Generative and predictive neural networks for the design of functional RNA molecules
Aidan T. Riley, James Robson, Aiganysh Ulanova, Alexander A. Green
Abstract
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. Designing high performance RNA molecules is a unifying challenge across many areas of biotechnology research. Here, authors develop GARDN and SANDSTORM, a data-efficient generative AI framework for designing a diverse set of RNA molecules. These tools represent a promising addition to the sequence design toolkit that could be used in many domains.