Accurate prediction of protein structures and interactions using a three-track neural network
Min Ki Baek, F DiMaio, I Anishchenko, J Dauparas, S Ovchinnikov, Lee GR, Jichao Wang, Quoc Huy Nguyen Cong, Kinch LN, Schaeffer RD, C Millan, Hyungwook Park, Catharine Adams, Glassman CR, A DeGiovanni, Pereira JH, Rodrigues AV, AA van Dijk, Ebrecht AC, Opperman DJ, T Sagmeister, C Buhlheller, T Pavkov-Keller, Rathinaswamy MK, U Dalwadi, Yip CK, Burke JE, Garcia KC, Grishin NV, Adams PD, Read RJ, D Baker
Abstract
Brief summary: This study reveals a Deep Learning method, 'RoseTTA fold', based on DeepMind's Alphafold2 framework, to predict 3-dimensional protein structures from 1-dimensional sequence information and generate models of protein–protein complexes with high accuracy.
Topics & Concepts
Artificial neural networkComputer scienceArtificial intelligenceProtein structure predictionDeep learningTrack (disk drive)Sequence (biology)Machine learningProtein structureBiologyBiochemistryOperating systemGeneticsMachine Learning in BioinformaticsProtein Structure and DynamicsBioinformatics and Genomic Networks