scholarly journals Assessment of protein model structure accuracy estimation in CASP13: Challenges in the era of deep learning

2019 ◽  
Vol 87 (12) ◽  
pp. 1351-1360 ◽  
Author(s):  
Jonghun Won ◽  
Minkyung Baek ◽  
Bohdan Monastyrskyy ◽  
Andriy Kryshtafovych ◽  
Chaok Seok
Keyword(s):  
Deep Learning ◽  
Model Structure ◽  
Accuracy Estimation ◽  
Protein Model ◽  
Structure Accuracy

scholarly journals Improved protein structure refinement guided by deep learning based accuracy estimation

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Naozumi Hiranuma ◽  
Hahnbeom Park ◽  
Minkyung Baek ◽  
Ivan Anishchenko ◽  
Justas Dauparas ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Structure ◽  
Structure Refinement ◽  
Global Energy ◽  
Accuracy Estimation ◽  
X Ray ◽  
Learning Framework ◽  
Protein Structure Refinement ◽  
Protein Models ◽  
Multiple Stages

AbstractWe develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.

scholarly journals Improved protein structure refinement guided by deep learning based accuracy estimation

2020 ◽  
Author(s):  
Naozumi Hiranuma ◽  
Hahnbeom Park ◽  
Minkyung Baek ◽  
Ivan Anishchanka ◽  
Justas Dauparas ◽  
...  
Keyword(s):  
Deep Learning ◽  
Protein Structure ◽  
Structure Refinement ◽  
Global Energy ◽  
Accuracy Estimation ◽  
X Ray ◽  
Learning Framework ◽  
Protein Structure Refinement ◽  
Protein Models ◽  
Multiple Stages

AbstractWe develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.

scholarly journals Protein model structure evaluation using the solvation free energy of folding.

1990 ◽  
Vol 87 (8) ◽  
pp. 3240-3243 ◽  
Author(s):  
L. Chiche ◽  
L. M. Gregoret ◽  
F. E. Cohen ◽  
P. A. Kollman
Keyword(s):  
Free Energy ◽  
Solvation Free Energy ◽  
Model Structure ◽  
Protein Model ◽  
Structure Evaluation
Sign in / Sign up

Export Citation Format

Share Document