miRBench: novel benchmark datasets for microRNA binding site prediction that mitigate against prevalent microRNA frequency class bias
Bioinformatics · 2025
DOI: 10.1093/bioinformatics/btaf233 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von Stephanie Sammut und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Molecular Medicine and Biobanking, University of Malta, Msida, MSD 2080, Malta. Hauptthemen laut MEDLINE: MicroRNAs, Computational Biology, Software. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BioGeMT, University of Malta and miRBench, Collaboration for microRNA Benchmarking.
Abstract (Originalsprache)
Motivation MicroRNAs (miRNAs) are crucial regulators of gene expression, but the precise mechanisms governing their binding to target sites remain unclear. A major contributing factor to this is the lack of unbiased experimental datasets for training accurate prediction models. While recent experimental advances have provided numerous miRNA–target interactions, these are solely positive interactions. Generating negative examples in silico is challenging and prone to introducing biases, such as the miRNA frequency class bias identified in this work. Biases within datasets can compromise model generalization, leading models to learn dataset-specific artifacts rather than true biological patterns. Results We introduce a novel methodology for negative sample generation that effectively mitigates the miRNA frequency class bias. Using this methodology, we curate several new, extensive datasets and benchmark several state-of-the-art methods on them. We find that a simple convolutional neural network model, retrained on some of these datasets, is able to outperform state-of-the-art methods reaching average precision scores between 0.81 and 0.86 in test datasets. This highlights the potential for leveraging unbiased datasets to achieve improved performance in miRNA binding site prediction. To facilitate further research and lower the barrier to entry for machine learning researchers, we provide an easily accessible Python package, miRBench, for dataset retrieval, sequence encoding, and the execution of state-of-the-art models. Availability and implementation The miRBench Python package is accessible at https://github.com/katarinagresova/miRBench/releases/tag/v1.0.1.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centre for Molecular Medicine and Biobanking, University of Malta, Msida, MSD 2080, Malta.
- Department of Applied Biomedical Science, Faculty of Health Sciences, University of Malta, Msida, MSD 2080, Malta.
- National Centre for Biomolecular Research, Faculty of Science, Masaryk University, Brno 61137, Czech Republic.
- Central European Institute of Technology, Masaryk University, Brno, 62500, Czech Republic.
ORCID-Profile: Panagiotis Alexiou
Förderung
- BioGeMT
- University of Malta and miRBench
- Collaboration for microRNA Benchmarking
- Xjenza Malta awarded to Panagiotis Alexiou
- Bioinformatics Core Facility of CEITEC Masaryk University
- NCMG Research Infrastructure
- Novel Drug Targets for Infectious Diseases
- Malta Council for Science and Technology
Zitieren
APA
Sammut, S., Gresova, K., Tzimotoudis, D., Marsalkova, E., Cechak, D., & Alexiou, P. (2025). miRBench: novel benchmark datasets for microRNA binding site prediction that mitigate against prevalent microRNA frequency class bias. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf233
Vancouver
Sammut S, Gresova K, Tzimotoudis D, Marsalkova E, Cechak D, Alexiou P. miRBench: novel benchmark datasets for microRNA binding site prediction that mitigate against prevalent microRNA frequency class bias. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf233
BibTeX
@article{Sammut2025,
author = {Sammut, Stephanie and Gresova, Katarina and Tzimotoudis, Dimosthenis and Marsalkova, Eva and Cechak, David and Alexiou, Panagiotis},
title = {miRBench: novel benchmark datasets for microRNA binding site prediction that mitigate against prevalent microRNA frequency class bias},
journal = {Bioinformatics},
year = {2025},
doi = {10.1093/bioinformatics/btaf233}
}
EUVIMED