PREDICTION OF PROTEIN FUNCTION FROM CONNECTIVITY OF PROTEIN INTERACTION NETWORKS

Abstract

Determining protein function on a proteomic scale is a major challenge in the post-genomic era. Right now only less than half of the actual functional annotations are available for a typical proteome. The recent high-throughput bio-techniques have provided us large-scale protein–protein interaction (PPI) data, and many studies have shown that function prediction from PPI data is a promising way as proteins are likely to collaborate for a common purpose. However, the protein interaction data is very noisy, which makes the task very challenging. In this paper, a distance matrix is proposed based on the smallworld property and connectivity of the PPI network. It measures the reliability of edges and filters the noise in the network. In addition, we design an ANN (artificial neural network) method to predict protein functions with integration of several protein interaction data sets. Our approach is tested with MIPS functional categories and the experiential results show that our approach has better performance than other existing methods in terms of precision and recall.