Improving prediction of protein function from protein interaction network using intelligent neighborhood approach

Abstract

Proteins are responsible for all biological activities in a living object. With the advent of genome sequencing projects for different organisms, large amounts of DNA and protein sequence data is available, whereas their biological function is still un-annotated in the most of the cases. Predicting protein function is the most challenging problem in post-genomic era. Using sequence homology, phylogenetic profiles, gene expression data, and function of un-annotated protein can be predicted. Recently, the large interaction networks constructed from high throughput techniques like Yeast2Hybrid experiments are also used in prediction of protein function. Based on the concept that a protein performs similar function like its neighbor in protein Interaction network, two methods are proposed to predict protein function from protein interaction network using neighborhood properties. The first method uses neighborhood approach and second one is an intelligent technique which applies heuristic knowledge to find densely connected regions for better prediction accuracy. The overall match rate achieved in method-I is 95.8% and in method-II, it is 97.8% over 15 functional groups.