DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability

Abstract

Predicting how a point mutation alters a protein’s stability can guide pharmaceutical drug design initiatives which aim to counter the effects of serious diseases. Conducting mutagenesis studies in physical proteins can give insights about the effects of amino acid substitutions, but such wet-lab work is prohibitive due to the time as well as financial resources needed to assess the effect of even a single amino acid substitution. Computational methods for predicting the effects of a mutation on a protein structure can complement wet-lab work, and varying approaches are available with promising accuracy rates. In this work we compare and assess the utility of several machine learning methods and their ability to predict the effects of single and double mutations. We in silico generate mutant protein structures, and compute several rigidity metrics for each of them. We use these as features for our Support Vector Regression (SVR), Random Forest (RF), and Deep Neural Network (DNN) methods. We validate the predictions of our in silico mutations against experimental ΔΔG stability data, and attain Pearson Correlation values upwards of 0.71 for single mutations, and 0.81 for double mutations. We perform ablation studies to assess which features contribute most to a model’s success, andmore » also introduce a voting scheme to synthesize a single prediction from the individual predictions of the three models.« less

Authors:
 [1];  [2];  [2];  [2];  [1];  [1];  [3];  [2]
  1. Univ. of Massachusetts Boston, MA (United States). Dept. of Computer Science
  2. Western Washington Univ., Bellingham, WA (United States). Dept. of Computer Science
  3. Western Washington Univ., Bellingham, WA (United States). Dept. of Computer Science; Pacific Northwest National Lab. (PNNL), Richland, WA (United States). Computing and Analytics Division
Publication Date:
Research Org.:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1628486
Grant/Contract Number:  
AC05-76RL01830
Resource Type:
Accepted Manuscript
Journal Name:
Molecules
Additional Journal Information:
Journal Volume: 23; Journal Issue: 2; Journal ID: ISSN 1420-3049
Publisher:
MDPI
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; 59 BASIC BIOLOGICAL SCIENCES; 97 MATHEMATICS AND COMPUTING; Biochemistry & Molecular Biology; Chemistry; machine learning; protein mutational study; SVR; RF; DNN; rigidity analysis

Citation Formats

Dehghanpoor, Ramin, Ricks, Evan, Hursh, Katie, Gunderson, Sarah, Farhoodi, Roshanak, Haspel, Nurit, Hutchinson, Brian, and Jagodzinski, Filip. Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability. United States: N. p., 2018. Web. doi:10.3390/molecules23020251.
Dehghanpoor, Ramin, Ricks, Evan, Hursh, Katie, Gunderson, Sarah, Farhoodi, Roshanak, Haspel, Nurit, Hutchinson, Brian, & Jagodzinski, Filip. Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability. United States. https://doi.org/10.3390/molecules23020251
Dehghanpoor, Ramin, Ricks, Evan, Hursh, Katie, Gunderson, Sarah, Farhoodi, Roshanak, Haspel, Nurit, Hutchinson, Brian, and Jagodzinski, Filip. Sat . "Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability". United States. https://doi.org/10.3390/molecules23020251. https://www.osti.gov/servlets/purl/1628486.
@article{osti_1628486,
title = {Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability},
author = {Dehghanpoor, Ramin and Ricks, Evan and Hursh, Katie and Gunderson, Sarah and Farhoodi, Roshanak and Haspel, Nurit and Hutchinson, Brian and Jagodzinski, Filip},
abstractNote = {Predicting how a point mutation alters a protein’s stability can guide pharmaceutical drug design initiatives which aim to counter the effects of serious diseases. Conducting mutagenesis studies in physical proteins can give insights about the effects of amino acid substitutions, but such wet-lab work is prohibitive due to the time as well as financial resources needed to assess the effect of even a single amino acid substitution. Computational methods for predicting the effects of a mutation on a protein structure can complement wet-lab work, and varying approaches are available with promising accuracy rates. In this work we compare and assess the utility of several machine learning methods and their ability to predict the effects of single and double mutations. We in silico generate mutant protein structures, and compute several rigidity metrics for each of them. We use these as features for our Support Vector Regression (SVR), Random Forest (RF), and Deep Neural Network (DNN) methods. We validate the predictions of our in silico mutations against experimental ΔΔG stability data, and attain Pearson Correlation values upwards of 0.71 for single mutations, and 0.81 for double mutations. We perform ablation studies to assess which features contribute most to a model’s success, and also introduce a voting scheme to synthesize a single prediction from the individual predictions of the three models.},
doi = {10.3390/molecules23020251},
journal = {Molecules},
number = 2,
volume = 23,
place = {United States},
year = {Sat Jan 27 00:00:00 EST 2018},
month = {Sat Jan 27 00:00:00 EST 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Figures / Tables:

Figure 1 Figure 1: Cartoon (left) and Rigidity analysis (right) of PDB file 1hvr. Atoms in different rigid clusters are colored by cluster membership. The largest rigid cluster (red-brown) spans both halves of the protein.

