A novel EDAs based method for HP model rotein folding

Benhui Chen, Long Li, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

The protein structure prediction (PSP) problem is one of the most important problems in computational biology. This paper proposes a novel Estimation of Distribution Algorithms (EDAs) based method to solve the PSP problem on HP model. Firstly, a composite fitness function containing the information of folding structure core formation is introduced to replace the traditional fitness function of HP model. It can help to select more optimum individuals for probabilistic model of EDAs algorithm. And a set of guided operators are used to increase the diversity of population and the likelihood of escaping from local optima. Secondly, an improved backtracking repairing algorithm is proposed to repair invalid individuals sampled by the probabilistic model of EDAs for the long sequence protein instances. A detection procedure of feasibility is added to avoid entering invalid closed areas when selecting directions for the residues. Thus, it can significant reduce the number of backtracking operation and the computational cost for long se quence protein. Experimental results demonstrate that the proposed method outperform the basic EDAs method. At the same time, it is very competitive with the other existing algorithms for the PSP problem on lattice HP models.

Original languageEnglish
Title of host publication2009 IEEE Congress on Evolutionary Computation, CEC 2009
Pages309-315
Number of pages7
DOIs
Publication statusPublished - 2009
Event2009 IEEE Congress on Evolutionary Computation, CEC 2009 - Trondheim
Duration: 2009 May 182009 May 21

Other

Other2009 IEEE Congress on Evolutionary Computation, CEC 2009
CityTrondheim
Period09/5/1809/5/21

Fingerprint

Folding
Protein Structure Prediction
Proteins
Backtracking
Fitness Function
Probabilistic Model
Model
Composite function
Computational Biology
Protein Sequence
Set theory
Repair
Mathematical operators
Computational Cost
Likelihood
Protein
Closed
Composite materials
Experimental Results
Operator

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Chen, B., Li, L., & Furuzuki, T. (2009). A novel EDAs based method for HP model rotein folding. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009 (pp. 309-315). [4982963] https://doi.org/10.1109/CEC.2009.4982963

A novel EDAs based method for HP model rotein folding. / Chen, Benhui; Li, Long; Furuzuki, Takayuki.

2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 309-315 4982963.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, B, Li, L & Furuzuki, T 2009, A novel EDAs based method for HP model rotein folding. in 2009 IEEE Congress on Evolutionary Computation, CEC 2009., 4982963, pp. 309-315, 2009 IEEE Congress on Evolutionary Computation, CEC 2009, Trondheim, 09/5/18. https://doi.org/10.1109/CEC.2009.4982963
Chen B, Li L, Furuzuki T. A novel EDAs based method for HP model rotein folding. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 309-315. 4982963 https://doi.org/10.1109/CEC.2009.4982963
Chen, Benhui ; Li, Long ; Furuzuki, Takayuki. / A novel EDAs based method for HP model rotein folding. 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. pp. 309-315
@inproceedings{7d12c1d46d0040fa93048e000109f9cf,
title = "A novel EDAs based method for HP model rotein folding",
abstract = "The protein structure prediction (PSP) problem is one of the most important problems in computational biology. This paper proposes a novel Estimation of Distribution Algorithms (EDAs) based method to solve the PSP problem on HP model. Firstly, a composite fitness function containing the information of folding structure core formation is introduced to replace the traditional fitness function of HP model. It can help to select more optimum individuals for probabilistic model of EDAs algorithm. And a set of guided operators are used to increase the diversity of population and the likelihood of escaping from local optima. Secondly, an improved backtracking repairing algorithm is proposed to repair invalid individuals sampled by the probabilistic model of EDAs for the long sequence protein instances. A detection procedure of feasibility is added to avoid entering invalid closed areas when selecting directions for the residues. Thus, it can significant reduce the number of backtracking operation and the computational cost for long se quence protein. Experimental results demonstrate that the proposed method outperform the basic EDAs method. At the same time, it is very competitive with the other existing algorithms for the PSP problem on lattice HP models.",
author = "Benhui Chen and Long Li and Takayuki Furuzuki",
year = "2009",
doi = "10.1109/CEC.2009.4982963",
language = "English",
isbn = "9781424429592",
pages = "309--315",
booktitle = "2009 IEEE Congress on Evolutionary Computation, CEC 2009",

}

TY - GEN

T1 - A novel EDAs based method for HP model rotein folding

AU - Chen, Benhui

AU - Li, Long

AU - Furuzuki, Takayuki

PY - 2009

Y1 - 2009

N2 - The protein structure prediction (PSP) problem is one of the most important problems in computational biology. This paper proposes a novel Estimation of Distribution Algorithms (EDAs) based method to solve the PSP problem on HP model. Firstly, a composite fitness function containing the information of folding structure core formation is introduced to replace the traditional fitness function of HP model. It can help to select more optimum individuals for probabilistic model of EDAs algorithm. And a set of guided operators are used to increase the diversity of population and the likelihood of escaping from local optima. Secondly, an improved backtracking repairing algorithm is proposed to repair invalid individuals sampled by the probabilistic model of EDAs for the long sequence protein instances. A detection procedure of feasibility is added to avoid entering invalid closed areas when selecting directions for the residues. Thus, it can significant reduce the number of backtracking operation and the computational cost for long se quence protein. Experimental results demonstrate that the proposed method outperform the basic EDAs method. At the same time, it is very competitive with the other existing algorithms for the PSP problem on lattice HP models.

AB - The protein structure prediction (PSP) problem is one of the most important problems in computational biology. This paper proposes a novel Estimation of Distribution Algorithms (EDAs) based method to solve the PSP problem on HP model. Firstly, a composite fitness function containing the information of folding structure core formation is introduced to replace the traditional fitness function of HP model. It can help to select more optimum individuals for probabilistic model of EDAs algorithm. And a set of guided operators are used to increase the diversity of population and the likelihood of escaping from local optima. Secondly, an improved backtracking repairing algorithm is proposed to repair invalid individuals sampled by the probabilistic model of EDAs for the long sequence protein instances. A detection procedure of feasibility is added to avoid entering invalid closed areas when selecting directions for the residues. Thus, it can significant reduce the number of backtracking operation and the computational cost for long se quence protein. Experimental results demonstrate that the proposed method outperform the basic EDAs method. At the same time, it is very competitive with the other existing algorithms for the PSP problem on lattice HP models.

UR - http://www.scopus.com/inward/record.url?scp=70450137092&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450137092&partnerID=8YFLogxK

U2 - 10.1109/CEC.2009.4982963

DO - 10.1109/CEC.2009.4982963

M3 - Conference contribution

SN - 9781424429592

SP - 309

EP - 315

BT - 2009 IEEE Congress on Evolutionary Computation, CEC 2009

ER -