Prediction of interface residue based on the features of residue interaction network

Xiong Jiao, Shoba Ranganathan

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Protein-protein interaction plays a crucial role in the cellular biological processes. Interface prediction can improve our understanding of the molecular mechanisms of the related processes and functions. In this work, we propose a classification method to recognize the interface residue based on the features of a weighted residue interaction network. The random forest algorithm is used for the prediction and 16 network parameters and the B-factor are acting as the element of the input feature vector. Compared with other similar work, the method is feasible and effective. The relative importance of these features also be analyzed to identify the key feature for the prediction. Some biological meaning of the important feature is explained. The results of this work can be used for the related work about the structure-function relationship analysis via a residue interaction network model.

LanguageEnglish
Pages49-54
Number of pages6
JournalJournal of Theoretical Biology
Volume432
DOIs
Publication statusPublished - 7 Nov 2017

Fingerprint

Biological Phenomena
prediction
Prediction
Interaction
Proteins
Random Forest
protein-protein interactions
Protein-protein Interaction
Structure-function
structure-activity relationships
Feature Vector
Network Model
methodology
3'-(1-butylphosphoryl)adenosine
Meaning
Relationships

Keywords

  • Interface prediction
  • Network feature
  • Protein-protein interaction
  • Random forest

Cite this

@article{2b33ba2a94eb46e2aff118f2a0d67476,
title = "Prediction of interface residue based on the features of residue interaction network",
abstract = "Protein-protein interaction plays a crucial role in the cellular biological processes. Interface prediction can improve our understanding of the molecular mechanisms of the related processes and functions. In this work, we propose a classification method to recognize the interface residue based on the features of a weighted residue interaction network. The random forest algorithm is used for the prediction and 16 network parameters and the B-factor are acting as the element of the input feature vector. Compared with other similar work, the method is feasible and effective. The relative importance of these features also be analyzed to identify the key feature for the prediction. Some biological meaning of the important feature is explained. The results of this work can be used for the related work about the structure-function relationship analysis via a residue interaction network model.",
keywords = "Interface prediction, Network feature, Protein-protein interaction, Random forest",
author = "Xiong Jiao and Shoba Ranganathan",
year = "2017",
month = "11",
day = "7",
doi = "10.1016/j.jtbi.2017.08.014",
language = "English",
volume = "432",
pages = "49--54",
journal = "Journal of Theoretical Biology",
issn = "0022-5193",
publisher = "ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD",

}

Prediction of interface residue based on the features of residue interaction network. / Jiao, Xiong; Ranganathan, Shoba.

In: Journal of Theoretical Biology, Vol. 432, 07.11.2017, p. 49-54.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Prediction of interface residue based on the features of residue interaction network

AU - Jiao, Xiong

AU - Ranganathan, Shoba

PY - 2017/11/7

Y1 - 2017/11/7

N2 - Protein-protein interaction plays a crucial role in the cellular biological processes. Interface prediction can improve our understanding of the molecular mechanisms of the related processes and functions. In this work, we propose a classification method to recognize the interface residue based on the features of a weighted residue interaction network. The random forest algorithm is used for the prediction and 16 network parameters and the B-factor are acting as the element of the input feature vector. Compared with other similar work, the method is feasible and effective. The relative importance of these features also be analyzed to identify the key feature for the prediction. Some biological meaning of the important feature is explained. The results of this work can be used for the related work about the structure-function relationship analysis via a residue interaction network model.

AB - Protein-protein interaction plays a crucial role in the cellular biological processes. Interface prediction can improve our understanding of the molecular mechanisms of the related processes and functions. In this work, we propose a classification method to recognize the interface residue based on the features of a weighted residue interaction network. The random forest algorithm is used for the prediction and 16 network parameters and the B-factor are acting as the element of the input feature vector. Compared with other similar work, the method is feasible and effective. The relative importance of these features also be analyzed to identify the key feature for the prediction. Some biological meaning of the important feature is explained. The results of this work can be used for the related work about the structure-function relationship analysis via a residue interaction network model.

KW - Interface prediction

KW - Network feature

KW - Protein-protein interaction

KW - Random forest

UR - http://www.scopus.com/inward/record.url?scp=85027578806&partnerID=8YFLogxK

U2 - 10.1016/j.jtbi.2017.08.014

DO - 10.1016/j.jtbi.2017.08.014

M3 - Article

VL - 432

SP - 49

EP - 54

JO - Journal of Theoretical Biology

T2 - Journal of Theoretical Biology

JF - Journal of Theoretical Biology

SN - 0022-5193

ER -