A novel, comprehensive method to detect and predict protein-protein interactions applied to the study of vesicular trafficking

Abstract

Motivation. Computational methods to predict protein-protein interactions are of great need. They can help to formulate hypotheses, guide experimental research and serve as additional measures to assess the quality of data obtained in high-throughput interaction experiments. Here, we describe a fully automated threestep procedure to predict and confirm protein-protein interactions. By maximising the information from text mining of the biomedical literature, data from interaction databases, and from available protein structures, we aim at generating a comprehensive picture of known and novel potential interactions between a given set of proteins. Results. A recent proteomics assay to identify the protein machinery involved in vesicular trafficking between the biosynthetic and the endosomal compartments revealed 35 proteins that were found as part of membrane coats on liposomes. When applying our method to this data set, we are able to reconstruct most of the interactions known to the molecular biologist. In addition, we predict novel interactions, among these potential linkers of the AP-1 and the Arp2/3 complex to membrane-bound proteins as well as a potential GTPase-GTPase effector interaction. Conclusions. Our method allows for a comprehensive network reconstruction that can assist the molecular biologist. Predicted interactions are backed up by structural or experimental evidence and can be inferred at varying levels of confidence. Our method pinpoints existing key interactions and can facilitate the generation of hypotheses.