Designing IL-36 miniprotein binders in a day with Codex and a few dollars of GPU
CatAstro_Piyush · x · 2026-11-13
Nathan Lambert walked through computationally designing miniprotein binders against IL-36 using Codex, in roughly a day's work with a few dollars of Runpod GPU compute.
Key steps:
- Generation with RFD4-Proteina: 8 matched seeds, 16 successful beam searches (60 steps, beam width 2), 74 distinct structures after deduplication
- Selection with Boltz2 predictions, ESMFold, and Protein-Sol for developability optimization
- Detecting and mitigating reward-hacking of the design function
His point: the impressive part isn't the result, it's that AI agents can now run a full computational protein-design pipeline at near-zero cost — AI for Science workflows are becoming accessible to individuals.
More from coding & agent
- Armin Ronacher: I started 141 projects in a year, but only maintain 10-15 — TheTuringPost · 2026-11-13
- One prompt spawns a 1M-nanobot GPU swarm that morphs into any shape at 60fps — bennash · 2026-11-13
- Dev shares personal agent stack: Hermes + open-source Hermex iOS client — _ScottCondron · 2026-11-13
- Anthropic launches self-hosted Claude Managed Agents in private beta for on-prem deployment — ClaudeDevs · 2026-11-13
- DeepSeek V4 Pro agent sets up a full Hive lab in VMware in about half an hour — huangyun_122 · 2026-11-13
- Benchmark Router launches to run public LLM benchmarks on any model at 1/10th the cost — ycombinator · 2026-11-13