A novel method to predict protein complexes based on Gene Ontology in PPI networks

Protein complexes are important for understanding principles of cellular organization and function. Since protein data are noisy with the high false positive and false negative rates, which may have a negative impact on the performance of complex discovery algorithms. In this paper, we propose a novel method to predict protein complexes based on Gene Ontology in PPI (protein-protein interaction) networks. A protein semantic similarity is employed to estimate the reliability of the interaction. By selecting protein pairs with high similarity for a new reliable network, complexes are detected in it. Experimental results show that our method performs better than the other algorithms. © 2013 by Binary Information Press.