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

Title: Adaptive local learning in sampling based motion planning for protein folding

Abstract

Background: Simulating protein folding motions is an important problem in computational biology. Motion planning algorithms, such as Probabilistic Roadmap Methods, have been successful in modeling the folding landscape. Probabilistic Roadmap Methods and variants contain several phases (i.e., sampling, connection, and path extraction). Most of the time is spent in the connection phase and selecting which variant to employ is a difficult task. Global machine learning has been applied to the connection phase but is inefficient in situations with varying topology, such as those typical of folding landscapes. Results: We develop a local learning algorithm that exploits the past performance of methods within the neighborhood of the current connection attempts as a basis for learning. It is sensitive not only to different types of landscapes but also to differing regions in the landscape itself, removing the need to explicitly partition the landscape. We perform experiments on 23 proteins of varying secondary structure makeup with 52–114 residues. We compare the success rate when using our methods and other methods. We demonstrate a clear need for learning (i.e., only learning methods were able to validate against all available experimental data) and show that local learning is superior to global learning producing, in manymore » cases, significantly higher quality results than the other methods. Conclusions: We present an algorithm that uses local learning to select appropriate connection methods in the context of roadmap construction for protein folding. Our method removes the burden of deciding which method to use, leverages the strengths of the individual input methods, and it is extendable to include other future connection methods.« less

Authors:
 [1];  [1];  [1]
  1. Texas A&M Univ., College Station, TX (United States). Dept. of Computer Science and Engineering
Publication Date:
Research Org.:
Lawrence Berkeley National Lab (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC); National Science Foundation (NSF); National Institutes of Health (NIH) National Cancer Institute (NCI)
OSTI Identifier:
1626879
Grant/Contract Number:  
AC02-05CH11231; CNS-0551685; CCF-0833199; CCF-1423111; CCF-0830753; IIS-0916053; IIS-0917266; EFRI-1240483; RI-1217991; R25 CA090301-11
Resource Type:
Accepted Manuscript
Journal Name:
BMC Systems Biology
Additional Journal Information:
Journal Volume: 10; Journal Issue: S2; Journal ID: ISSN 1752-0509
Publisher:
BioMed Central
Country of Publication:
United States
Language:
English
Subject:
Mathematical & Computational Biology

Citation Formats

Ekenna, Chinwe, Thomas, Shawna, and Amato, Nancy M. Adaptive local learning in sampling based motion planning for protein folding. United States: N. p., 2016. Web. doi:10.1186/s12918-016-0297-9.
Ekenna, Chinwe, Thomas, Shawna, & Amato, Nancy M. Adaptive local learning in sampling based motion planning for protein folding. United States. https://doi.org/10.1186/s12918-016-0297-9
Ekenna, Chinwe, Thomas, Shawna, and Amato, Nancy M. Mon . "Adaptive local learning in sampling based motion planning for protein folding". United States. https://doi.org/10.1186/s12918-016-0297-9. https://www.osti.gov/servlets/purl/1626879.
@article{osti_1626879,
title = {Adaptive local learning in sampling based motion planning for protein folding},
author = {Ekenna, Chinwe and Thomas, Shawna and Amato, Nancy M.},
abstractNote = {Background: Simulating protein folding motions is an important problem in computational biology. Motion planning algorithms, such as Probabilistic Roadmap Methods, have been successful in modeling the folding landscape. Probabilistic Roadmap Methods and variants contain several phases (i.e., sampling, connection, and path extraction). Most of the time is spent in the connection phase and selecting which variant to employ is a difficult task. Global machine learning has been applied to the connection phase but is inefficient in situations with varying topology, such as those typical of folding landscapes. Results: We develop a local learning algorithm that exploits the past performance of methods within the neighborhood of the current connection attempts as a basis for learning. It is sensitive not only to different types of landscapes but also to differing regions in the landscape itself, removing the need to explicitly partition the landscape. We perform experiments on 23 proteins of varying secondary structure makeup with 52–114 residues. We compare the success rate when using our methods and other methods. We demonstrate a clear need for learning (i.e., only learning methods were able to validate against all available experimental data) and show that local learning is superior to global learning producing, in many cases, significantly higher quality results than the other methods. Conclusions: We present an algorithm that uses local learning to select appropriate connection methods in the context of roadmap construction for protein folding. Our method removes the burden of deciding which method to use, leverages the strengths of the individual input methods, and it is extendable to include other future connection methods.},
doi = {10.1186/s12918-016-0297-9},
journal = {BMC Systems Biology},
number = S2,
volume = 10,
place = {United States},
year = {Mon Aug 01 00:00:00 EDT 2016},
month = {Mon Aug 01 00:00:00 EDT 2016}
}

