Deciphering biological processes, ranging from cellular functioning to disease mechanisms, requires the ability to accurately predict complicated protein–protein interactions (PPIs). Nevertheless, the computational cost of experimental approaches to PPI determination is high. As a result, machine learning techniques have gained interest lately. Additionally, not enough work has been done to analyze signed PPI networks, which capture both inhibitory (negative) and activating (positive) interactions. The authors introduce the Signed Two-Space Proximity Model (S2-SPM) for signed PPI networks, which explicitly takes into account both kinds of contacts and reflects the intricate regulatory processes seen in biological systems, in order to authentically depict biological relationships.
S2-SPM’s superior performance in predicting the presence and sign of interactions in SPPI networks is demonstrated in link prediction tasks against relevant baseline methods. Additionally, the biological prevalence of the identified archetypes is confirmed by an enrichment analysis of Gene Ontology (GO) terms, which reveals that distinct biological tasks are associated with archetypal groups formed by both interactions. This study is also validated regarding statistical significance and sensitivity analysis, providing insights into the functional roles of different interaction types. Finally, the robustness and consistency of the extracted archetype structures are confirmed using the Bayesian Normalized Mutual Information (BNMI) metric, proving the model’s reliability in capturing meaningful SPPI patterns.
The implementation of S2-SPM is and freely available at https://github.com/Nicknakis/S2SPMReference:
Nikolaos Nakis et.al.(2025) The signed two-space proximity model for learning representations in protein–protein interaction networks. Bioinformatics 41(6):btaf204.