- Article -

Volume 9

Full article

Amino-acid residue association models for large scale protein-protein interaction prediction

Raghuraj Rao¹, Kyaw Tun², Yuko Makita ³, Samavedham Lakshminarayanan¹, Pawan K. Dhar²*

¹ Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore - 117576
² Synthetic Biology Team, RIKEN Genomic Sciences Center, Tsurumi-ku, Yokohama, Japan - 2300045
³ Bioinformatics and Systems Engineering Team, RIKEN, Tsurumi-Ku, Yokohama, Japan - 2300045

* Corresponding author
   Email: pkdhar@riken.jp


Edited by E. Wingender; received February 01, 2009; revised April 08, 2009; accepted April 11, 2009; published May 29, 2009

Abstract

The computational prediction of protein-protein interactions (PPI) is an essential complement to direct experimental evidence. Traditional approaches rely on less available or computationally predicted surface properties, show database-specific performances and are computationally expensive for large-scale datasets. Several sensitivity and specificity issues remain. Here, we report a novel method based on 'Amino-acid Residue Associations' (ARA) among interacting proteins which utilizes the accurate and easily available primary sequence.

E. coli to human) were studied. The ARA method shows up to 73% sensitivity and 78% specificity. Furthermore, the method performs remarkably well in terms of stability and generalizability. The performance of ARA method benchmarked against existing prediction techniques shows performance improvement up to 25%. Ability of ARA method to predict PPI across species and across databases is also demonstrated. Overall, the ARA method provides a significant improvement over existing ones in correctly identifying large scale protein-protein interactions, irrespective of the data resource, network size or organism.

Keywords: protein-protein interaction, amino acid residue, proteomics, systems biology, pattern recognition, machine learning, computational method, prediction