Accurate prediction of protein structures and interactions using a three-track neural network
| Autor: | Jose Henrique Pereira, Ana C. Ebrecht, Lisa N. Kinch, R. Dustin Schaeffer, Ivan Anishchenko, Justas Dauparas, Udit Dalwadi, Gyu Rie Lee, Christoph Buhlheller, Diederik J. Opperman, David Baker, Tea Pavkov-Keller, Qian Cong, Caleb R. Glassman, Alberdina A. van Dijk, Jue Wang, Andria V. Rodrigues, Theo Sagmeister, Randy J. Read, Andy DeGiovanni, Hahnbeom Park, Paul D. Adams, Calvin K. Yip, Frank DiMaio, John E. Burke, Claudia Millán, K. Christopher Garcia, Carson Adams, Minkyung Baek, Nick V. Grishin, Sergey Ovchinnikov, Manoj K. Rathinaswamy |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Structure (mathematical logic)
0303 health sciences Sequence Network architecture Multidisciplinary Artificial neural network business.industry Computer science Deep learning computer.software_genre Modeling and simulation 03 medical and health sciences Structural bioinformatics 0302 clinical medicine Data mining Artificial intelligence business Distance transform computer 030217 neurology & neurosurgery 030304 developmental biology |
| Zdroj: | Science. 373:871-876 |
| ISSN: | 1095-9203 0036-8075 |
| DOI: | 10.1126/science.abj8754 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|