miRBind2 enables sequence-only prediction of miRNA binding and transcript repression
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag410 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von David Čechák und 6 weiteren Autor:innen. Beteiligte Einrichtung: Central European Institute of Technology, Masaryk University, Brno 625 00, Czech Republic. Hauptthemen laut MEDLINE: MicroRNAs, Computational Biology, Deep Learning, Software. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BioGeMT, HORIZON-WIDERA-2022, Bioinformatics Core Facility of CEITEC Masaryk University supported by the NCMG Research Infrastructure.
Abstract (Originalsprache)
Motivation MicroRNAs (miRNAs) regulate gene expression by guiding Argonaute proteins to partially complementary sites on target RNAs. While classical prediction methods rely on engineered features such as seed match categories, evolutionary conservation, and site context, recent advances in deep learning offer the potential to learn targeting rules directly from sequence. We developed a sequence-based deep learning model that improves miRNA target site prediction, and further validated the learned target site representations by extending the model to gene-level functional repression prediction. Results We introduce miRBind2, a deep learning method for miRNA target site prediction that incorporates a novel pairwise nucleotide representation capturing all possible miRNA-target nucleotide interactions, with a CNN-based architecture. miRBind2 outperforms previous SotA models across four independent datasets from the debiased miRBench benchmark, while using 92% fewer parameters. We show that the convolutional features and weights learned by miRBind2 can be transferred to transcript-level prediction by extending the miRBind2 architecture and fine-tuning it on miRNA perturbation experiments. This miRBind2-3UTR model predicts gene repression from sequence alone. On a dataset of 50 549 miRNA-gene pairs, miRBind2-3UTR significantly outperforms TargetScan. These results show that deep models pretrained on target site data can capture regulatory signals and predict functional repression without requiring conventional engineered biological features. Availability Models and source code are freely available via GitHub (https://github.com/BioGeMT/miRBind_2.0). A publicly available web-tool for novel predictions and visualization is available at: (https://huggingface.co/spaces/dimostzim/BioGeMT-miRBind2).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Central European Institute of Technology, Masaryk University, Brno 625 00, Czech Republic.
- National Centre for Biomolecular Research, Faculty of Science, Masaryk University, Brno 625 00, Czech Republic.
- Department of Applied Biomedical Science, Faculty of Health Sciences, University of Malta, Msida, Malta.
- Centre for Molecular Medicine and Biobanking, University of Malta, Msida, Malta.
- Max-Delbrück-Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin Institute for Medical Systems Biology (BIMSB), Berlin, Germany.
- Faculty of ICT, University of Malta, Msida, MSD 2080, Malta.
ORCID-Profile: Panagiotis Alexiou
Förderung
- BioGeMT
- HORIZON-WIDERA-2022
- Bioinformatics Core Facility of CEITEC Masaryk University supported by the NCMG Research Infrastructure
- MEYS CR
- University of Malta, and the e-INFRA CZ project
Zitieren
APA
Čechák, D., Tzimotoudis, D., Sammut, S., Gresova, K., Marsalkova, E., Farrugia, D., & Alexiou, P. (2026). miRBind2 enables sequence-only prediction of miRNA binding and transcript repression. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag410
Vancouver
Čechák D, Tzimotoudis D, Sammut S, Gresova K, Marsalkova E, Farrugia D, et al. miRBind2 enables sequence-only prediction of miRNA binding and transcript repression. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag410
BibTeX
@article{echk2026,
author = {Čechák, David and Tzimotoudis, Dimosthenis and Sammut, Stephanie and Gresova, Katarina and Marsalkova, Eva and Farrugia, David and Alexiou, Panagiotis},
title = {miRBind2 enables sequence-only prediction of miRNA binding and transcript repression},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag410}
}
EUVIMED