Unsupervised and Supervised Learning over the Energy Landscape for Protein Decoy Selection

Akhter, Nasrin; Chennupati, Gopinath; Kabir, Kazi Lutful; Djidjev, Hristo Nikolov; Shehu, Amarda

doi:10.3390/biom9100607

Title: Unsupervised and Supervised Learning over the Energy Landscape for Protein Decoy Selection

Journal Article · Mon Oct 14 00:00:00 EDT 2019 · Biomolecules

DOI:https://doi.org/10.3390/biom9100607· OSTI ID:1604000

^[1];

^[2];

^[1];

^[2];

^[1]

George Mason Univ., Fairfax, VA (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

The energy landscape that organizes microstates of a molecular system and governs the underlying molecular dynamics exposes the relationship between molecular form/structure, changes to form, and biological activity or function in the cell. However, several challenges stand in the way of leveraging energy landscapes for relating structure and structural dynamics to function. Energy landscapes are high-dimensional, multi-modal, and often overly-rugged. Deep wells or basins in them do not always correspond to stable structural states but are instead the result of inherent inaccuracies in semi-empirical molecular energy functions. Due to these challenges, energetics is typically ignored in computational approaches addressing long-standing central questions in computational biology, such as protein decoy selection. In the latter, the goal is to determine over a possibly large number of computationally-generated three-dimensional structures of a protein those structures that are biologically-active/native. In recent work, we have recast our attention on the protein energy landscape and its role in helping us to advance decoy selection. Here, we summarize some of our successes so far in this direction via unsupervised learning. More importantly, we further advance the argument that the energy landscape holds valuable information to aid and advance the state of protein decoy selection via novel machine learning methodologies that leverage supervised learning. Our focus in this article is on decoy selection for the purpose of a rigorous, quantitative evaluation of how leveraging protein energy landscapes advances an important problem in protein modeling. However, the ideas and concepts presented here are generally useful to make discoveries in studies aiming to relate molecular structure and structural dynamics to function.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA); National Science Foundation (NSF); Jeffress Memorial Trust

Grant/Contract Number:: 89233218CNA000001; 1900061; 1821154; 20160317ER; AC52-06NA25396

OSTI ID:: 1604000

Report Number(s):: LA-UR-19-27828; BIOMHC

Journal Information:: Biomolecules, Vol. 9, Issue 10; Related Information: This article belongs to the Special Issue An Energy Landscape Perspective of Protein Structure Prediction and Analysis.; ISSN 2218-273X

Publisher:: MDPICopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 4 works

Citation information provided by
Web of Science

References (64)

