Anthropic's Claude Autonomously Designs Protein Mini-Binders Against Scorpion Neurotoxins
Start here
Anthropic ran an internal research version of Claude largely autonomously for 64 hours within its Claude Science program to design protein mini-binders targeting five scorpion neurotoxins. During the run, the model generated 318,484 candidate designs, from which 180 were selected for screening. The work demonstrates AI systems taking on an end-to-end role in protein design for biomedical applications. Where the screening stands — including any wet-lab validation results, binding affinities, or therapeutic implications — has not yet been reported, so the biological outcome of the selected designs remains open.
Written by a model from the reports · updated 15 min ago
Coverage timeline
Follow the coverage to see the different angles.
- anthropic.comPickAnthropic Uses Claude to Design Protein Mini-Binders Against Five Scorpion Neurotoxins
Anthropic ran an internal research model largely autonomously for 64 hours in Claude Science to design protein mini-binders against five scorpion neurotoxins. The model generated 318,484 designs in total and 180 were selected for screening. Original link: https://anthropic.com/research/claude-scorpion-toxin-binder-design
Coverage and heat for this story
Reports so far 1·Heat now 17·Peak heat 19 (Oct 21 20:00)·Reports, 24h +1
Two panels, same clock (pointer stays in sync): top is cumulative editorial reports — only rises; last point = All reports; slope = new reports that hour. Bottom is Live-board heatIndex — 7-day participants with a 24-hour half-life, so it can fall when talk cools.