Researchers develop ProMORNA for de novo mRNA design from protein sequences

Researchers have developed ProMORNA, a novel framework for designing therapeutic messenger RNA (mRNA) sequences. This system uses a BART-style encoder-decoder model trained on millions of protein-mRNA pairs and employs multi-objective reinforcement learning to optimize for stability, translation efficiency, and immune safety simultaneously. ProMORNA demonstrated improved performance in silico for predicting half-life and translation efficiency on an unseen target, outperforming existing supervised methods. AI

影响 Introduces a new ML-driven approach for designing complex biological molecules, potentially accelerating therapeutic development.

排序理由 Academic paper detailing a new method for mRNA design using machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

• BART
• firefly luciferase
• ProMORNA

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →