Riley Aidan T, Robson James M, Ulanova Aiganysh, Green Alexander A
Department of Biomedical Engineering, Boston University, Boston, MA, USA.
Biological Design Center, Boston University, Boston, MA, USA.
Nat Commun. 2025 May 4;16(1):4155. doi: 10.1038/s41467-025-59389-8.
RNA is a remarkably versatile molecule that has been engineered for applications in therapeutics, diagnostics, and in vivo information-processing systems. However, the complex relationship between the sequence, structure, and function of RNA often necessitates extensive experimental screening of candidate sequences. Here we present a generalized, efficient neural network architecture that utilizes the sequence and structure of RNA molecules (SANDSTORM) to inform functional predictions across a diverse range of settings. We pair these predictive models with generative adversarial RNA design networks (GARDN), allowing the generative modelling of a diverse range of functional RNA molecules with targeted experimental attributes. This approach enables the design of novel sequence candidates that outperform those encountered during training or returned by classical thermodynamic algorithms, and can be deployed using as few as 384 example sequences. SANDSTORM and GARDN thus represent powerful new predictive and generative tools for the development of RNA molecules with improved function.
RNA是一种用途极为广泛的分子，已被设计用于治疗、诊断及体内信息处理系统。然而，RNA的序列、结构和功能之间的复杂关系常常需要对候选序列进行广泛的实验筛选。在此，我们展示了一种通用、高效的神经网络架构，该架构利用RNA分子的序列和结构（SANDSTORM）来进行各种情况下的功能预测。我们将这些预测模型与生成对抗RNA设计网络（GARDN）相结合，从而能够生成具有特定实验属性的各种功能性RNA分子。这种方法能够设计出优于训练过程中遇到的或经典热力学算法返回的新型序列候选物，并且仅需使用384个示例序列即可进行部署。因此，SANDSTORM和GARDN代表了用于开发功能改进的RNA分子的强大新型预测和生成工具。
