Predicting protein-protein interactions based on protein-domain relationships

This paper proposes a new method that can predict the interactions between proteins intermediated by the protein-domain relations. We utilize the lazy expectation maximization (LEM) to compute an improved maximization likelihood estimation (MLE) model. The protein-domain relationships are extruded from Flam database and the combined data set of Uetz and Ito are used as the source of protein-protein interactions. Finally, the efficiency and the effectiveness of our proposed approach can be validated by a better performance such as the sensitivity of 80.1%, the specificity of 43.5%, and the lesser computational cost.