Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access Highly Accessed Open Badges Research article

Prediction of protein-protein interaction types using association rule based classification

Sung Hee Park1, José A Reyes23, David R Gilbert2, Ji Woong Kim14 and Sangsoo Kim1*

Author Affiliations

1 Department of Bioinformatics & Life Science, Soongsil University, Seoul, 156-743, Korea

2 School of Information Systems, Computing and Mathematics, Brunel University, Uxbridge, UB8 3PH, UK

3 Facultad de Ingeniería, Universidad de Talca, Talca, Chile

4 Equispharm Co., Ltd, Seoul, 443-766, Korea

For all author emails, please log on.

BMC Bioinformatics 2009, 10:36  doi:10.1186/1471-2105-10-36

Published: 28 January 2009



Protein-protein interactions (PPI) can be classified according to their characteristics into, for example obligate or transient interactions. The identification and characterization of these PPI types may help in the functional annotation of new protein complexes and in the prediction of protein interaction partners by knowledge driven approaches.


This work addresses pattern discovery of the interaction sites for four different interaction types to characterize and uses them for the prediction of PPI types employing Association Rule Based Classification (ARBC) which includes association rule generation and posterior classification. We incorporated domain information from protein complexes in SCOP proteins and identified 354 domain-interaction sites. 14 interface properties were calculated from amino acid and secondary structure composition and then used to generate a set of association rules characterizing these domain-interaction sites employing the APRIORI algorithm. Our results regarding the classification of PPI types based on a set of discovered association rules shows that the discriminative ability of association rules can significantly impact on the prediction power of classification models. We also showed that the accuracy of the classification can be improved through the use of structural domain information and also the use of secondary structure content.


The advantage of our approach is that we can extract biologically significant information from the interpretation of the discovered association rules in terms of understandability and interpretability of rules. A web application based on our method can be found at webcite