Modeling of negative protein-protein interactions: methods and experiments

TL;DR

This paper compares methods for simulating negative protein-protein interactions and evaluates the performance of state-of-the-art prediction systems under reliable data settings, addressing key challenges in PPI prediction accuracy.

Contribution

It introduces a comparison of negative PPI simulation methods and assesses system performance with high-quality data, improving prediction reliability.

Findings

Negative PPI simulation methods vary in effectiveness.

State-of-the-art systems perform better with reliable negative data.

Reliable data settings significantly impact PPI prediction accuracy.

Abstract

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.