EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SPPIDER-seq: sequence-based partner-aware predictor of protein-protein interaction sites

Aleksey Porollo iD, Om Jadhav iD, Aaron Alvarez iD, Jichao Chen iD

Bioinformatics · 02.07.2026 · 42 (7)

DOI: 10.1093/bioinformatics/btag388 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 13.06.2026. Verfasst von Aleksey Porollo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Health Informatics and Data Sciences, University of Cincinnati College of Medicine, Cincinnati, OH 45267, United States. Hauptthemen laut MEDLINE: Protein Interaction Mapping, Proteins, Software, Computational Biology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Sequence-based protein–protein interaction (PPI) site predictors typically analyze proteins in isolation, neglecting partner-specific context that is critical for interface specificity, particularly in transient and disordered interactions. Results We introduce SPPIDER-seq, a partner-aware PPI site prediction framework that combines pretrained ESM-2 embeddings with a cross-attention architecture to enable residue-level conditioning on interacting partners. We curated non-redundant protein–peptide interaction datasets from BioLiP and used them to train and benchmark two complementary models: a receptor-centric model optimized for structured interfaces and a peptide-centric model tailored to disordered, motif-driven binding. On blind benchmarks, SPPIDER-seq achieved AUROC values up to 0.797 and MCC values up to 0.269, outperforming AlphaFold3 on peptide-mediated and disordered interfaces while remaining complementary on globular complexes. Application to 341 TP53 interaction partners revealed coherent, partner-specific interface patterns across both structured and intrinsically disordered regions. Availability SPPIDER-seq models, datasets, and the Python code are freely available on the web at https://github.com/aporollo-lab/SPPIDER-seq and archived on Zenodo at DOI: 10.5281/zenodo.19835990, corresponding to GitHub release v2.0-manuscript.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Protein Interaction MappingProteinsSoftwareComputational BiologySequence Analysis, ProteinBinding SitesProtein BindingDatabases, Protein

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Biostatistics, Health Informatics and Data Sciences, University of Cincinnati College of Medicine, Cincinnati, OH 45267, United States.
  • Department of Computer Science, University of Cincinnati College of Engineering and Applied Science, Cincinnati, OH 45221, United States.
  • Department of Pediatrics, Perinatal Institute Division of Pulmonary Biology, University of Cincinnati and Cincinnati Children's Hospital Medical Center, Cincinnati, OH 45229, United States.

ORCID-Profile: Aleksey Porollo, Om Jadhav, Aaron Alvarez, Jichao Chen

Förderung

  • NHLBI NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Porollo, A., Jadhav, O., Alvarez, A., & Chen, J. (2026). SPPIDER-seq: sequence-based partner-aware predictor of protein-protein interaction sites. Bioinformatics, 42(7). https://doi.org/10.1093/bioinformatics/btag388

Vancouver

Porollo A, Jadhav O, Alvarez A, Chen J. SPPIDER-seq: sequence-based partner-aware predictor of protein-protein interaction sites. Bioinformatics. 2026;42(7). doi:10.1093/bioinformatics/btag388

BibTeX
@article{Porollo2026,
  author = {Porollo, Aleksey and Jadhav, Om and Alvarez, Aaron and Chen, Jichao},
  title = {SPPIDER-seq: sequence-based partner-aware predictor of protein-protein interaction sites},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {7},
  doi = {10.1093/bioinformatics/btag388}
}
Kostenlos starten →