Pascal Notin
Research in AI for Protein Design @Harvard | Prev. CS PhD @UniofOxford, Maths & Physics @Polytechnique
- 🚨 New paper 🚨 RNA modeling just got its own Gym! 🏋️ Introducing RNAGym, large-scale benchmarks for RNA fitness and structure prediction. 🧵 1/9
- 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
- RNAGym tackles three essential RNA prediction tasks: 🔬 Fitness prediction: How mutations affect RNA function 🔗 Secondary structure: Base-pairing patterns 🌀 Tertiary structure: 3D molecular architecture All evaluated zero-shot to test true generalization! 3/9
-
View full threadLinks: 🔗 Paper: www.biorxiv.org/content/10.1... 💻 Code: github.com/MarksLab-Das... 9/9
- Reposted by Pascal NotinEnd-to-end differentiable homology search for protein fitness prediction. @yaringal.bsky.social @deboramarks.bsky.social @pascalnotin.bsky.social arxiv.org/abs/2506.089...
- Reposted by Pascal NotinPascal Notin at #VariantEffect25
- Have we hit a "scaling wall" for protein language models? 🤔 Our latest ProteinGym v1.3 release suggests that for zero-shot fitness prediction, simply making pLMs bigger isn't better beyond 1-4B parameters. The winning strategy? Combining MSAs & structure in multimodal models!
- Even simple methods leveraging these 2 modalities significantly outperform billion-parameter sequence-only models. So, what's next? Better retrieval, advanced multimodal approaches, & alignment. Read more: pascalnotin.substack.com/p/have-we-hi... #BioTech #AI #pLMs