Methods for estimation of model accuracy in CASP12 Elofsson, Arne; Joo, Keehyoung; Keasar, Chen Proteins: Structure, Function, and Bioinformatics, Vol. 86 https://doi.org/10.1002/prot.25395	journal	October 2017
A mathematical procedure for superimposing atomic coordinates of proteins McLachlan, A. D. Acta Crystallographica Section A, Vol. 28, Issue 6 https://doi.org/10.1107/S0567739472001627	journal	November 1972
The structural bioinformatics library: modeling in biomolecular science and beyond Cazals, Frédéric; Dreyfus, Tom Bioinformatics https://doi.org/10.1093/bioinformatics/btw752	journal	January 2017
Assessment of the assessment: Evaluation of the model quality estimates in CASP10: Model Quality Assessment Kryshtafovych, Andriy; Barbato, Alessandro; Fidelis, Krzysztof Proteins: Structure, Function, and Bioinformatics, Vol. 82 https://doi.org/10.1002/prot.24347	journal	August 2013
Graph-Based Community Detection for Decoy Selection in Template-Free Protein Structure Prediction Kabir, Kazi; Hassan, Liban; Rajabi, Zahra Molecules, Vol. 24, Issue 5 https://doi.org/10.3390/molecules24050854	journal	February 2019
MQAPsingle: A quasi single-model approach for estimation of the quality of individual protein structure models: MQAPsingle Pawlowski, Marcin; Kozlowski, Lukasz; Kloczkowski, Andrzej Proteins: Structure, Function, and Bioinformatics, Vol. 84, Issue 8 https://doi.org/10.1002/prot.24787	journal	May 2016
Scoring function for automated assessment of protein structure template quality Zhang, Yang; Skolnick, Jeffrey Proteins: Structure, Function, and Bioinformatics, Vol. 57, Issue 4 https://doi.org/10.1002/prot.20264	journal	January 2004
Protein model accuracy estimation based on local structure quality assessment using 3D convolutional neural network Sato, Rin; Ishida, Takashi PLOS ONE, Vol. 14, Issue 9 https://doi.org/10.1371/journal.pone.0221347	journal	September 2019
Energy Functions that Discriminate X-ray and Near-native Folds from Well-constructed Decoys Park, Britt; Levitt, Michael Journal of Molecular Biology, Vol. 258, Issue 2 https://doi.org/10.1006/jmbi.1996.0256	journal	May 1996
Announcing the worldwide Protein Data Bank Berman, Helen; Henrick, Kim; Nakamura, Haruki Nature Structural & Molecular Biology, Vol. 10, Issue 12 https://doi.org/10.1038/nsb1203-980	journal	December 2003
The energy landscapes and motions of proteins Frauenfelder, H.; Sligar, S.; Wolynes, P. Science, Vol. 254, Issue 5038 https://doi.org/10.1126/science.1749933	journal	December 1991
Mining high-throughput experimental data to link gene and function Blaby-Haas, Crysten E.; de Crécy-Lagard, Valérie Trends in Biotechnology, Vol. 29, Issue 4 https://doi.org/10.1016/j.tibtech.2011.01.001	journal	April 2011
From molecular energy landscapes to equilibrium dynamics via landscape analysis and markov state models Kabir, Kazi Lutful; Akhter, Nasrin; Shehu, Amarda Journal of Bioinformatics and Computational Biology, Vol. 17, Issue 06 https://doi.org/10.1142/S0219720019400146	journal	December 2019
The role of dynamic conformational ensembles in biomolecular recognition Boehr, David D.; Nussinov, Ruth; Wright, Peter E. Nature Chemical Biology, Vol. 5, Issue 11 https://doi.org/10.1038/nchembio.232	journal	October 2009
Entropy-accelerated exact clustering of protein decoys Berenger, F.; Zhou, Y.; Shrestha, R. Bioinformatics, Vol. 27, Issue 7 https://doi.org/10.1093/bioinformatics/btr072	journal	February 2011
An Energy Landscape Treatment of Decoy Selection in Template-Free Protein Structure Prediction Akhter, Nasrin; Qiao, Wanli; Shehu, Amarda Computation, Vol. 6, Issue 2 https://doi.org/10.3390/computation6020039	journal	June 2018
Improved model quality assessment using ProQ2 Ray, Arjun; Lindahl, Erik; Wallner, Björn BMC Bioinformatics, Vol. 13, Issue 1 https://doi.org/10.1186/1471-2105-13-224	journal	January 2012
Fast algorithm for population-based protein structural model analysis Zhang, Jingfen; Xu, Dong PROTEOMICS, Vol. 13, Issue 2 https://doi.org/10.1002/pmic.201200334	journal	January 2013