Works referenced in this record:

Protein Misfolding, Functional Amyloid, and Human Disease
journal, June 2006


Folding protein α-carbon chains into compact forms by monte carlo methods
journal, November 1992


A simplified representation of protein conformations for rapid simulation of protein folding
journal, June 1976


A statistical mechanical model for  -hairpin kinetics
journal, May 1998

  • Munoz, V.; Henry, E. R.; Hofrichter, J.
  • Proceedings of the National Academy of Sciences, Vol. 95, Issue 11
  • DOI: 10.1073/pnas.95.11.5872

Spin glasses and the statistical mechanics of protein folding.
journal, November 1987

  • Bryngelson, J. D.; Wolynes, P. G.
  • Proceedings of the National Academy of Sciences, Vol. 84, Issue 21
  • DOI: 10.1073/pnas.84.21.7524

Using Motion Planning to Study Protein Folding Pathways
journal, April 2002


Stochastic Roadmap Simulation: An Efficient Representation and Algorithm for Analyzing Molecular Motion
journal, June 2003

  • Apaydin, Mehmet Serkan; Brutlag, Douglas L.; Guestrin, Carlos
  • Journal of Computational Biology, Vol. 10, Issue 3-4
  • DOI: 10.1089/10665270360688011

Geometric algorithms for the conformational analysis of long protein loops: Conformational Analysis of Long Protein Loops
journal, March 2004

  • Cortés, J.; Siméon, T.; Remaud-Siméon, M.
  • Journal of Computational Chemistry, Vol. 25, Issue 7
  • DOI: 10.1002/jcc.20021

Improved roadmap connection via local learning for sampling based planners
conference, September 2015

  • Ekenna, Chinwe; Uwacu, Diane; Thomas, Shawna
  • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • DOI: 10.1109/IROS.2015.7353825

Prediction of protein secondary structure from circular dichroism using theoretically derived spectra
journal, November 2011

  • Louis-Jeune, Caroline; Andrade-Navarro, Miguel A.; Perez-Iratxeta, Carol
  • Proteins: Structure, Function, and Bioinformatics, Vol. 80, Issue 2
  • DOI: 10.1002/prot.23188

Fluorescence as a method to reveal structures and membrane-interactions of amyloidogenic proteins
journal, August 2007

  • Munishkina, Larissa A.; Fink, Anthony L.
  • Biochimica et Biophysica Acta (BBA) - Biomembranes, Vol. 1768, Issue 8
  • DOI: 10.1016/j.bbamem.2007.03.015

Protein backbone and sidechain torsion angles predicted from NMR chemical shifts using artificial neural networks
journal, June 2013


x Ray crystallography
journal, February 2000


Minimalist Protein Model as a Diagnostic Tool for Misfolding and Aggregation
journal, October 2006


Probabilistic roadmaps for path planning in high-dimensional configuration spaces
journal, January 1996

  • Kavraki, L. E.; Svestka, P.; Latombe, J. -C.
  • IEEE Transactions on Robotics and Automation, Vol. 12, Issue 4
  • DOI: 10.1109/70.508439

Annual acknowledgement of manuscript reviewers
journal, January 2013


Simulating Protein Motions with Rigidity Analysis
journal, July 2007

  • Thomas, Shawna; Tang, Xinyu; Tapia, Lydia
  • Journal of Computational Biology, Vol. 14, Issue 6
  • DOI: 10.1089/cmb.2007.R019

Local randomization in neighbor selection improves PRM roadmap quality
conference, October 2012

  • McMahon, Troy; Jacobs, Sam; Boyd, Bryan
  • 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012)
  • DOI: 10.1109/IROS.2012.6386061

Hydrogen exchange mass spectrometry for the analysis of protein dynamics
journal, January 2005

  • Wales, Thomas E.; Engen, John R.
  • Mass Spectrometry Reviews, Vol. 25, Issue 1
  • DOI: 10.1002/mas.20064

The hydrogen exchange core and protein folding
journal, January 1999


Satisfying general proximity / similarity queries with metric trees
journal, November 1991


An optimal algorithm for approximate nearest neighbor searching fixed dimensions
journal, November 1998

  • Arya, Sunil; Mount, David M.; Netanyahu, Nathan S.
  • Journal of the ACM, Vol. 45, Issue 6
  • DOI: 10.1145/293347.293348

