RNA-X: Modeling RNA interactions to design binder RNA and simultaneously target multiple molecules of different types

Abstract

RNA interactions with proteins, other RNA molecules, and DNA play essential roles in numerous cellular processes and underpin a wide range of therapeutic mechanisms. Consequently, modeling these interactions is critical for understanding biological systems and designing novel RNA-based therapeutics. However, designing RNA sequences that selectively and strongly bind to a specific target remains a major challenge due to the vast sequence space and the current limitations of experimental and computational methods. In this study, we introduce RNA-X, the first RNA interaction foundation model which is based on masked language modeling for representation learning, conditional RNA design, and optimization. For the first time, RNA-X enables (i) RNA design targeting not only proteins but also other RNA and DNA molecules, and (ii) simultaneous design against multiple targets. Our extensive experiments demonstrate that RNA-X generates RNA sequences with natural structural characteristics and surpasses state-of-the-art methods in protein targeting. We experimentally validate RNA-X in vitro, where a RNAX-designed RNA targeting the 5'UTR of the androgen receptor (AR) mRNA was shown to reduce both AR transcript and protein levels in prostate cancer cells. Using affinity predictors and molecular dynamics simulations, we further show that the model can design RNA molecules that (i) target therapeutically relevant molecules such as p53 and thrombin proteins, and (ii) bind to targets with no prior interaction data, such as PHF6 protein. As a proof of concept, we designed a novel guide RNA from scratch that simultaneously binds (i) to the DNA of a bacterium and (ii) to the Cas9 protein. The resulting design achieves a predicted binding energy comparable to that of the wild-type guide RNA reported in the Protein Data Bank. Despite having orders of magnitude fewer parameters than existing RNA foundation models, RNA-X produces representations that outperform them across diverse RNA interaction-related downstream tasks. The code and pretrained model are publicly available on GitHub.