Network properties of decoys and CASP predicted models: a comparison with native protein structures Chatterjee, S.; Ghosh, S.; Vishveshwara, S. Molecular BioSystems, Vol. 9, Issue 7 https://doi.org/10.1039/c3mb70157c	journal	January 2013
An empirical energy potential with a reference state for protein fold and sequence recognition Miyazawa, Sanzo; Jernigan, Robert L. Proteins: Structure, Function, and Genetics, Vol. 36, Issue 3 https://doi.org/10.1002/(SICI)1097-0134(19990815)36:3<357::AID-PROT10>3.0.CO;2-U	journal	August 1999
From Extraction of Local Structures of Protein Energy Landscapes to Improved Decoy Selection in Template-Free Protein Structure Prediction Akhter, Nasrin; Shehu, Amarda Molecules, Vol. 23, Issue 1 https://doi.org/10.3390/molecules23010216	journal	January 2018
DeepQA: improving the estimation of single protein model quality with deep belief networks Cao, Renzhi; Bhattacharya, Debswapna; Hou, Jie BMC Bioinformatics, Vol. 17, Issue 1 https://doi.org/10.1186/s12859-016-1405-y	journal	December 2016
Protein Structural Model Selection by Combining Consensus and Single Scoring Methods He, Zhiquan; Alazmi, Meshari; Zhang, Jingfen PLoS ONE, Vol. 8, Issue 9 https://doi.org/10.1371/journal.pone.0074006	journal	September 2013
GOAP: A Generalized Orientation-Dependent, All-Atom Statistical Potential for Protein Structure Prediction Zhou, Hongyi; Skolnick, Jeffrey Biophysical Journal, Vol. 101, Issue 8 https://doi.org/10.1016/j.bpj.2011.09.012	journal	October 2011
Random Forest-Based Protein Model Quality Assessment (RFMQA) Using Structural Features and Potential Energy Terms Manavalan, Balachandran; Lee, Juyong; Lee, Jooyoung PLoS ONE, Vol. 9, Issue 9 https://doi.org/10.1371/journal.pone.0106542	journal	September 2014
Processing and analysis of CASP3 protein structure predictions Zemla, Adam; Venclovas, ?eslovas; Moult, John Proteins: Structure, Function, and Genetics, Vol. 37, Issue S3 https://doi.org/10.1002/(SICI)1097-0134(1999)37:3+<22::AID-PROT5>3.0.CO;2-W	journal	January 1999
Protein structural model selection based on protein-dependent scoring function He, Zhiquan; Shang, Yi; Xu, Dong Statistics and Its Interface, Vol. 5, Issue 1 https://doi.org/10.4310/SII.2012.v5.n1.a10	journal	January 2012
A second molecular biology revolution? The energy landscapes of biomolecular function Nussinov, Ruth; Wolynes, Peter G. Physical Chemistry Chemical Physics, Vol. 16, Issue 14 https://doi.org/10.1039/c4cp90027h	journal	January 2014
machine. Friedman, Jerome H. The Annals of Statistics, Vol. 29, Issue 5 https://doi.org/10.1214/aos/1013203451	journal	October 2001
Distance-scaled, finite ideal-gas reference state improves structure-derived potentials of mean force for structure selection and stability prediction Zhou, Hongyi; Zhou, Yaoqi Protein Science, Vol. 11, Issue 11 https://doi.org/10.1110/ps.0217002	journal	November 2002
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design Alford, Rebecca F.; Leaver-Fay, Andrew; Jeliazkov, Jeliazko R. Journal of Chemical Theory and Computation, Vol. 13, Issue 6 https://doi.org/10.1021/acs.jctc.7b00125	journal	May 2017
Principles that Govern the Folding of Protein Chains Anfinsen, C. B. Science, Vol. 181, Issue 4096 https://doi.org/10.1126/science.181.4096.223	journal	July 1973
Calibur: a tool for clustering large numbers of protein decoys Li, Shuai Cheng; Ng, Yen Kaow BMC Bioinformatics, Vol. 11, Issue 1 https://doi.org/10.1186/1471-2105-11-25	journal	January 2010
SVMQA: support–vector-machine-based protein single-model quality assessment Manavalan, Balachandran; Lee, Jooyoung Bioinformatics, Vol. 33, Issue 16 https://doi.org/10.1093/bioinformatics/btx222	journal	April 2017
Assessment of model accuracy estimations in CASP12 Kryshtafovych, Andriy; Monastyrskyy, Bohdan; Fidelis, Krzysztof Proteins: Structure, Function, and Bioinformatics, Vol. 86 https://doi.org/10.1002/prot.25371	journal	September 2017