Generic rigidity in three-dimensional bond-bending networks
journal, August 1998


Improving Protein Fold Recognition by Deep Learning Networks
journal, December 2015

  • Jo, Taeho; Hou, Jie; Eickholt, Jesse
  • Scientific Reports, Vol. 5, Issue 1
  • DOI: 10.1038/srep17573

Folding rate prediction based on neural network model
journal, March 2003


A self-learning algorithm for biased molecular dynamics
journal, September 2010

  • Tribello, Gareth A.; Ceriotti, Michele; Parrinello, Michele
  • Proceedings of the National Academy of Sciences, Vol. 107, Issue 41
  • DOI: 10.1073/pnas.1011511107

The Nonstochastic Multiarmed Bandit Problem
journal, January 2002

  • Auer, Peter; Cesa-Bianchi, Nicolò; Freund, Yoav
  • SIAM Journal on Computing, Vol. 32, Issue 1
  • DOI: 10.1137/S0097539701398375

Pure Exploration in Multi-armed Bandits Problems
book, January 2009

  • Bubeck, Sébastien; Munos, Rémi; Stoltz, Gilles
  • Algorithmic Learning Theory. Lecture Notes in Computer Science
  • DOI: 10.1007/978-3-642-04414-4_7

Submillisecond kinetics of protein folding
journal, February 1997

  • Eaton, William A.; Muñoz, Victor; Thompson, Peggy A.
  • Current Opinion in Structural Biology, Vol. 7, Issue 1
  • DOI: 10.1016/S0959-440X(97)80003-6

The Protein Data Bank
journal, January 2000


Fast folding of a prototypic polypeptide: The immunoglobulin binding domain of streptococcal protein G
journal, November 1994

  • Kuszewski, John; Clore, G. Marius; Gronenborn, Angela M.
  • Protein Science, Vol. 3, Issue 11
  • DOI: 10.1002/pro.5560031106

Computer-based redesign of a protein folding pathway
journal, July 2001

  • Nauli, Sehat; Kuhlman, Brian; Baker, David
  • Nature Structural Biology, Vol. 8, Issue 7, p. 602-605
  • DOI: 10.1038/89638

Different folding transition states may result in the same native structure
journal, October 1996

  • Viguera, Ana Rosa; Serrano, Luis; Wilmanns, Matthias
  • Nature Structural & Molecular Biology, Vol. 3, Issue 10
  • DOI: 10.1038/nsb1096-874

Important role of hydrogen bonds in the structurally polarized transition state for folding of the src SH3 domain
journal, August 1998

  • Grantcharova, Viara P.; Riddle, David S.; Santiago, Jed V.
  • Nature Structural & Molecular Biology, Vol. 5, Issue 8
  • DOI: 10.1038/1412

Structure of the transition state in the folding process of human procarboxypeptidase A2 activation domain
journal, November 1998

  • Villegas, Virtudes; Martı́nez, Jose C.; Avilés, Francesc X.
  • Journal of Molecular Biology, Vol. 283, Issue 5
  • DOI: 10.1006/jmbi.1998.2158

Formation of hydrogen bonds precedes the rate-limiting formation of persistent structure in the folding of ACBP
journal, September 2000

  • Teilum, Kaare; Kragelund, Birthe B.; Knudsen, Jens
  • Journal of Molecular Biology, Vol. 301, Issue 5
  • DOI: 10.1006/jmbi.2000.4003

The folding of an enzyme
journal, April 1992

  • Matouschek, Andreas; Serrano, Luis; Meiering, Elizabeth M.
  • Journal of Molecular Biology, Vol. 224, Issue 3
  • DOI: 10.1016/0022-2836(92)90565-2

Fast folding of a prototypic polypeptide: The immunoglobulin binding domain of streptococcal protein G
journal, November 1994

  • Kuszewski, John; Clore, G. Marius; Gronenborn, Angela M.
  • Protein Science, Vol. 3, Issue 11
  • DOI: 10.1002/pro.5560031106

Prediction of protein secondary structure from circular dichroism using theoretically derived spectra
journal, September 2012

  • Louis-Jeune, Caroline; Andrade-Navarro, Miguel A.; Perez-Iratxeta, Carol
  • Proteins: Structure, Function, and Bioinformatics, Vol. 80, Issue 12
  • DOI: 10.1002/prot.24168

Folding protein α-carbon chains into compact forms by monte carlo methods
journal, November 1992


