EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MiRformer: a dual-transformer-encoder framework for predicting microRNA-mRNA interactions from paired sequences

Jiayao Gu, Can Chen, Yue Li iD

Bioinformatics · 01.07.2026 · 42 (Supplement_1)

DOI: 10.1093/bioinformatics/btag222 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.07.2026. Verfasst von Jiayao Gu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, McGill University, Montréal, QC, H3A 0G4, Canada. Hauptthemen laut MEDLINE: MicroRNAs, RNA, Messenger, Computational Biology, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DNA2RNA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation MicroRNAs (miRNAs) regulate gene expression by binding to target messenger RNAs (mRNAs), inducing translational repression or mRNA degradation. Accurate prediction of miRNA–mRNA interactions and precise localization of binding and cleavage sites are critical for understanding post-transcriptional regulation and for enabling RNA therapeutics. Existing computational methods often rely on handcrafted or indirect features, scale poorly to kilobase-long mRNA sequences, or provide limited interpretability. Results We present MiRformer, a transformer-based framework that jointly predicts miRNA–mRNA interactions and localizes miRNA binding and cleavage sites directly from raw sequence pairs. MiRformer employs a dual-transformer encoder architecture for miRNA and mRNA sequences and incorporates a sliding-window attention mechanism to efficiently model kilobase-long mRNA contexts while preserving nucleotide-level resolution. Across multiple benchmrks, MiRformer achieves state-of-the-art performance on interaction prediction, binding-site localization, and cleavage-site identification from experimental Human Degradome-seq data. Beyond accuracy, MiRformer provides strong interpretability: attention patterns consistently highlight miRNA seed regions within 500-nt mRNA windows, revealing clear and biologically meaningful interaction signals. When applied to jointly infer binding and cleavage sites across 13k miRNA–mRNA pairs, predicted sites frequently co-localize, supporting a miRNA-mediated degradation mechanism. Availability and implementation Python code and datasets are publicly available at https://github.com/li-lab-mcgill/miRformer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MicroRNAsRNA, MessengerComputational BiologySoftwareSequence Analysis, RNAHumansBinding Sites

Substanzen

MicroRNAsRNA, Messenger

Autor:innen und Institutionen

  • School of Computer Science, McGill University, Montréal, QC, H3A 0G4, Canada.
  • Mila-Quebéc AI Institute, Montréal, QC, H2S 3H1, Canada.

ORCID-Profile: Yue Li

Förderung

  • DNA2RNA

Zitieren

APA

Gu, J., Chen, C., & Li, Y. (2026). MiRformer: a dual-transformer-encoder framework for predicting microRNA-mRNA interactions from paired sequences. Bioinformatics, 42(Supplement_1). https://doi.org/10.1093/bioinformatics/btag222

Vancouver

Gu J, Chen C, Li Y. MiRformer: a dual-transformer-encoder framework for predicting microRNA-mRNA interactions from paired sequences. Bioinformatics. 2026;42(Supplement_1). doi:10.1093/bioinformatics/btag222

BibTeX
@article{Gu2026,
  author = {Gu, Jiayao and Chen, Can and Li, Yue},
  title = {MiRformer: a dual-transformer-encoder framework for predicting microRNA-mRNA interactions from paired sequences},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {Supplement_1},
  doi = {10.1093/bioinformatics/btag222}
}
Kostenlos starten →