evERdock BAI: Machine-learning-guided selection of protein-protein complex structure
- 5 December 2019
- journal article
- research article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 151 (21), 215104
- https://doi.org/10.1063/1.5129551
Abstract
Computational techniques for accurate and efficient prediction of protein-protein complex structures are widely used for elucidating protein-protein interactions, which play important roles in biological systems. Recently, it has been reported that selecting a structure similar to the native structure among generated structure candidates (decoys) is possible by calculating binding free energies of the decoys based on all-atom molecular dynamics (MD) simulations with explicit solvent and the solution theory in the energy representation, which is called evERdock. A recent version of evERdock achieves a higher-accuracy decoy selection by introducing MD relaxation and multiple MD simulations/energy calculations; however, huge computational cost is required. In this paper, we propose an efficient decoy selection method using evERdock and the best arm identification (BAI) framework, which is one of the techniques of reinforcement learning. The BAI framework realizes an efficient selection by suppressing calculations for nonpromising decoys and preferentially calculating for the promising ones. We evaluate the performance of the proposed method for decoy selection problems of three protein-protein complex systems. Their results show that computational costs are successfully reduced by a factor of 4.05 (in the best case) compared to a standard decoy selection approach without sacrificing accuracy.Funding Information
- Japan Science and Technology Agency, PRSIM (JPMJCR18Y3)
- Japan Society for the Promotion of Science (JP17KT0026, JP19H03191)
- Japan Science and Technology Agency, Core Research for Evolutional Science and Technology (JPMJCR1502)
- Ministry of Education, Culture, Sports, Science and Technology, “Priority Issue on Post-K Computer”
- New Energy and Industrial Technology, P15009, SIP
This publication has 46 references indexed in Scilit:
- Rapid and Accurate Prediction and Scoring of Water Molecules in Protein Binding SitesPLOS ONE, 2012
- Accelerating Protein Docking in ZDOCK Using an Advanced 3D Convolution LibraryPLOS ONE, 2011
- Rosetta3Methods in Enzymology, 2010
- FRODOCK: a new approach for fast rotational protein–protein dockingBioinformatics, 2009
- AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreadingJournal of Computational Chemistry, 2009
- Convergence and combination of methods in protein–protein dockingCurrent Opinion in Structural Biology, 2009
- Conformer Selection and Induced Fit in Flexible Backbone Protein–Protein Docking Using Computational and NMR EnsemblesJournal of Molecular Biology, 2008
- Scalable molecular dynamics with NAMDJournal of Computational Chemistry, 2005
- VMD: Visual molecular dynamicsJournal of Molecular Graphics, 1996
- The refined 2.0 Å X‐ray crystal structure of the complex formed between bovine β‐trypsin and CMTI‐I, a trypsin inhibitor from squash seeds (Cucurbita maxima) Topological similarity of the squash seed inhibitors with the carboxypeptidase A inhibitor from potatoesFEBS Letters, 1989