Claude autonomously designs 17 protein binders against scorpion neurotoxins in 64 hours
Anthropic Research · rss · 2026-10-20
Anthropic reports that an internal research model running in Claude Science designed protein minibinders against five scorpion neurotoxins (Cn2, Ts1, AaH I, AaH II, LqhIII), working mainly autonomously for 64 hours with only four follow-up prompts. The campaign generated 318,484 designs; 211 were lab-tested by Adaptyv Bio and Twist Bioscience, and 17 successfully bound their targets, including multitoxin designs aimed at a universal antivenom cocktail.
- Motivation: scorpion envenomation affects 1.2M+ people yearly, killing 3,250+, mostly children; it's a neglected tropical disease with little commercial incentive, and traditional horse-immunization antivenoms are slow, costly, and narrow.
- External experts called it a promising first step, noting binder binding is no longer the bottleneck — the real challenge is turning binders into safe, affordable drugs.
- All 211 designs and data are being released openly. Anthropic does not claim a working antivenom yet.
More from Models
- Carbon-X DNA model slammed: worse than random on 8/10 clinical variant cases — anshulkundaje · 2026-10-23
- Rumor: Anthropic training a model matching OpenAI's internal one; big launches in December — imjustnewatai · 2026-10-23
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23
- Dream Labs emerges from stealth with Dream-1 robot foundation model at $3/hour — scott_e_reed · 2026-10-23
- Claude Models on Google Cloud (Anthropic managed) is now generally available — claudeai · 2026-10-23
- Beam vs GLM 5.3 Abliterated: 10-round attack/defense test shows 96% of vulns patched — bigblueboo · 2026-10-23