Workshop paper
Benchmarking Fine-Tuned RNA Language Models for Intronic Branch Point Prediction
* Equal contribution: Pablo Rodenas-Ruiz, Ali Saadat, Timothy T. Tran, Oliver Müller Smedt.
ICLR 2025 MLGenX Workshop (Tiny Papers track)
Abstract
Accurate prediction of RNA branch points is critical for understanding splicing mechanisms and identifying variants that may lead to genetic diseases. Despite their biological importance, few computational methods have been developed for reliably identifying branch points. In this work, we fine-tune several RNA language models for branch point prediction. The top-performing model, ERNIE-RNA, achieved an F1 score of 0.811, a sequence accuracy of 0.790, and an average precision score of 0.868, outperforming previous leading models. These results showcase the potential of RNA-specific language models in capturing the subtle sequence features relevant to splicing. Our findings suggest that extended training and hyperparameter tuning could yield additional performance gains, positioning this study as a strong baseline for future research in RNA splicing.
Keywords: RNA language models, branch point prediction, RNA splicing, model fine-tuning
Cite
Download .bib@inproceedings{rodenasruiz2025benchmarking,
title = {{Benchmarking Fine-Tuned RNA Language Models for Intronic Branch Point Prediction}},
author = {Rodenas-Ruiz, Pablo and Saadat, Ali and Tran, Timothy T. and Müller Smedt, Oliver and Zhang, Peng and Fellay, Jacques},
year = {2025},
booktitle = {ICLR 2025 MLGenX Workshop (Tiny Papers track)},
url = {https://openreview.net/forum?id=Q15Dg5lQou},
keywords = {RNA language models, branch point prediction, RNA splicing, model fine-tuning},
note = {Equal contribution: Pablo Rodenas-Ruiz, Ali Saadat, Timothy T. Tran, Oliver Müller Smedt.}
}