A knowledge-driven probabilistic framework for the prediction of protein-protein interaction networks

Authors:
Fiona Browne;Haiying Wang;Huiru Zheng;Francisco Azuaje
Affiliations:
School of Computing and Mathematics, Computer Science Research Institute, University of Ulster at Jordanstown, Northern Ireland BT37 0QB, UK;School of Computing and Mathematics, Computer Science Research Institute, University of Ulster at Jordanstown, Northern Ireland BT37 0QB, UK;School of Computing and Mathematics, Computer Science Research Institute, University of Ulster at Jordanstown, Northern Ireland BT37 0QB, UK;Public Research Centre for Health (CRP-Santé), Laboratory of Cardiovascular Research, 120 route d Arlon, L-1150, Luxembourg
Venue:
Computers in Biology and Medicine
Year:
2010

Citing 8
Cited 4

The computational complexity of probabilistic inference using Bayesian belief networks (research note)

Artificial Intelligence
Online Predicted Human Interaction Database

Bioinformatics
The relationship between Precision-Recall and ROC curves

ICML '06 Proceedings of the 23rd international conference on Machine learning
Assessing semantic similarity measures for the characterization of human regulatory pathways

Bioinformatics
Variational approximations in Bayesian model selection for finite mixture distributions

Computational Statistics & Data Analysis
Bayesian Network Structure Ensemble Learning

ADMA '07 Proceedings of the 3rd international conference on Advanced Data Mining and Applications
A decomposition algorithm for learning Bayesian network structures from data

PAKDD'08 Proceedings of the 12th Pacific-Asia conference on Advances in knowledge discovery and data mining
Integration of Genomic Data for Inferring Protein Complexes from Global Protein–Protein Interaction Networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Using machine learning techniques and genomic/proteomic information from known databases for defining relevant features for PPI classification

Computers in Biology and Medicine
Domain information based prediction of protein-protein interactions of glucosinolate biosynthesis

International Journal of Computer Applications in Technology
An effective, practical and low computational cost framework for the integration of heterogeneous data to predict functional associations between proteins by means of Artificial Neural Networks

Neurocomputing
An information theoretic approach to assessing gene-ontology-driven similarity and its application

International Journal of Data Mining and Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study applied a knowledge-driven data integration framework for the inference of protein-protein interactions (PPI). Evidence from diverse genomic features is integrated using a knowledge-driven Bayesian network (KD-BN). Receiver operating characteristic (ROC) curves may not be the optimal assessment method to evaluate a classifier's performance in PPI prediction as the majority of the area under the curve (AUC) may not represent biologically meaningful results. It may be of benefit to interpret the AUC of a partial ROC curve whereby biologically interesting results are represented. Therefore, the novel application of the assessment method referred to as the partial ROC has been employed in this study to assess predictive performance of PPI predictions along with calculating the True positive/false positive rate and true positive/positive rate. By incorporating domain knowledge into the construction of the KD-BN, we demonstrate improvement in predictive performance compared with previous studies based upon the Naive Bayesian approach.