Save / Share:

Works referenced in this record:

Hydrophobic stabilization in T4 lysozyme determined directly by multiple substitutions of Ile 3
journal, August 1988

  • Matsumura, Masazumi; Becktel, Wayne J.; Matthews, Brian W.
  • Nature, Vol. 334, Issue 6181
  • DOI: 10.1038/334406a0

Contributions of hydrogen bonds of Thr 157 to the thermodynamic stability of phage T4 lysozyme
journal, November 1987

  • Alber, Tom; Dao-pin, Sun; Wilson, Keith
  • Nature, Vol. 330, Issue 6143
  • DOI: 10.1038/330041a0

Improved prediction of protein side-chain conformations with SCWRL4
journal, December 2009

  • Krivov, Georgii G.; Shapovalov, Maxim V.; Dunbrack, Roland L.
  • Proteins: Structure, Function, and Bioinformatics, Vol. 77, Issue 4
  • DOI: 10.1002/prot.22488

Subsemble: an ensemble method for combining subset-specific algorithm fits
journal, November 2013


Predicting the Effect of Mutations on Protein-Protein Binding Interactions through Structure-Based Interface Profiles
journal, October 2015


Stacked generalization
journal, January 1992


Dissection of helix capping in T4 lysozyme by structural and thermodynamic analysis of six amino acid substitutions at Thr 59
journal, April 1992

  • Bell, Jeffrey A.; Becktel, Wayne J.; Sauer, Uwe
  • Biochemistry, Vol. 31, Issue 14
  • DOI: 10.1021/bi00129a006

Scalable molecular dynamics with NAMD
journal, January 2005

  • Phillips, James C.; Braun, Rosemary; Wang, Wei
  • Journal of Computational Chemistry, Vol. 26, Issue 16, p. 1781-1802
  • DOI: 10.1002/jcc.20289

Prediction of protein stability changes for single-site mutations using support vector machines
journal, December 2005

  • Cheng, Jianlin; Randall, Arlo; Baldi, Pierre
  • Proteins: Structure, Function, and Bioinformatics, Vol. 62, Issue 4
  • DOI: 10.1002/prot.20810

Response of a protein structure to cavity-creating mutations and its relation to the hydrophobic effect
journal, January 1992


Prediction of the stability of protein mutants based on structural environment-dependent amino acid substitution and propensity tables
journal, January 1997

  • Topham, C. M.; Srinivasan, N.; Blundell, T. L.
  • Protein Engineering Design and Selection, Vol. 10, Issue 1
  • DOI: 10.1093/protein/10.1.7

Tertiary templates for proteins
journal, February 1987


Structure Based Thermostability Prediction Models for Protein Single Point Mutations with Machine Learning Tools
journal, September 2015


Combining Estimates in Regression and Classification
journal, December 1996


ProTherm and ProNIT: thermodynamic databases for proteins and protein-nucleic acid interactions
journal, January 2006


Contributions of left-handed helical residues to the structure and stability of bacteriophage T4 lysozyme
journal, November 1989


Contributions of all 20 amino acids at site 96 to the stability and structure of T4 lysozyme
journal, May 2009

  • Mooers, Blaine H. M.; Baase, Walter A.; Wray, Jonathan W.
  • Protein Science, Vol. 18, Issue 5
  • DOI: 10.1002/pro.94

LIBSVM: A library for support vector machines
journal, April 2011

  • Chang, Chih-Chung; Lin, Chih-Jen
  • ACM Transactions on Intelligent Systems and Technology, Vol. 2, Issue 3
  • DOI: 10.1145/1961189.1961199

Contribution of the hydrophobic effect to protein stability: analysis based on simulations of the Ile-96----Ala mutation in barnase.
journal, December 1991

  • Prevost, M.; Wodak, S. J.; Tidor, B.
  • Proceedings of the National Academy of Sciences, Vol. 88, Issue 23
  • DOI: 10.1073/pnas.88.23.10880

