Claude designed protein binders against scorpion neurotoxins
What happened
Anthropic asked an internal Claude model to design minibinders—small proteins that tightly attach—to scorpion neurotoxins, collaborating with Citrini Research. Over 64 hours Claude generated 318,484 designs, selected 180 for testing, and with team input added 31 more, totaling 211 designs that were lab‑tested by Adaptyv Bio and Twist Bioscience. Seventeen designs met the criteria for binding to four dangerous scorpion neurotoxins, though neutralization in cells was not yet confirmed. The full set of designs and data have been released as a resource for the field.
Why it matters
If AI can quickly produce protein binders for hard‑to‑target toxins, it could speed the search for treatments for neglected diseases like scorpion envenomation. Faster discovery may eventually lead to more affordable antivenoms for people in low‑resource regions.
Reality check
An automated, sceptical read of the sourceIncremental. The work shows AI can aid protein‑binder design faster than traditional methods, but it still requires experimental validation and does not yet deliver a finished therapy.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Anthropic
Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-FreeAnthropic · 14 Nov 2026Claude designed FPGA scaler board for 6th-gen consolesAnthropic · 13 Nov 2026I asked Claude Fable 5.2 to turn my site into a 90s Silicon Graphics workstationAnthropic · 13 Nov 2026Anthropic is endorsing SB 53Anthropic · 13 Nov 2026Understanding and addressing AI harmsAnthropic · 13 Nov 2026This page was collected from anthropic.com and summarised automatically by AIPulsee's pipeline. See how it runs.