EukaUTR: a foundation model for functional modelling and design of eukaryotic 3' UTRs
- 1Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, 310018, Zhejiang, China
Abstract
Eukaryotic mRNA 3' UTRs encode regulatory information that shapes post-transcriptional control, RNA fate and gene expression. However, a 3' UTR-specific foundation model that spans broad eukaryotic sequence diversity while supporting both functional prediction and sequence design is lacking. Here we present EukaUTR, a 3' UTR-specific foundation model trained on a large-scale eukaryotic 3' UTR sequence corpus spanning diverse evolutionary lineages. Across 13 prediction tasks spanning post-transcriptional regulation, RNA fate and expression output, EukaUTR models matched or exceeded the strongest external baselines on nearly all tasks, with relative improvements of up to 27.45%. EukaUTR also generated de novo 3' UTRs with natural-like sequence and regulatory properties. EukaUTR-Guide further derived stability-associated signals from small sequence sets to guide editing towards enhanced predicted stability. Together, EukaUTR provides a sequence-to-function-to-design framework for transferable 3' UTR modelling and design.
Related
- A foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies
- Genomic foundation models do not yet boost common variant discovery beyond standard functional annotations
- RNASeek: A Cross-Phyla Generative Foundation Model for Multipurpose RNA Modeling and Reinforcement Learning-Based Design
- A modelling challenge to improve preparedness for highly pathogenicavian influenza epidemics: objectives, design and synthetic datageneration
- AnewDDE: An Agentic Drug Discovery Engine for Biomolecular Interaction Modelling and Closed-Loop Design
BibTeX
@misc{lang2026eukautr,
title = {{EukaUTR: a foundation model for functional modelling and design of eukaryotic 3' UTRs}},
author = {M. lang and X. Fang and M. Chen and Z. Wang and Z. Cheng and X. Zhu and K. Y. Tam and J. Zhang and X. Li},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.07.749809},
url = {https://www.biorxiv.org/content/10.64898/2026.09.07.749809v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - EukaUTR: a foundation model for functional modelling and design of eukaryotic 3' UTRs
AU - M. lang
AU - X. Fang
AU - M. Chen
AU - Z. Wang
AU - Z. Cheng
AU - X. Zhu
AU - K. Y. Tam
AU - J. Zhang
AU - X. Li
PY - 2026
DA - 2026/09/07
PB - bioRxiv
DO - 10.64898/2026.09.07.749809
UR - https://www.biorxiv.org/content/10.64898/2026.09.07.749809v1
AB - Eukaryotic mRNA 3' UTRs encode regulatory information that shapes post-transcriptional control, RNA fate and gene expression. However, a 3' UTR-specific foundation model that spans broad eukaryotic sequence diversity while supporting both functional prediction and sequence design is lacking. Here we present EukaUTR, a 3' UTR-specific foundation model trained on a large-scale eukaryotic 3' UTR sequence corpus spanning diverse evolutionary lineages. Across 13 prediction tasks spanning post-transcriptional regulation, RNA fate and expression output, EukaUTR models matched or exceeded the strongest external baselines on nearly all tasks, with relative improvements of up to 27.45%. EukaUTR also generated de novo 3' UTRs with natural-like sequence and regulatory properties. EukaUTR-Guide further derived stability-associated signals from small sequence sets to guide editing towards enhanced predicted stability. Together, EukaUTR provides a sequence-to-function-to-design framework for transferable 3' UTR modelling and design.
ER -