Accurate prediction of protein structures and interactions using a three-track neural network
Minkyung Baek, Frank DiMaio, David Baker · Collaboration of ~23 authors led from the University of Washington (Baker lab) and collaborators; David Baker is the corresponding/senior author. Other authors include Ivan Anishchenko, Justas Dauparas, Sergey Ovchinnikov, Gyu Rie Lee, Jue Wang.
Summary
This paper presented RoseTTAFold, a three-track neural network that simultaneously processes one-dimensional sequence, two-dimensional residue-pair distances, and three-dimensional atomic coordinate information, with information flowing between the tracks. The method achieved protein structure prediction accuracy approaching that of AlphaFold2 while being more computationally efficient. It also demonstrated rapid generation of accurate models for protein-protein complexes.
Key findings
- A three-track architecture that exchanges information among sequence, distance, and coordinate representations substantially improves prediction over two-track approaches.
- RoseTTAFold produced accurate single-chain structures and could model protein complexes, with run times short enough for practical use.
- The system was used to build models for biologically important proteins, including human targets relevant to function and drug discovery.
Subjects & keywords
Cite this paper
Minkyung Baek, Frank DiMaio, & David Baker [Collaboration of ~23 authors led from the University of Washington (Baker lab) and collaborators; David Baker is the corresponding/senior author. Other authors include Ivan Anishchenko, Justas Dauparas, Sergey Ovchinnikov, Gyu Rie Lee, Jue Wang.] (2021). Accurate prediction of protein structures and interactions using a three-track neural network. Science. https://doi.org/10.1126/science.abj8754
@article{baek2021accurate,
author = {Minkyung Baek and Frank DiMaio and David Baker and {Collaboration of ~23 authors led from the University of Washington (Baker lab) and collaborators; David Baker is the corresponding/senior author. Other authors include Ivan Anishchenko, Justas Dauparas, Sergey Ovchinnikov, Gyu Rie Lee, Jue Wang.}},
title = {Accurate prediction of protein structures and interactions using a three-track neural network},
journal = {Science},
year = {2021},
doi = {10.1126/science.abj8754},
url = {https://doi.org/10.1126/science.abj8754}
}