QBES: Predicting real values of solvent accessibility from sequences by efficient, constrained energy optimization

Zhigang Xu, Chi Zhang, Song Liu, Yaoqi Zhou

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Solvent accessibility, one of the key properties of amino acid residues in proteins, can be used to assist protein structure prediction. Various approaches such as neural network, support vector machines, probability profiles, information theory, Bayesian theory, logistic function, and multiple linear regression have been developed for solvent accessibility prediction. In this article, a much simpler quadratic programming method based on the buriability parameter set of amino acid residues is developed. The new method, called QBES (Quadratic programming and Buriability Energy function for Solvent accessibility prediction), is reasonably accurate for predicting the real value of solvent accessibility. By using a dataset of 30 proteins to optimize three parameters, the average correlation coefficients between the predicted and actual solvent accessibility are about 0.5 for all four independent test sets ranging from 126 to 513 proteins. The method is efficient. It takes only 20 min for a regular PC to obtain results of 30 proteins with an average length of 263 amino acids. Although the proposed method is less accurate than a few more sophisticated methods based on neural network or support vector machines, this is the first attempt to predict solvent accessibility by energy optimization with constraints. Possible improvements and other applications of the method are discussed.

Original languageEnglish (US)
Pages (from-to)961-966
Number of pages6
JournalProteins: Structure, Function and Genetics
Volume63
Issue number4
DOIs
StatePublished - Jun 1 2006

Fingerprint

Quadratic programming
Proteins
Amino Acids
Support vector machines
Information Theory
Neural networks
Information theory
Linear regression
Logistics
Linear Models
Support Vector Machine
Datasets

Keywords

  • Amino acid residues
  • Proteins
  • Solvent accessibility

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology

Cite this

QBES : Predicting real values of solvent accessibility from sequences by efficient, constrained energy optimization. / Xu, Zhigang; Zhang, Chi; Liu, Song; Zhou, Yaoqi.

In: Proteins: Structure, Function and Genetics, Vol. 63, No. 4, 01.06.2006, p. 961-966.

Research output: Contribution to journalArticle

@article{9d871533d2f54c459b0825f03bf76c49,
title = "QBES: Predicting real values of solvent accessibility from sequences by efficient, constrained energy optimization",
abstract = "Solvent accessibility, one of the key properties of amino acid residues in proteins, can be used to assist protein structure prediction. Various approaches such as neural network, support vector machines, probability profiles, information theory, Bayesian theory, logistic function, and multiple linear regression have been developed for solvent accessibility prediction. In this article, a much simpler quadratic programming method based on the buriability parameter set of amino acid residues is developed. The new method, called QBES (Quadratic programming and Buriability Energy function for Solvent accessibility prediction), is reasonably accurate for predicting the real value of solvent accessibility. By using a dataset of 30 proteins to optimize three parameters, the average correlation coefficients between the predicted and actual solvent accessibility are about 0.5 for all four independent test sets ranging from 126 to 513 proteins. The method is efficient. It takes only 20 min for a regular PC to obtain results of 30 proteins with an average length of 263 amino acids. Although the proposed method is less accurate than a few more sophisticated methods based on neural network or support vector machines, this is the first attempt to predict solvent accessibility by energy optimization with constraints. Possible improvements and other applications of the method are discussed.",
keywords = "Amino acid residues, Proteins, Solvent accessibility",
author = "Zhigang Xu and Chi Zhang and Song Liu and Yaoqi Zhou",
year = "2006",
month = "6",
day = "1",
doi = "10.1002/prot.20934",
language = "English (US)",
volume = "63",
pages = "961--966",
journal = "Proteins: Structure, Function and Bioinformatics",
issn = "0887-3585",
publisher = "Wiley-Liss Inc.",
number = "4",

}

TY - JOUR

T1 - QBES

T2 - Predicting real values of solvent accessibility from sequences by efficient, constrained energy optimization

AU - Xu, Zhigang

AU - Zhang, Chi

AU - Liu, Song

AU - Zhou, Yaoqi

PY - 2006/6/1

Y1 - 2006/6/1

N2 - Solvent accessibility, one of the key properties of amino acid residues in proteins, can be used to assist protein structure prediction. Various approaches such as neural network, support vector machines, probability profiles, information theory, Bayesian theory, logistic function, and multiple linear regression have been developed for solvent accessibility prediction. In this article, a much simpler quadratic programming method based on the buriability parameter set of amino acid residues is developed. The new method, called QBES (Quadratic programming and Buriability Energy function for Solvent accessibility prediction), is reasonably accurate for predicting the real value of solvent accessibility. By using a dataset of 30 proteins to optimize three parameters, the average correlation coefficients between the predicted and actual solvent accessibility are about 0.5 for all four independent test sets ranging from 126 to 513 proteins. The method is efficient. It takes only 20 min for a regular PC to obtain results of 30 proteins with an average length of 263 amino acids. Although the proposed method is less accurate than a few more sophisticated methods based on neural network or support vector machines, this is the first attempt to predict solvent accessibility by energy optimization with constraints. Possible improvements and other applications of the method are discussed.

AB - Solvent accessibility, one of the key properties of amino acid residues in proteins, can be used to assist protein structure prediction. Various approaches such as neural network, support vector machines, probability profiles, information theory, Bayesian theory, logistic function, and multiple linear regression have been developed for solvent accessibility prediction. In this article, a much simpler quadratic programming method based on the buriability parameter set of amino acid residues is developed. The new method, called QBES (Quadratic programming and Buriability Energy function for Solvent accessibility prediction), is reasonably accurate for predicting the real value of solvent accessibility. By using a dataset of 30 proteins to optimize three parameters, the average correlation coefficients between the predicted and actual solvent accessibility are about 0.5 for all four independent test sets ranging from 126 to 513 proteins. The method is efficient. It takes only 20 min for a regular PC to obtain results of 30 proteins with an average length of 263 amino acids. Although the proposed method is less accurate than a few more sophisticated methods based on neural network or support vector machines, this is the first attempt to predict solvent accessibility by energy optimization with constraints. Possible improvements and other applications of the method are discussed.

KW - Amino acid residues

KW - Proteins

KW - Solvent accessibility

UR - http://www.scopus.com/inward/record.url?scp=33646864744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646864744&partnerID=8YFLogxK

U2 - 10.1002/prot.20934

DO - 10.1002/prot.20934

M3 - Article

C2 - 16514609

AN - SCOPUS:33646864744

VL - 63

SP - 961

EP - 966

JO - Proteins: Structure, Function and Bioinformatics

JF - Proteins: Structure, Function and Bioinformatics

SN - 0887-3585

IS - 4

ER -