Computational prediction of protein interaction networks through supervised classification techniques

Browne Fiona, HY Wang, H Zheng, Azuaje Francisco

Research output: Contribution to journalArticle

Abstract

This paper implements integrative methods to predict Pairwise (PW) and Module-Based (MB) protein interactions in Saccharomyces cerevisiae. The predictive ability of combining diverse sets of relatively strong and weak predictive datasets is investigated. Different classification techniques: Naive Bayesian (NB), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN) were evaluated. The assessment demonstrated that as the predictive power of single-source datasets became weaker, MLP and NB performed better than KNN. Generation of PPI maps for S. cerevisiae and beyond will be improved with new, higher-quality datasets with increased interactome coverage and the integration of classification methods.
LanguageEnglish
Pages205-221
JournalInternational Journal of Functional Informatics and Personalised Medicine
Volume1
Issue number2
DOIs
Publication statusPublished - Sep 2008

Fingerprint

Multilayer neural networks
Yeast
Proteins

Cite this

@article{58da5c2fa3d444dba66b5c6c47dc766c,
title = "Computational prediction of protein interaction networks through supervised classification techniques",
abstract = "This paper implements integrative methods to predict Pairwise (PW) and Module-Based (MB) protein interactions in Saccharomyces cerevisiae. The predictive ability of combining diverse sets of relatively strong and weak predictive datasets is investigated. Different classification techniques: Naive Bayesian (NB), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN) were evaluated. The assessment demonstrated that as the predictive power of single-source datasets became weaker, MLP and NB performed better than KNN. Generation of PPI maps for S. cerevisiae and beyond will be improved with new, higher-quality datasets with increased interactome coverage and the integration of classification methods.",
author = "Browne Fiona and HY Wang and H Zheng and Azuaje Francisco",
year = "2008",
month = "9",
doi = "10.1504/IJFIPM.2008.020188",
language = "English",
volume = "1",
pages = "205--221",
journal = "International Journal of Functional Informatics and Personalised Medicine",
issn = "1756-2104",
number = "2",

}

TY - JOUR

T1 - Computational prediction of protein interaction networks through supervised classification techniques

AU - Fiona, Browne

AU - Wang, HY

AU - Zheng, H

AU - Francisco, Azuaje

PY - 2008/9

Y1 - 2008/9

N2 - This paper implements integrative methods to predict Pairwise (PW) and Module-Based (MB) protein interactions in Saccharomyces cerevisiae. The predictive ability of combining diverse sets of relatively strong and weak predictive datasets is investigated. Different classification techniques: Naive Bayesian (NB), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN) were evaluated. The assessment demonstrated that as the predictive power of single-source datasets became weaker, MLP and NB performed better than KNN. Generation of PPI maps for S. cerevisiae and beyond will be improved with new, higher-quality datasets with increased interactome coverage and the integration of classification methods.

AB - This paper implements integrative methods to predict Pairwise (PW) and Module-Based (MB) protein interactions in Saccharomyces cerevisiae. The predictive ability of combining diverse sets of relatively strong and weak predictive datasets is investigated. Different classification techniques: Naive Bayesian (NB), Multilayer Perceptron (MLP) and K-Nearest Neighbors (KNN) were evaluated. The assessment demonstrated that as the predictive power of single-source datasets became weaker, MLP and NB performed better than KNN. Generation of PPI maps for S. cerevisiae and beyond will be improved with new, higher-quality datasets with increased interactome coverage and the integration of classification methods.

UR - http://www.inderscience.com/browse/index.php

U2 - 10.1504/IJFIPM.2008.020188

DO - 10.1504/IJFIPM.2008.020188

M3 - Article

VL - 1

SP - 205

EP - 221

JO - International Journal of Functional Informatics and Personalised Medicine

T2 - International Journal of Functional Informatics and Personalised Medicine

JF - International Journal of Functional Informatics and Personalised Medicine

SN - 1756-2104

IS - 2

ER -