ProQ2: estimation of model accuracy implemented in Rosetta Uziela, Karolis; Wallner, Björn Bioinformatics, Vol. 32, Issue 9 https://doi.org/10.1093/bioinformatics/btv767	journal	January 2016
A Novel Side-Chain Orientation Dependent Potential Derived from Random-Walk Reference State for Protein Fold Selection and Structure Prediction Zhang, Jian; Zhang, Yang PLoS ONE, Vol. 5, Issue 10 https://doi.org/10.1371/journal.pone.0015386	journal	October 2010
Smooth orientation-dependent scoring function for coarse-grained protein quality assessment Karasikov, Mikhail; Pagès, Guillaume; Grudinin, Sergei Bioinformatics, Vol. 35, Issue 16 https://doi.org/10.1093/bioinformatics/bty1037	journal	December 2018
Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13 Hou, Jie; Wu, Tianqi; Cao, Renzhi Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12 https://doi.org/10.1002/prot.25697	journal	April 2019
Connecting Molecular Energy Landscape Analysis with Markov Model-based Analysis of Equilibrium Structural Dynamics Kabir, Kazi Lutful; Akhter, Nasrin; Shehu, Amarda Proceedings of 11th International Conference on Bioinformatics and Computational Biology, EPiC Series in Computing https://doi.org/10.29007/tmgc	conference	March 2019
Protein structure prediction by all-atom free-energy refinement Verma, Abhinav; Wenzel, Wolfgang BMC Structural Biology, Vol. 7, Issue 1 https://doi.org/10.1186/1472-6807-7-12	journal	January 2007
BIOCHEMISTRY: How Do Proteins Interact? Boehr, D. D.; Wright, P. E. Science, Vol. 320, Issue 5882 https://doi.org/10.1126/science.1158818	journal	June 2008
Specific interactions for ab initio folding of protein terminal regions with secondary structures Yang, Yuedong; Zhou, Yaoqi Proteins: Structure, Function, and Bioinformatics, Vol. 72, Issue 2 https://doi.org/10.1002/prot.21968	journal	February 2008
CHARMM: A program for macromolecular energy, minimization, and dynamics calculations Brooks, Bernard R.; Bruccoleri, Robert E.; Olafson, Barry D. Journal of Computational Chemistry, Vol. 4, Issue 2 https://doi.org/10.1002/jcc.540040211	journal	July 1983
Ranking predicted protein structures with support vector regression Qiu, Jian; Sheffler, Will; Baker, David Proteins: Structure, Function, and Bioinformatics, Vol. 71, Issue 3 https://doi.org/10.1002/prot.21809	journal	November 2007
Protein model quality assessment using 3D oriented convolutional neural networks Pagès, Guillaume; Charmettant, Benoit; Grudinin, Sergei Bioinformatics, Vol. 35, Issue 18 https://doi.org/10.1093/bioinformatics/btz122	journal	February 2019
Probabilistic Search and Energy Guidance for Biased Decoy Sampling in Ab Initio Protein Structure Prediction Molloy, Kevin; Saleh, Sameh; Shehu, Amarda IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 10, Issue 5 https://doi.org/10.1109/TCBB.2013.29	journal	September 2013
Methods of model accuracy estimation can help selecting the best models from decoy sets: Assessment of model accuracy estimations in CASP11: Estimation of Model Accuracy Kryshtafovych, Andriy; Barbato, Alessandro; Monastyrskyy, Bohdan Proteins: Structure, Function, and Bioinformatics, Vol. 84 https://doi.org/10.1002/prot.24919	journal	September 2015
Free energies of protein decoys provide insight into determinants of protein stability Vorobjev, Y. N. Protein Science, Vol. 10, Issue 12 https://doi.org/10.1110/ps.ps.15501	journal	November 2001
Principles and Overview of Sampling Methods for Modeling Macromolecular Structure and Dynamics Maximova, Tatiana; Moffatt, Ryan; Ma, Buyong PLOS Computational Biology, Vol. 12, Issue 4 https://doi.org/10.1371/journal.pcbi.1004619	journal	April 2016
Critical assessment of methods of protein structure prediction: Progress and new directions in round XI: Progress in CASP XI Moult, John; Fidelis, Krzysztof; Kryshtafovych, Andriy Proteins: Structure, Function, and Bioinformatics, Vol. 84 https://doi.org/10.1002/prot.25064	journal	June 2016
