Prediction of protein-protein interactions based on molecular interface features and the support vector machine

Weiqiang Zhou, Hong Yan, Xiaodan Fan, Quan Hao

Research output: Contribution to journalArticle

Abstract

Protein-protein interactions play important roles in many biological progresses. Previous studies about proteinprotein interactions were mainly based on sequence analysis. As more 3D structural information can be obtained from protein-protein complexes, structural analysis becomes feasible and useful. In this study, we used structural alignment to predict protein-binding sites and analyzed interface properties using 3D alpha shape. We have developed a method for protein-protein interaction prediction. The result indicates good performance of our method in discriminating proteinbinding structures from non-protein-binding structures. In the experiment, our method shows best Matthews correlation coefficient of 0.204.

Original languageEnglish (US)
Pages (from-to)3-8
Number of pages6
JournalCurrent Bioinformatics
Volume8
Issue number1
StatePublished - Jan 1 2013
Externally publishedYes

Fingerprint

Protein-protein Interaction
Support vector machines
Support Vector Machine
Proteins
Protein
Prediction
Sequence Analysis
Structural Analysis
Correlation coefficient
Alignment
Predict
Binding sites
Protein Binding
Structural analysis
Experiment
Binding Sites
Experiments

Keywords

  • Alpha shape
  • Protein-protein interaction
  • Structural alignment

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Genetics
  • Computational Mathematics

Cite this

Prediction of protein-protein interactions based on molecular interface features and the support vector machine. / Zhou, Weiqiang; Yan, Hong; Fan, Xiaodan; Hao, Quan.

In: Current Bioinformatics, Vol. 8, No. 1, 01.01.2013, p. 3-8.

Research output: Contribution to journalArticle

@article{96dbf36788084241b2ef2ed599331c1c,
title = "Prediction of protein-protein interactions based on molecular interface features and the support vector machine",
abstract = "Protein-protein interactions play important roles in many biological progresses. Previous studies about proteinprotein interactions were mainly based on sequence analysis. As more 3D structural information can be obtained from protein-protein complexes, structural analysis becomes feasible and useful. In this study, we used structural alignment to predict protein-binding sites and analyzed interface properties using 3D alpha shape. We have developed a method for protein-protein interaction prediction. The result indicates good performance of our method in discriminating proteinbinding structures from non-protein-binding structures. In the experiment, our method shows best Matthews correlation coefficient of 0.204.",
keywords = "Alpha shape, Protein-protein interaction, Structural alignment",
author = "Weiqiang Zhou and Hong Yan and Xiaodan Fan and Quan Hao",
year = "2013",
month = "1",
day = "1",
language = "English (US)",
volume = "8",
pages = "3--8",
journal = "Current Bioinformatics",
issn = "1574-8936",
publisher = "Bentham Science Publishers B.V.",
number = "1",

}

TY - JOUR

T1 - Prediction of protein-protein interactions based on molecular interface features and the support vector machine

AU - Zhou, Weiqiang

AU - Yan, Hong

AU - Fan, Xiaodan

AU - Hao, Quan

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Protein-protein interactions play important roles in many biological progresses. Previous studies about proteinprotein interactions were mainly based on sequence analysis. As more 3D structural information can be obtained from protein-protein complexes, structural analysis becomes feasible and useful. In this study, we used structural alignment to predict protein-binding sites and analyzed interface properties using 3D alpha shape. We have developed a method for protein-protein interaction prediction. The result indicates good performance of our method in discriminating proteinbinding structures from non-protein-binding structures. In the experiment, our method shows best Matthews correlation coefficient of 0.204.

AB - Protein-protein interactions play important roles in many biological progresses. Previous studies about proteinprotein interactions were mainly based on sequence analysis. As more 3D structural information can be obtained from protein-protein complexes, structural analysis becomes feasible and useful. In this study, we used structural alignment to predict protein-binding sites and analyzed interface properties using 3D alpha shape. We have developed a method for protein-protein interaction prediction. The result indicates good performance of our method in discriminating proteinbinding structures from non-protein-binding structures. In the experiment, our method shows best Matthews correlation coefficient of 0.204.

KW - Alpha shape

KW - Protein-protein interaction

KW - Structural alignment

UR - http://www.scopus.com/inward/record.url?scp=84890466859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890466859&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84890466859

VL - 8

SP - 3

EP - 8

JO - Current Bioinformatics

JF - Current Bioinformatics

SN - 1574-8936

IS - 1

ER -