom Park
AU  - Carson Adams
AU  - Caleb R. Glassman
AU  - Andy DeGiovanni
AU  - Jose H. Pereira
AU  - Andria V. Rodrigues
AU  - Alberdina A. van Dijk
AU  - Ana C. Ebrecht
AU  - Diederik J. Opperman
AU  - Theo Sagmeister
AU  - Christoph Buhlheller
AU  - Tea Pavkov-Keller
AU  - Manoj K Rathinaswamy
AU  - Udit Dalwadi
AU  - Calvin K Yip
AU  - John E Burke
AU  - K. Christopher Garcia
AU  - Nick V. Grishin
AU  - Paul D. Adams
AU  - Randy J. Read
AU  - David Baker
TI  - Accurate prediction of protein structures and interactions using a 3-track network
AID  - 10.1101/2021.06.14.448402
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.06.14.448402
4099  - http://biorxiv.org/content/early/2021/06/15/2021.06.14.448402.short
4100  - http://biorxiv.org/content/early/2021/06/15/2021.06.14.448402.full
AB  - DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research.One-Sentence Summary Accurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.Competing Interest StatementThe authors have declared no competing interest.