Paper Info
Title
Prediction of protein interaction with neural network-based feature association rule mining
Abstract
Prediction of protein interactions is one of the central problems in post-genomic biology. In this paper, we present an association rule-based protein interaction prediction method. We adopted neural network to cluster protein interaction data, and used information theory based feature selection method to reduce protein feature dimension. After model training, feature association rules are generated to interaction prediction by decoding a set of learned weights of trained neural network and by mining association rules. For model training, an initial network model was constructed with public Yeast protein interaction data considering their functional categories, set of features, and interaction partners. The prediction performance was compared with traditional simple association rule mining method. The experimental results show that proposed method has about 96.1% interaction prediction accuracy compared to simple association mining approach which achieved about 91.4% accuracy.
Year
DOI
Venue
2006
10.1007/11893295_4
ICONIP (3)
Keywords
Field
DocType
feature association rule,cluster protein interaction data,interaction prediction accuracy,association rule-based protein interaction,neural network-based feature association,public yeast protein interaction,prediction method,rule mining,mining association rule,protein interaction,interaction partner,model training,feature selection,association rule,network model,association rule mining,neural network,information theory
Information theory,Data mining,Adaptive resonance theory,Feature selection,Computer science,Expert system,Association rule learning,Artificial intelligence,Decoding methods,Artificial neural network,Network model,Machine learning
Conference
Volume
ISSN
ISBN
4234
0302-9743
3-540-46484-0
Citations 
PageRank 
References 
0
0.34
11
Authors
2
Name
Order
Citations
PageRank
Jae-Hong Eom1868.91
Byoung-Tak Zhang21571158.56