Accurate prediction of protein structures and interactions using a 3-track network
Abstract
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 Statement
The authors have declared no competing interest.
Subject Area
- Biochemistry (11725)
- Bioengineering (8728)
- Bioinformatics (29135)
- Biophysics (14940)
- Cancer Biology (12052)
- Cell Biology (17363)
- Clinical Trials (138)
- Developmental Biology (9408)
- Ecology (14147)
- Epidemiology (2067)
- Evolutionary Biology (18272)
- Genetics (12223)
- Genomics (16773)
- Immunology (11844)
- Microbiology (28027)
- Molecular Biology (11564)
- Neuroscience (60841)
- Paleontology (451)
- Pathology (1864)
- Pharmacology and Toxicology (3232)
- Physiology (4940)
- Plant Biology (10405)
- Synthetic Biology (2878)
- Systems Biology (7335)
- Zoology (1642)