Stacked regressions
journal, July 1996


Conformation of amino acid side-chains in proteins
journal, November 1978


Super Learner
journal, January 2007

  • van der Laan, Mark J.; Polley, Eric C.; Hubbard, Alan E.
  • Statistical Applications in Genetics and Molecular Biology, Vol. 6, Issue 1
  • DOI: 10.2202/1544-6115.1309

Protein flexibility predictions using graph theory
journal, January 2001

  • Jacobs, Donald J.; Rader, A. J.; Kuhn, Leslie A.
  • Proteins: Structure, Function, and Genetics, Vol. 44, Issue 2
  • DOI: 10.1002/prot.1081

Accurate prediction of the stability and activity effects of site-directed mutagenesis on a protein core
journal, August 1991

  • Lee, Christopher; Levitt, Michael
  • Nature, Vol. 352, Issue 6334
  • DOI: 10.1038/352448a0

SDM--a server for predicting effects of mutations on protein stability and malfunction
journal, May 2011

  • Worth, C. L.; Preissner, R.; Blundell, T. L.
  • Nucleic Acids Research, Vol. 39, Issue suppl
  • DOI: 10.1093/nar/gkr363

KINARI-Web: a server for protein rigidity analysis
journal, June 2011

  • Fox, N.; Jagodzinski, F.; Li, Y.
  • Nucleic Acids Research, Vol. 39, Issue suppl
  • DOI: 10.1093/nar/gkr482

Conformational analysis of the backbone-dependent rotamer preferences of protein sidechains
journal, May 1994

  • Dunbrack, Roland L.; Karplus, Martin
  • Nature Structural & Molecular Biology, Vol. 1, Issue 5
  • DOI: 10.1038/nsb0594-334

Exploiting the Link between Protein Rigidity and Thermostability for Data-Driven Protein Engineering
journal, October 2008


Random Forests
journal, January 2001


HPSLPred: An Ensemble Multi-Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source
journal, September 2017


PROTS-RF: A Robust Model for Predicting Mutation-Induced Protein Stability Changes
journal, October 2012


Exploiting the Link between Protein Rigidity and Thermostability for Data-Driven Protein Engineering
journal, October 2008


HPSLPred: An Ensemble Multi-Label Classifier for Human Protein Subcellular Location Prediction with Imbalanced Source
journal, September 2017


Protein flexibility predictions using graph theory
journal, January 2001

  • Jacobs, Donald J.; Rader, A. J.; Kuhn, Leslie A.
  • Proteins: Structure, Function, and Genetics, Vol. 44, Issue 2
  • DOI: 10.1002/prot.1081

Prediction of protein stability changes for single-site mutations using support vector machines
journal, December 2005

  • Cheng, Jianlin; Randall, Arlo; Baldi, Pierre
  • Proteins: Structure, Function, and Bioinformatics, Vol. 62, Issue 4
  • DOI: 10.1002/prot.20810

Improved prediction of protein side-chain conformations with SCWRL4
journal, December 2009

  • Krivov, Georgii G.; Shapovalov, Maxim V.; Dunbrack, Roland L.
  • Proteins: Structure, Function, and Bioinformatics, Vol. 77, Issue 4
  • DOI: 10.1002/prot.22488

Conformation of amino acid side-chains in proteins
journal, November 1978


Contributions of left-handed helical residues to the structure and stability of bacteriophage T4 lysozyme
journal, November 1989


Structural basis of Fabry disease
journal, September 2002


Dissection of helix capping in T4 lysozyme by structural and thermodynamic analysis of six amino acid substitutions at Thr 59
journal, April 1992

  • Bell, Jeffrey A.; Becktel, Wayne J.; Sauer, Uwe
  • Biochemistry, Vol. 31, Issue 14
  • DOI: 10.1021/bi00129a006

Contributions of hydrogen bonds of Thr 157 to the thermodynamic stability of phage T4 lysozyme
journal, November 1987

  • Alber, Tom; Dao-pin, Sun; Wilson, Keith
  • Nature, Vol. 330, Issue 6143
  • DOI: 10.1038/330041a0

Accurate prediction of the stability and activity effects of site-directed mutagenesis on a protein core
journal, August 1991

  • Lee, Christopher; Levitt, Michael
  • Nature, Vol. 352, Issue 6334
  • DOI: 10.1038/352448a0

Combining Estimates in Regression and Classification
journal, December 1996


Subsemble: an ensemble method for combining subset-specific algorithm fits
journal, November 2013


