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

Other free copies

• Cold Spring Harbor Laboratory (biorxiv.org)Accepted manuscript · PDF
• California Digital Library (escholarship.org)Preprint · PDF
• Office of Scientific and Technical Information (osti.gov)Preprint · PDF
• National Institutes of Health (ncbi.nlm.nih.gov)Preprint · Web page
• University of Cambridge (repository.cam.ac.uk)Preprint · Web page
• doi.orgFree copy · Web page

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.