The major goal of Computational Biology and Bioinformatics is to achieve a better understanding of the principles of biological systems and processes using informatics tools. Elucidation of the full network of protein-protein interactions is a crucial part of this challenge. Thus, there is a growing need for fast and reliable in silico methods for predicting protein-protein interactions. Here, we present a high-performance algorithm for automated prediction of protein-protein interactions. We adopt a novel bottom-up approach that combines structure and sequence conservation in protein interfaces.