Using Claude to generate MSAs with coevolution signal, then feeding them to AlphaFold
sim0nsays · x · 2026-11-20
A demo of an AI-for-Science trick: using Claude (jokingly dubbed "Fable 5.2") to generate protein multiple sequence alignments (MSAs) that show clear coevolution signal, which can then be fed into AlphaFold for structure prediction. Follow-up questions probe whether the model does this from memory or via reasoning, highlighting community interest in whether LLMs truly encode evolutionary information.
Related event: Developers use Claude-generated MSAs to power AlphaFold predictions(4 posts)→
More from Research
- Implementing DEFLATE Compression From Scratch in C, Following RFC 1951 — tetsuoai · 2026-11-20
- Recalling homologs with Fable 5.2 for de novo protein coevolution: Top7 hits 35% of top-L contacts — sokrypton · 2026-11-20
- A photonic chip plays Mario using a NEAT network trained for just 472 generations — CatAstro_Piyush · 2026-11-20
- Huawei Cuts Generative Recommendation Inference Latency up to 25x vs vLLM Without Custom Kernels — _reachsumit · 2026-11-20
- iWSP: LLM Agents Build Interpretable Neural Nets by Programming Weights Directly — kalyan_kpl · 2026-11-20
- Tencent's CONCORD-Rec Weights Each Modality by Reliability in Diffusion-Based Recommendation — _reachsumit · 2026-11-20