EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RIBEX: predicting and explaining RNA binding across structured and intrinsically disordered regions (IDR)-rich proteins

Samuele Firmani iD, Felix Steinbauer iD, Gjergji Kasneci iD, Annalisa Marsico iD, Marc Horlacher iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag471 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Samuele Firmani und 4 weiteren Autor:innen. Beteiligte Einrichtung: Computational Health Center, Helmholtz Center Munich, Neuherberg 85764, Germany. Hauptthemen laut MEDLINE: RNA-Binding Proteins, RNA, Intrinsically Disordered Proteins, Computational Biology. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Helmholtz Association under the joint research school Munich School for Data Science-MUDS, Technical University of Munich, SFB TRR267.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation RNA-binding proteins (RBPs) regulate post-transcriptional processes, yet many remain undiscovered because RNA-binding activity often occurs outside canonical RNA-binding domains (RBDs), including within intrinsically disordered regions (IDRs) or through protein complexes. Computational methods can help identify novel RBPs, but approaches relying solely on sequence-derived features or ignoring the cellular interaction context are limited in capturing the complexity of RNA-binding behavior. To date, no framework rigorously integrates both sequence information and protein interaction context for RBP prediction. Results We introduce RIBEX, a multimodal framework that combines protein language model (pLM) embeddings with protein interactome topology to improve RBP prediction and interpretation. Specifically, we integrate sequence representations with graph-derived positional encodings (PE) from the human STRING protein–protein interaction (PPI) network. PE are computed using Personalized PageRank, reduced with principal component analysis, and fused with pooled sequence embeddings through FiLM conditioning, while Low-Rank Adaptation (LoRA) enables parameter-efficient task adaptation. Across both an annotation-based benchmark and experimental RNA Interactome Capture (RIC) dataset, PE consistently improves predictive performance, indicating that interactome topology provides complementary information beyond sequence features. LoRA adaptation of ESM2-650M further yields larger gains than simply scaling frozen backbone size. RIBEX outperforms state-of-the-art methods such as RBP-TSTL and HydRA, particularly on challenging subsets including proteins lacking canonical RBDs and those enriched in IDRs. For interpretability, we combine sequence-level computational alanine scanning with network-level positional-encoding ablation and inverse-PCA mapping, recovering known RNA-binding domains, IDR-associated contributions, and functional interactome communities linked to RBP predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RNA-Binding ProteinsRNAIntrinsically Disordered ProteinsComputational BiologySoftwareHumansProtein BindingBinding Sites

Substanzen

RNA-Binding ProteinsRNAIntrinsically Disordered Proteins

Autor:innen und Institutionen

  • Computational Health Center, Helmholtz Center Munich, Neuherberg 85764, Germany.
  • School of Computation, Information and Technology, Technical University of Munich, Munich 80333, Germany.
  • Munich Center for Machine Learning (MCML), Munich, Germany.
  • School of Social Sciences and Technology, Technical University of Munich, Munich 80333, Germany.
  • Cluster for Nucleic Acid Sciences and Technologies-NUCLEATE, Munich, Germany.

ORCID-Profile: Samuele Firmani, Felix Steinbauer, Gjergji Kasneci, Annalisa Marsico, Marc Horlacher

Förderung

  • Helmholtz Association under the joint research school Munich School for Data Science-MUDS
  • Technical University of Munich
  • SFB TRR267
  • Deutsche Forschungsgemeinschaft
  • Cluster for Nucleic Acid Sciences and Technologies-NUCLEATE
  • Helmholtz Association under the joint research school Munich School for Data Science—MUDS
  • Cluster for Nucleic Acid Sciences and Technologies—NUCLEATE

Zitieren

APA

Firmani, S., Steinbauer, F., Kasneci, G., Marsico, A., & Horlacher, M. (2026). RIBEX: predicting and explaining RNA binding across structured and intrinsically disordered regions (IDR)-rich proteins. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag471

Vancouver

Firmani S, Steinbauer F, Kasneci G, Marsico A, Horlacher M. RIBEX: predicting and explaining RNA binding across structured and intrinsically disordered regions (IDR)-rich proteins. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag471

BibTeX
@article{Firmani2026,
  author = {Firmani, Samuele and Steinbauer, Felix and Kasneci, Gjergji and Marsico, Annalisa and Horlacher, Marc},
  title = {RIBEX: predicting and explaining RNA binding across structured and intrinsically disordered regions (IDR)-rich proteins},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag471}
}
Kostenlos starten →