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

Abstract

Deep learning takes on protein folding In 1972, Anfinsen won a Nobel prize for demonstrating a connection between a protein’s amino acid sequence and its three-dimensional structure. Since 1994, scientists have competed in the biannual Critical Assessment of Structure Prediction (CASP) protein-folding challenge. Deep learning methods took center stage at CASP14, with DeepMind’s Alphafold2 achieving remarkable accuracy. Baek et al . explored network architectures based on the DeepMind framework. They used a three-track network to process sequence, distance, and coordinate information simultaneously and achieved accuracies approaching those of DeepMind. The method, RoseTTA fold, can solve challenging x-ray crystallography and cryo–electron microscopy modeling problems and generate accurate models of protein-protein complexes. —VV

Keywords

MeSH Terms

Affiliated Institutions

• University of California, Berkeley US
• BioTechMed-Graz AT
• Harvard University US
• University of Graz AT
• Lawrence Berkeley National Laboratory US
• University of Cambridge GB
• Stanford University US
• North-West University ZA
• The University of Texas Southwestern Medical Center US
• University of the Free State ZA
• University of British Columbia CA
• University of Washington US
• Howard Hughes Medical Institute US
• Harvard University Press US
• Medical University of Graz AT
• University of Victoria CA

Related Publications