ProTherm and ProNIT: thermodynamic databases for proteins and protein-nucleic acid interactions
journal, January 2006


SDM--a server for predicting effects of mutations on protein stability and malfunction
journal, May 2011

  • Worth, C. L.; Preissner, R.; Blundell, T. L.
  • Nucleic Acids Research, Vol. 39, Issue suppl
  • DOI: 10.1093/nar/gkr363

KINARI-Web: a server for protein rigidity analysis
journal, June 2011

  • Fox, N.; Jagodzinski, F.; Li, Y.
  • Nucleic Acids Research, Vol. 39, Issue suppl
  • DOI: 10.1093/nar/gkr482

Prediction of the stability of protein mutants based on structural environment-dependent amino acid substitution and propensity tables
journal, January 1997

  • Topham, C. M.; Srinivasan, N.; Blundell, T. L.
  • Protein Engineering Design and Selection, Vol. 10, Issue 1
  • DOI: 10.1093/protein/10.1.7

Fast Prediction of Protein Methylation Sites Using a Sequence-Based Feature Selection Technique
journal, July 2019

  • Wei, Leyi; Xing, Pengwei; Shi, Gaotao
  • IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 16, Issue 4
  • DOI: 10.1109/tcbb.2017.2670558

PhosPred-RF: A Novel Sequence-Based Predictor for Phosphorylation Sites Using Sequential Information Only
journal, June 2017

  • Wei, Leyi; Xing, Pengwei; Tang, Jijun
  • IEEE Transactions on NanoBioscience, Vol. 16, Issue 4
  • DOI: 10.1109/tnb.2017.2661756

Using Rigidity Analysis to Probe Mutation-Induced Structural Changes in Proteins
journal, June 2012

  • Jagodzinski, Filip; Hardy, Jeanne; Streinu, Ileana
  • Journal of Bioinformatics and Computational Biology, Vol. 10, Issue 03
  • DOI: 10.1142/s0219720012420103

LIBSVM: A library for support vector machines
journal, April 2011

  • Chang, Chih-Chung; Lin, Chih-Jen
  • ACM Transactions on Intelligent Systems and Technology, Vol. 2, Issue 3
  • DOI: 10.1145/1961189.1961199

ProMuteHT
conference, August 2017

  • Andersson, Erik; Jagodzinski, Filip
  • Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics
  • DOI: 10.1145/3107411.3116251

A conservation and rigidity based method for detecting critical protein residues
journal, January 2013

  • Akbal-Delibas, Bahar; Jagodzinski, Filip; Haspel, Nurit
  • BMC Structural Biology, Vol. 13, Issue Suppl 1
  • DOI: 10.1186/1472-6807-13-s1-s6

Predicting the Effect of Mutations on Protein-Protein Binding Interactions through Structure-Based Interface Profiles
journal, October 2015


PROTS-RF: A Robust Model for Predicting Mutation-Induced Protein Stability Changes
journal, October 2012


Super Learner
journal, January 2007

  • van der Laan, Mark J.; Polley, Eric C.; Hubbard, Alan E.
  • Statistical Applications in Genetics and Molecular Biology, Vol. 6, Issue 1
  • DOI: 10.2202/1544-6115.1309

Works referencing / citing this record:

Robust Prediction of Single and Multiple Point Protein Mutations Stability Changes
journal, December 2019

  • Álvarez-Machancoses, Óscar; De Andrés-Galiana, Enrique J.; Fernández-Martínez, Juan Luis
  • Biomolecules, Vol. 10, Issue 1
  • DOI: 10.3390/biom10010067

Amino-Acid Network Clique Analysis of Protein Mutation Non-Additive Effects: A Case Study of Lysozme
journal, May 2018

  • Ming, Dengming; Chen, Rui; Huang, He
  • International Journal of Molecular Sciences, Vol. 19, Issue 5
  • DOI: 10.3390/ijms19051427

Evaluating Protein Engineering Thermostability Prediction Tools Using an Independently Generated Dataset
journal, March 2020


Amino-Acid Network Clique Analysis of Protein Mutation Non-Additive Effects: A Case Study of Lysozme
journal, May 2018

  • Ming, Dengming; Chen, Rui; Huang, He
  • International Journal of Molecular Sciences, Vol. 19, Issue 5
  • DOI: 10.3390/ijms19051427

PETRA: Drug Engineering via Rigidity Analysis
journal, March 2020