LLM predicts ubiquitin's protein fold from sequence alone via a clever contact-map prompt
sokrypton · x · 2026-11-18
X user sokrypton shows that a relatively simple prompt combining dynamic programming and linear algebra lets an LLM return a protein's 3D structure from its sequence alone by predicting residue-residue contacts — and ubiquitin's fold came out reasonably correct. The prompt rules force the model to reason only from the sequence: infer secondary structure from 3/14 periodicity and amphipathic patterns, then predict C-beta contacts within 8 Å, build a 3D model from them, inspect and revise. The output visibly matches the real ubiquitin structure (1UBQ, 76 residues) rendered in 2Dmol.
More from coding & agent
- Azure launches App Service Builder public preview: code-first, agent-ready hosting — adnan_hashmi · 2026-11-18
- NVIDIA open-sources Auto Ontology, a semantic graph reasoning layer for LLM agents — adnan_hashmi · 2026-11-18
- AI made writing code faster — did the bottleneck just move to code review? — djgoel123 · 2026-11-18
- Open-source MCP server connects Claude to Lychee Redmine project management — modelcontextprotocol · 2026-11-18
- Pharma Intel MCP chains ClinicalTrials.gov tools for AI pharma research — modelcontextprotocol · 2026-11-18
- Indie dev: skip GPT-6.2 hype, what I want is a better Antigravity harness — yihui_indie · 2026-11-18