Modeling of negative protein-protein interactions: methods and experiments

Protein-protein interactions (PPIs) are of fundamental importance for the human body, and the knowledge of their existence can facilitate very important tasks like drug target developing and therapy design. The high-throughput experiments for detecting new PPIs are costly and time-consuming, stressing the need for new computational systems able to generate high-quality PPIs predictions. These systems have to face two main problems: the high incompleteness of the human interactome and the lack of high-quality negative protein-protein interactions (i.e. proteins that are known to not interact). The latter is usually overlooked by the PPIs prediction systems, causing a significant bias in the performances and metrics. In this work, we compare methods for simulating negative knowledge using highly reliable training and test sets. Moreover, we measure the performances of two state-of-the-art systems when very reliable settings are adopted.