Improved protein structure prediction using predicted inter-residue orientations

Citations Over Time

Abstract

Abstract The prediction of inter-residue contacts and distances from co-evolutionary data using deep learning has considerably advanced protein structure prediction. Here we build on these advances by developing a deep residual network for predicting inter-residue orientations in addition to distances, and a Rosetta constrained energy minimization protocol for rapidly and accurately generating structure models guided by these restraints. In benchmark tests on CASP13 and CAMEO derived sets, the method outperforms all previously described structure prediction methods. Although trained entirely on native proteins, the network consistently assigns higher probability to de novo designed proteins, identifying the key fold determining residues and providing an independent quantitative measure of the “ideality” of a protein structure. The method promises to be useful for a broad range of protein structure prediction and design problems.

Related Papers

• → Energy minimization for the flow in ducts and networks(2014)5 cited
• → Constrained optimization and protein structure determination(1991)4 cited
• → An energy minimization method for matching and comparing structured object representations(1997)1 cited
• → Batteries and Energy Minimization Problems(2003)1 cited
• → Can local energy minimization refine the PDB structures of different resolution universally?(2009)