Discrimination of native protein structures using atom-atom contact scoring McConkey, B. J.; Sobolev, V.; Edelman, M. Proceedings of the National Academy of Sciences, Vol. 100, Issue 6 https://doi.org/10.1073/pnas.0535768100	journal	March 2003
MaxSub: an automated measure for the assessment of protein structure prediction quality Siew, N.; Elofsson, A.; Rychlewski, L. Bioinformatics, Vol. 16, Issue 9 https://doi.org/10.1093/bioinformatics/16.9.776	journal	September 2000
Discrimination of the native from misfolded protein models with an energy function including implicit solvation Lazaridis, Themis; Karplus, Martin Journal of Molecular Biology, Vol. 288, Issue 3 https://doi.org/10.1006/jmbi.1999.2685	journal	May 1999
SCUD: Fast structure clustering of decoys using reference state to remove overall rotation Li, Hongzhi; Zhou, Yaoqi Journal of Computational Chemistry, Vol. 26, Issue 11 https://doi.org/10.1002/jcc.20251	journal	January 2005
Sorting protein decoys by machine-learning-to-rank Jing, Xiaoyang; Wang, Kai; Lu, Ruqian Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep31571	journal	August 2016
Distinguishing native conformations of proteins from decoys with an effective free energy estimator based on the OPLS all-atom force field and the surface generalized born solvent model Felts, Anthony K.; Gallicchio, Emilio; Wallqvist, Anders Proteins: Structure, Function, and Genetics, Vol. 48, Issue 2 https://doi.org/10.1002/prot.10171	journal	June 2002
A Second Generation Force Field for the Simulation of Proteins, Nucleic Acids, and Organic Molecules J . Am . Chem . Soc . 1995 , 117 , 5179−5197 Cornell, Wendy D.; Cieplak, Piotr; Bayly, Christopher I. Journal of the American Chemical Society, Vol. 118, Issue 9 https://doi.org/10.1021/ja955032e	journal	January 1996
Protein single-model quality assessment by feature-based probability density functions Cao, Renzhi; Cheng, Jianlin Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep23990	journal	April 2016
Four Small Puzzles That Rosetta Doesn't Solve Das, Rhiju PLoS ONE, Vol. 6, Issue 5 https://doi.org/10.1371/journal.pone.0020044	journal	May 2011
Scoring function for automated assessment of protein structure template quality Zhang, Yang; Skolnick, Jeffrey Proteins: Structure, Function, and Bioinformatics, Vol. 68, Issue 4 https://doi.org/10.1002/prot.21643	journal	June 2007
Factors associated with sufficient knowledge of antibiotics and antimicrobial resistance in the Japanese general population Tsuzuki, Shinya; Fujitsuka, Niina; Horiuchi, Keisuke Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-60444-1	journal	February 2020
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design Douglas, Renfrew, P.; J., O'Meara, Matthew; Philip, Bradley, The University of North Carolina at Chapel Hill University Libraries https://doi.org/10.17615/6sk2-v510	text	January 2017
Protein single-model quality assessment by feature-based probability density functions Cao, Renzhi; Cheng, Jianlin arXiv https://doi.org/10.48550/arxiv.1607.04152	preprint	January 2016

Similar Records

Decoy selection for protein structure prediction via extreme gradient boosting and ranking

Journal Article · Wed Dec 09 00:00:00 EST 2020 · BMC Bioinformatics · OSTI ID:1604000

Akhter, Nasrin; Chennupati, Gopinath; Djidjev, Hristo Nikolov; +1 more

Enforcing constraints for time series prediction in supervised, unsupervised and reinforcement learning

Conference · Fri Apr 03 00:00:00 EDT 2020 · OSTI ID:1604000

Stinis, Panagiotis

Robust Molecular Predictive Methods for Novel Polymer Discovery and Applications

Technical Report · Thu Jan 21 00:00:00 EST 2021 · OSTI ID:1604000

Jiang, Chengyang; Goddard, III, William A.; Jaramillo-Botero, Andres; +1 more

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
97 MATHEMATICS AND COMPUTING
energy landscape
basin
decoy selection
machine learning
purity
model quality assessment

Title: Unsupervised and Supervised Learning over the Energy Landscape for Protein Decoy Selection

Citation Formats

References (64)

Similar Records

Related Subjects