Protein Interaction Prediction by Integrating Genomic Features and Protein Interaction Network Analysis

The recent explosion of genomic-scale protein interaction screens has made it possible to study protein interactions on a level of interactome and networks. In this chapter, we begin with an introduction of a novel approach that probabilistically combines multiple information sources to predict protein interactions in yeast. Specifically, Section 5.2 describes the sources of genomic features. Section 5.3 provides a basic tutorial on machine-learning approaches and describes in detail the decision tree and naı̈ve Bayesian network that have been used in above study. Section 5.4 discusses the missing value challenges in further development of our existing method. We then shift our attention to discuss protein–protein interactions in the context of networks in Section 5.5, where we present two important network analysis approaches: topology network analysis and modular network analysis. Finally we discuss advantages and key limitations of our method, and our vision of challenges in this area.