The moderate performance across all tasks reveals exciting opportunities! Key directions: RNA-specific training data, integrating structure-function relationships, and improving non-canonical base pair prediction. RNAGym provides the standardized foundation for progress.
7/9
I'm excited to announce some major updates to our ProteinEBM paper with Chenxi Ou @sokrypton.org!
Pascal Notin
RNAGym tackles three essential RNA prediction tasks: ๐ฌ Fitness prediction: How mutations affect RNA function ๐ Secondary structure: Base-pairing patterns ๐ Tertiary structure: 3D molecular architecture
All evaluated zero-shot to test true generalization!
3/9
Why do we need this? RNA modeling faces major challenges: limited experimental data (<1% of PDB entries), inherently less stable structures than proteins, and evaluation has been scattered across different studies with varying approaches.
2/9
๐จ New paper ๐จ RNA modeling just got its own Gym! ๐๏ธ Introducing RNAGym, large-scale benchmarks for RNA fitness and structure prediction.
๐งต 1/9
๐ Secondary structure: 901k chemical mapping profiles using DMS & 2A3 reactivity. EternaFold achieves top performance (0.656 F1-score), closely followed by CONTRAfold & Vienna. Traditional thermodynamic methods are still competitive with newer deep learning approaches
5/9
Pascal Notin
๐ Tertiary structure: 215 diverse 3D structures from the PDB. NuFold leads monomers (0.393 TM-score), AlphaFold3 dominates complexes (0.381 TM-score). Non-Watson-Crick interactions remain a major challenge for all methods
6/9
Congratulations to the entire RNAGym team @rohitarorayyc.bsky.social @murfalo.bsky.social @christianchoe.bsky.social @cshearer.bsky.social Aaron Kollasch, Fiona Qu, Ruben Weitzman, Artem Gazizov, @sarahgurev.bsky.social Erik Xie @deboramarks.bsky.social
8/9
๐ฌ Fitness prediction: 70 assays across tRNA, ribozymes, aptamers & mRNAs (1M+ mutations total). Evo 2 performs best overall (0.276), but performance varies dramatically by RNA type: RNA-FM excels at tRNA/aptamers while Evo 2 leads mRNA tasks. Lots of room for improvement across the board!
4/9