Claude Fable 5.2 correctly predicts de novo protein contacts from sequence alone
sokrypton · x · 2026-11-18
researcher sokrypton prompted Claude Fable 5.2 to predict, from a 68-residue protein sequence alone, which residue pairs are in contact (C-beta within 8Å, sequence separation ≥6), returning the top 128 pairs as a contact map.
Comparing against the true contact map of 6MRR chain A (91 pairs), the model's predictions align closely with the experimental structure, including the banded contacts typical of beta-sheet regions.
The demo suggests LLMs can infer structural contact information directly from sequence without retrieval or specialized protein tools — a striking display of implicit scientific knowledge.
More from Models
- Asking Gemini 10,701 questions: Google Search rewrites ~45% of brand picks — dejanseo · 2026-11-18
- Cursor's CursorBench 4.0: Gemini 4 Carbon tops at 60.4%, DeepSeek under $1 per task — mattyp · 2026-11-18
- Salesforce's SOV-Transcribe-1 ASR model trends on Hugging Face — salesforce-sovereign-intelligence · 2026-11-18
- OpenAI explains the 6.2 influencer/community vibe gap: demo videos used pre-release models — i_dg23 · 2026-11-18
- Ruff author Charlie Marsh: GPT-6.2 was an enormous step-up for my work — charliermarsh · 2026-11-18
- Claude Code ignored an explicit rule and invented timestamps 4 hours ahead — shymecw · 2026-11-18