Formation of hydrogen bonds precedes the rate-limiting formation of persistent structure in the folding of ACBP
journal, September 2000

  • Teilum, Kaare; Kragelund, Birthe B.; Knudsen, Jens
  • Journal of Molecular Biology, Vol. 301, Issue 5
  • DOI: 10.1006/jmbi.2000.4003

Protein backbone and sidechain torsion angles predicted from NMR chemical shifts using artificial neural networks
journal, June 2013


A simplified representation of protein conformations for rapid simulation of protein folding
journal, June 1976


Minimalist Protein Model as a Diagnostic Tool for Misfolding and Aggregation
journal, October 2006


Protein folding by restrained energy minimization and molecular dynamics
journal, November 1983


Important role of hydrogen bonds in the structurally polarized transition state for folding of the src SH3 domain
journal, August 1998

  • Grantcharova, Viara P.; Riddle, David S.; Santiago, Jed V.
  • Nature Structural & Molecular Biology, Vol. 5, Issue 8
  • DOI: 10.1038/1412

Computer-based redesign of a protein folding pathway
journal, July 2001

  • Nauli, Sehat; Kuhlman, Brian; Baker, David
  • Nature Structural Biology, Vol. 8, Issue 7, p. 602-605
  • DOI: 10.1038/89638

Spin glasses and the statistical mechanics of protein folding.
journal, November 1987

  • Bryngelson, J. D.; Wolynes, P. G.
  • Proceedings of the National Academy of Sciences, Vol. 84, Issue 21
  • DOI: 10.1073/pnas.84.21.7524

A statistical mechanical model for  -hairpin kinetics
journal, May 1998

  • Munoz, V.; Henry, E. R.; Hofrichter, J.
  • Proceedings of the National Academy of Sciences, Vol. 95, Issue 11
  • DOI: 10.1073/pnas.95.11.5872

Stochastic Roadmap Simulation: An Efficient Representation and Algorithm for Analyzing Molecular Motion
journal, June 2003

  • Apaydin, Mehmet Serkan; Brutlag, Douglas L.; Guestrin, Carlos
  • Journal of Computational Biology, Vol. 10, Issue 3-4
  • DOI: 10.1089/10665270360688011

Probabilistic roadmaps for path planning in high-dimensional configuration spaces
journal, January 1996

  • Kavraki, L. E.; Svestka, P.; Latombe, J. -C.
  • IEEE Transactions on Robotics and Automation, Vol. 12, Issue 4
  • DOI: 10.1109/70.508439

A robot path planning framework that learns from experience
conference, May 2012

  • Berenson, Dmitry; Abbeel, Pieter; Goldberg, Ken
  • 2012 IEEE International Conference on Robotics and Automation
  • DOI: 10.1109/icra.2012.6224742

Folding@home: Lessons from eight years of volunteer distributed computing
conference, May 2009

  • Beberg, Adam L.; Ensign, Daniel L.; Jayachandran, Guha
  • 2009 IEEE International Symposium on Parallel & Distributed Processing
  • DOI: 10.1109/ipdps.2009.5160922

Improving Motion-Planning Algorithms by Efficient Nearest-Neighbor Searching
journal, February 2007


The hydrogen exchange core and protein folding
journal, January 1999


x Ray crystallography
journal, February 2000


An optimal algorithm for approximate nearest neighbor searching fixed dimensions
journal, November 1998

  • Arya, Sunil; Mount, David M.; Netanyahu, Nathan S.
  • Journal of the ACM, Vol. 45, Issue 6
  • DOI: 10.1145/293347.293348

Using motion planning to study protein folding pathways
conference, January 2001

  • Song, Guang; Amato, Nancy M.
  • Proceedings of the fifth annual international conference on Computational biology - RECOMB '01
  • DOI: 10.1145/369133.369239

Protein Misfolding, Functional Amyloid, and Human Disease
journal, June 2006


New mini- zincin structures provide a minimal scaffold for members of this metallopeptidase superfamily
journal, January 2014

  • Trame, Christine B.; Chang, Yuanyuan; Axelrod, Herbert L.
  • BMC Bioinformatics, Vol. 15, Issue 1
  • DOI: 10.1186/1471-2105-15-1

Annual acknowledgement of manuscript reviewers
journal, March 2016


A self-learning algorithm for biased molecular dynamics
text, January 2010


Works referencing / citing this record:

Predicting the protein half-life in tissue from its cellular properties
journal, July 2017