Gradient-based optimization for mRNA sequence design
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag667 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Hongmin Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, …. Hauptthemen laut MEDLINE: RNA, Messenger, Computational Biology, Software, Sequence Analysis, RNA. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science (JSPS) KAKENHI, Japan Science and Technology Agency (JST) CREST, Google Asia Pacific Pte. Ltd..
Abstract (Originalsprache)
Motivation Designing mRNA coding sequences that simultaneously optimize RNA accessibility in the translation initiation region and codon adaptation while preserving the encoded protein requires navigating a vast discrete combinatorial space. The inherently discrete nature of codon choices prevents direct application of gradient-based optimization, despite the availability of accurate deep learning predictors such as DeepRaccess for RNA accessibility prediction. Results We present the Input Data Differentiable Designer (ID3), a unified framework for mRNA codon optimization. ID3 treats trained models as fixed differentiable functions and optimizes input data through continuous probability distributions while preserving the encoded amino acid sequence through three constraint mechanisms. The framework shows strong performance in both accessibility optimization and joint accessibility-CAI optimization across diverse protein targets. We also provide convergence analyses from the perspective of trained model input optimization. Availability and implementation Code, datasets, and reproduction scripts are available at https://github.com/Li-Hongmin/ID3.git and archived on Zenodo (DOI: 10.5281/zenodo.18917770).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba, 277-8561, Japan.
- School of Life Science and Technology, Institute of Science Tokyo, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8550, Japan.
- AI-Empowered Life Science Initiative (ALIS), Research Organization of Information and Systems (ROIS), 4-1-1 Toranomon, Tokyo, 105-6929, Japan.
ORCID-Profile: Hongmin Li, Goro Terai, Takumi Otagaki, Kiyoshi Asai
Förderung
- Japan Society for the Promotion of Science (JSPS) KAKENHI
- Japan Science and Technology Agency (JST) CREST
- Google Asia Pacific Pte. Ltd.
Zitieren
APA
Li, H., Terai, G., Otagaki, T., & Asai, K. (2026). Gradient-based optimization for mRNA sequence design. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag667
Vancouver
Li H, Terai G, Otagaki T, Asai K. Gradient-based optimization for mRNA sequence design. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag667
BibTeX
@article{Li2026,
author = {Li, Hongmin and Terai, Goro and Otagaki, Takumi and Asai, Kiyoshi},
title = {Gradient-based optimization for mRNA sequence design},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag667}
}
EUVIMED