Predicting contact map using Radial Basis Function Neural Network with Conformational Energy Function

Peng Chen, De Shuang Huang, Xing Ming Zhao, Xueling Li

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Contact map, which is important to understand and reconstruct protein's three-dimensional (3D) structure, may be helpful to solve the protein's 3D structure. This paper presents a novel approach to predict the contact map using Radial Basis Function Neural Network (RBFNN) optimised by Conformational Energy Function (CEF) based on chemico-physical knowledge of amino acids. Finally, the results are trimmed by Short-Range Contact Function (SRCF). Consequently, it can be found that our proposed method is better than the existing methods such as PROFcon and the PE-based method. Particularly, this method can accurately predict 35% of contacts at a distance cutoff of 8 Å.

Original languageEnglish (US)
Pages (from-to)123-136
Number of pages14
JournalInternational Journal of Bioinformatics Research and Applications
Volume4
Issue number2
DOIs
StatePublished - May 2008
Externally publishedYes

Fingerprint

Neural networks
Proteins
Amino acids
Amino Acids

Keywords

  • Bioinformatics
  • CEF
  • Conformational energy function
  • Contact map
  • PCA
  • Principal component analysis
  • Radial basis function neural network
  • RBFNN
  • Short-range contact function
  • SRCF

ASJC Scopus subject areas

  • Health Informatics
  • Health Information Management
  • Biomedical Engineering
  • Clinical Biochemistry

Cite this

Predicting contact map using Radial Basis Function Neural Network with Conformational Energy Function. / Chen, Peng; Huang, De Shuang; Zhao, Xing Ming; Li, Xueling.

In: International Journal of Bioinformatics Research and Applications, Vol. 4, No. 2, 05.2008, p. 123-136.

Research output: Contribution to journalArticle

@article{69f9a7d97b774f4ca77a6d6b95557fb7,
title = "Predicting contact map using Radial Basis Function Neural Network with Conformational Energy Function",
abstract = "Contact map, which is important to understand and reconstruct protein's three-dimensional (3D) structure, may be helpful to solve the protein's 3D structure. This paper presents a novel approach to predict the contact map using Radial Basis Function Neural Network (RBFNN) optimised by Conformational Energy Function (CEF) based on chemico-physical knowledge of amino acids. Finally, the results are trimmed by Short-Range Contact Function (SRCF). Consequently, it can be found that our proposed method is better than the existing methods such as PROFcon and the PE-based method. Particularly, this method can accurately predict 35{\%} of contacts at a distance cutoff of 8 {\AA}.",
keywords = "Bioinformatics, CEF, Conformational energy function, Contact map, PCA, Principal component analysis, Radial basis function neural network, RBFNN, Short-range contact function, SRCF",
author = "Peng Chen and Huang, {De Shuang} and Zhao, {Xing Ming} and Xueling Li",
year = "2008",
month = "5",
doi = "10.1504/IJBRA.2008.018340",
language = "English (US)",
volume = "4",
pages = "123--136",
journal = "International Journal of Bioinformatics Research and Applications",
issn = "1744-5485",
publisher = "Inderscience Enterprises Ltd",
number = "2",

}

TY - JOUR

T1 - Predicting contact map using Radial Basis Function Neural Network with Conformational Energy Function

AU - Chen, Peng

AU - Huang, De Shuang

AU - Zhao, Xing Ming

AU - Li, Xueling

PY - 2008/5

Y1 - 2008/5

N2 - Contact map, which is important to understand and reconstruct protein's three-dimensional (3D) structure, may be helpful to solve the protein's 3D structure. This paper presents a novel approach to predict the contact map using Radial Basis Function Neural Network (RBFNN) optimised by Conformational Energy Function (CEF) based on chemico-physical knowledge of amino acids. Finally, the results are trimmed by Short-Range Contact Function (SRCF). Consequently, it can be found that our proposed method is better than the existing methods such as PROFcon and the PE-based method. Particularly, this method can accurately predict 35% of contacts at a distance cutoff of 8 Å.

AB - Contact map, which is important to understand and reconstruct protein's three-dimensional (3D) structure, may be helpful to solve the protein's 3D structure. This paper presents a novel approach to predict the contact map using Radial Basis Function Neural Network (RBFNN) optimised by Conformational Energy Function (CEF) based on chemico-physical knowledge of amino acids. Finally, the results are trimmed by Short-Range Contact Function (SRCF). Consequently, it can be found that our proposed method is better than the existing methods such as PROFcon and the PE-based method. Particularly, this method can accurately predict 35% of contacts at a distance cutoff of 8 Å.

KW - Bioinformatics

KW - CEF

KW - Conformational energy function

KW - Contact map

KW - PCA

KW - Principal component analysis

KW - Radial basis function neural network

KW - RBFNN

KW - Short-range contact function

KW - SRCF

UR - http://www.scopus.com/inward/record.url?scp=43749113791&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43749113791&partnerID=8YFLogxK

U2 - 10.1504/IJBRA.2008.018340

DO - 10.1504/IJBRA.2008.018340

M3 - Article

C2 - 18490258

AN - SCOPUS:43749113791

VL - 4

SP - 123

EP - 136

JO - International Journal of Bioinformatics Research and Applications

JF - International Journal of Bioinformatics Research and Applications

SN - 1744-5485

IS - 2

ER -