深度生成模型设计的mRNA序列具有增强的翻译能力和稳定性
该研究团队提出了GEMORNA，这是一种生成式RNA模型，利用针对mRNA编码序列（CDSs）和非翻译区（UTRs）量身定制的Transformer架构来设计具有增强表达和稳定性的新型mRNA。与体外优化的基准相比，GEMORNA设计的全长mRNA在萤火虫荧光素酶表达上增加了41倍。GEMORNA产生的治疗性mRNA使人促红细胞生成素（EPO）表达提高了15倍，并在小鼠中显著提高了COVID疫苗的抗体滴度。此外，GEMORNA的多功能性扩展到环状RNA，显著增强环状EPO表达并增强CAR-T细胞的抗肿瘤细胞毒性。这些进展凸显了深度生成人工智能在mRNA治疗方面的巨大潜力。
据悉，尽管mRNA COVID-19疫苗取得了成功，但将这种模式扩展到更多疾病需要大量改进。
附：英文原文
Title: Deep generative models design mRNA sequences with enhanced translational capacity and stability
Author: He Zhang, Hailong Liu, Yushan Xu, Haoran Huang, Yiming Liu, Jia Wang, Yan Qin, Haiyan Wang, Lili Ma, Zhiyuan Xun, Xuzhuang Hou, Timothy K. Lu, Jicong Cao
Issue&Volume: 2025-08-28
Abstract: Despite the success of mRNA COVID-19 vaccines, extending this modality to more diseases necessitates substantial enhancements. We present GEMORNA, a generative RNA model that utilizes Transformer architectures tailored for mRNA coding sequences (CDSs) and untranslated regions (UTRs), to design novel mRNAs with enhanced expression and stability. GEMORNA-designed full-length mRNAs exhibited up to a 41-fold increase in firefly luciferase expression compared to an optimized benchmark in vitro. GEMORNA-generated therapeutic mRNAs achieved up to a 15-fold enhancement in human erythropoietin (EPO) expression and substantially elicited antibody titers of COVID vaccine in mice. Additionally, GEMORNA’s versatility extends to circular RNA, substantially enhancing circular EPO expression and boosting anti-tumor cytotoxicity in CAR-T cells. These advancements highlight deep generative AI’s vast potential for mRNA therapeutics.
DOI: adr8470
Source: https://www.science.org/doi/10.1126/science.adr8470