Keywords: RNA, RNA Design, RNA Inverse Folding, Transformers, Generative Design, Axial Attention, pseduoknots, multiplets
Abstract: The function of an RNA molecule depends on its structure and a strong structure-to-function relationship is already achieved on the secondary structure level of RNA. Therefore, the secondary structure based design of RNAs is one of the major challenges in computational biology. A common approach of RNA design is inverse RNA folding. However, existing RNA design approaches cannot invert all folding algorithms because they cannot represent all types of base interactions. In this work, we propose RNAinformer, a novel generative transformer based approach to the inverse RNA folding problem. Leveraging axial-attention, we directly model the secondary structure input represented as an adjacency matrix in a 2D latent space, which allows us to invert all existing secondary structure prediction algorithms. Consequently, RNAinformer is the first model capable of designing RNAs from secondary structures with all base interactions, including non-canonical base pairs and tertiary interactions like pseudoknots and base multiplets. We demonstrate RNAinformer’s state-of-the-art performance across different RNA design benchmarks and showcase its novelty by inverting different RNA secondary structure prediction algorithms.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4342
Loading