EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

The role of protein embeddings for protein–protein interaction prediction with graph neural networks

Laura Balbi, Rita T Sousa, Pedro Cotovio, Catia Pesquita

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Laura Balbi und 3 weiteren Autor:innen. Beteiligte Einrichtung: LASIGE, Faculdade de Ciências da Universidade de Lisboa, Campo Grande, 1749-016 Lisbon, Portugal. Hauptthemen laut MEDLINE: Computational Biology, Graph Neural Networks, Protein Interaction Mapping, Protein Interaction Maps. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 208 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: LASIGE Research Unit, European Union's Horizon 2020 research and innovation programme, CancerScan project by the EU's HORIZON Europe research and innovation programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph neural networks are a natural fit for protein–protein interaction (PPI) prediction because they exploit the graph structure of interactomes, yet it remains unclear how much they benefit from protein-level representations and which sources of protein information matter most. We address this by surveying and organizing the field into a coherent taxonomy that describes three paradigms: network-level approaches (shallow and deep graph representation learning), protein-level approaches (sequence, structure, and function), and hybrid methods that combine both paradigms—providing a cohesive synthesis that highlights their respective strengths, complementarities, and tradeoffs. We developed a unified framework to systematically compare these paradigms that incorporates multiple representative methods and evaluates them on two widely used benchmarks: OGBl-ppa and HuRI. Our results indicate that hybrid methods have improved performance, with function-driven representations emerging as the most informative protein-level representations for PPI prediction. This work provides a taxonomical map of the field, a reproducible framework for evaluating representative methods across paradigms, and practical guidance for future PPI prediction efforts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyGraph Neural NetworksProtein Interaction MappingProtein Interaction MapsProteinsHumansDatabases, Protein

Stichwörter der Autor:innen

PPI networksgraph neural networksprotein language modelsprotein–protein interaction

Substanzen

Proteins

Autor:innen und Institutionen

  • LASIGE, Faculdade de Ciências da Universidade de Lisboa, Campo Grande, 1749-016 Lisbon, Portugal.
  • University of Mannheim, 68131 Mannheim, Germany.
  • Department of Computer Science, City St George's, University of London, EC1V 0HB, United Kingdom.

Förderung

  • LASIGE Research Unit
  • European Union's Horizon 2020 research and innovation programme
  • CancerScan project by the EU's HORIZON Europe research and innovation programme
  • European Union’s Horizon 2020 research and innovation programme
  • CancerScan project by the EU’s HORIZON Europe research and innovation programme

Zitieren

APA

Balbi, L., Sousa, R. T., Cotovio, P., & Pesquita, C. (2026). The role of protein embeddings for protein–protein interaction prediction with graph neural networks. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag313

Vancouver

Balbi L, Sousa RT, Cotovio P, Pesquita C. The role of protein embeddings for protein–protein interaction prediction with graph neural networks. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag313

BibTeX
@article{Balbi2026,
  author = {Balbi, Laura and Sousa, Rita T and Cotovio, Pedro and Pesquita, Catia},
  title = {The role of protein embeddings for protein–protein interaction prediction with graph neural networks},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag313}
}
Kostenlos starten →