ProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design
Abstract
Designing therapeutic messenger RNA (mRNA) requires generating full-length transcripts that optimally balance intracellular stability and translation efficiency. While generative models have advanced mRNA design, existing approaches rely on region-wise generation, expensive inference-time search, or target-specific model updates. To overcome these limitations, we introduce ProMORNA, a zero-shot, end-to-end generative framework for full-length mRNA design. ProMORNA aligns the design process with modern Large Language Model training pipelines: it utilizes a BART-style architecture pre-trained on over 6 million natural protein-mRNA pairs, followed by a two-stage post-training process comprising cold-start supervised fine-tuning and multi-objective reinforcement learning. By standardizing and aggregating relative advantages at the individual metric level with domain-specific stabilization, our post-training stage directly aligns the generative policy with conflicting biological constraints while avoiding direct scalarization of raw objective scores. In silico evaluations demonstrate that ProMORNA pushes the Pareto frontier of predicted stability and translation efficiency beyond standard baselines and GEMORNA, a leading state-of-the-art method. In three independent in vitro Fluc2P experiments, Candidate 2 achieved a 12-72h reporter-activity AUC 3.33 times that of the conventional Benchmark (Holm-adjusted P=0.01285), while its estimated 1.29-fold advantage over the reported best GEMORNA candidate remained exploratory. These results support ProMORNA as a promising framework for generating functionally active full-length mRNA candidates.
Related
- Design of full-length agonist and antagonist antibodies for hard targets
- GenAI-Net: A generative AI framework for automated biomolecular network design
- Dimeric granzyme-A mediates the specific recognition and cleavage of full-length GSDMB
- Human NHE1 binds full-length calcineurin with high affinity and inhibits substrate dephosphorylation
- Neuronal lipid composition regulates distinct states of full-length tau assembly, mechanics and membrane interactions
BibTeX
@misc{shao2026promorna,
title = {{ProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design}},
author = {Zixi Shao and Tao Wang and Ye Shen and Tianyi Huang and Yibei Xiao},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.01513},
eprint = {2605.01513},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.01513},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ProMORNA: An End-to-End Generative Framework for Full-Length mRNA Design
AU - Zixi Shao
AU - Tao Wang
AU - Ye Shen
AU - Tianyi Huang
AU - Yibei Xiao
PY - 2026
DA - 2026/10/21
PB - arXiv
DO - 10.48550/arxiv.2605.01513
UR - https://arxiv.org/abs/2605.01513
AB - Designing therapeutic messenger RNA (mRNA) requires generating full-length transcripts that optimally balance intracellular stability and translation efficiency. While generative models have advanced mRNA design, existing approaches rely on region-wise generation, expensive inference-time search, or target-specific model updates. To overcome these limitations, we introduce ProMORNA, a zero-shot, end-to-end generative framework for full-length mRNA design. ProMORNA aligns the design process with modern Large Language Model training pipelines: it utilizes a BART-style architecture pre-trained on over 6 million natural protein-mRNA pairs, followed by a two-stage post-training process comprising cold-start supervised fine-tuning and multi-objective reinforcement learning. By standardizing and aggregating relative advantages at the individual metric level with domain-specific stabilization, our post-training stage directly aligns the generative policy with conflicting biological constraints while avoiding direct scalarization of raw objective scores. In silico evaluations demonstrate that ProMORNA pushes the Pareto frontier of predicted stability and translation efficiency beyond standard baselines and GEMORNA, a leading state-of-the-art method. In three independent in vitro Fluc2P experiments, Candidate 2 achieved a 12-72h reporter-activity AUC 3.33 times that of the conventional Benchmark (Holm-adjusted P=0.01285), while its estimated 1.29-fold advantage over the reported best GEMORNA candidate remained exploratory. These results support ProMORNA as a promising framework for generating functionally active full-length mRNA candidates.
ER -