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

• DOI: 10.1126/science.abj8754
• Publication Date: 2021-07-15T19:15:14Z
• Authors: Minkyung Baek; Frank DiMaio; Ivan Anishchenko; Justas Dauparas; Sergey Ovchinnikov; Gyu Rie Lee; Jue Wang; Qian Cong; Lisa N. Kinch; R. Dustin Schaeffer; Claudia Millán; Hahnbeom Park; Carson Adams; Caleb R. Glassman; Andy DeGiovanni; Jose H. Pereira; Andria V. Rodrigues; Alberdina A. van ...; Ana C. Ebrecht; Diederik J. Opperman; Theo Sagmeister; Christoph Buhlheller; Tea Pavkov-Keller; Manoj K. Rathinas...; Udit Dalwadi; Calvin K. Yip; John E. Burke; K. Christopher Ga...; Nick V. Grishin; Paul D. Adams; Randy J. Read; David Baker
• Keywords: CASP; Folding (DSP implementation); Sequence (biology)

Deep learning takes on protein folding In 1972, Anfinsen won a Nobel prize for demonstrating connection between 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. methods took center stage at CASP14, with DeepMind’s Alphafold2 achieving remarkable accuracy. Baek et al . explored network architectures based DeepMind framework. They used three-track to process sequence, distance, coordinate information simultaneously achieved accuracies approaching those DeepMind. The method, RoseTTA fold, can solve challenging x-ray crystallography cryo–electron microscopy modeling problems generate accurate models protein-protein complexes. —VV