Skip to main content

# RNA sequence design

2 related articles

Subscribe to updates

researchsquare.com Nov 9, 2026
RNA design moves to discrete diffusion: structure-matched candidates without a folding oracle, and far more sequence variety
RNA inverse folding has long relied on iterative optimization scored by an external folding algorithm, which is sensitive to initialization and prone to local optima. This work defines multinomial diffusion directly over nucleotide sequences, guides denoising with a target secondary structure, and compares a 2D contact-map projection with a purely 1D pairing-aware architecture. On the in-distribution test set, the 2D and 1D models reach median normalized RNAforester similarities of 0.82 and 0.79, while generated sequences stay close to random-sequence diversity.
RNA inverse folding has long relied on iterative optimization scored by an external folding algorithm, which is sensitive to initialization and prone to local optima. This work defines multinomial diffusion directly over nucleotide sequences, guides denoising with a target secondary structure, and compares a 2D contact-map projection with a purely 1D pairing-aware architecture. On the in-distribution test set, the 2D and 1D models reach median normalized RNAforester similarities of 0.82 and 0.79, while generated sequences stay close to random-sequence diversity.
Weihenstephan-Triesdorf University of Applied Sciences Max Planck Society
Georg Back（First author, Corresponding author）
RNA Inverse Folding Multinomial Diffusion RNA sequence design
bioRxiv Sep 28, 2026
RNASeek uses a 1.6B-parameter cross-phyla transcriptomic model for RNA function prediction and GRPO-guided design, yielding ribozymes at wild-type activity and 3′ UTRs beyond the training data
The authors present RNASeek, a 1.6-billion-parameter generative foundation model built on a DeepSeek architecture and trained on a cross-phyla transcriptomic corpus, using natural-language tokens for conditional prediction and sequence design; it captures species-specific transcript features and intron–exon boundaries in a zero-shot setting, can be fine-tuned to predict ribozyme self-cleavage activity and viral mRNA stability while revealing interpretable features such as loop flexibility, stem stability, and AU-rich motifs, and these functional predictors then serve as reward models for GRPO updates to the generation policy, producing faster-cleaving ribozymes and stability-enhancing 3′ UTRs under user-specified IUPAC constraints, with experimentally validated generated ribozymes reaching
The authors present RNASeek, a 1.6-billion-parameter generative foundation model built on a DeepSeek architecture and trained on a cross-phyla transcriptomic corpus, using natural-language tokens for conditional prediction and sequence design; it captures species-specific transcript features and intron–exon boundaries in a zero-shot setting, can be fine-tuned to predict ribozyme self-cleavage activity and viral mRNA stability while revealing interpretable features such as loop flexibility, stem stability, and AU-rich motifs, and these functional predictors then serve as reward models for GRPO updates to the generation policy, producing faster-cleaving ribozymes and stability-enhancing 3′ UTRs under user-specified IUPAC constraints, with experimentally validated generated ribozymes reaching
Columbia University Irving Medical Center University of California, Riverside
Shiyuan Chen（First author）Joy S. Xiang（Corresponding author）
RNASeek RNA Foundation Models Group-Relative Policy Optimization RNA sequence design

You’re all caught up