What changed
Anthropic's Claude largely autonomously designed protein binders targeting scorpion neurotoxins, which kill more than 3,250 people every year. These small protein molecules are shaped to latch onto a specific target molecule. Claude generated 318,484 designs for such protein binders targeting five toxins from four scorpion species. After an initial prompt, Claude worked on its own for 24 hours. The research team then steered the work with additional instructions. Claude picked 180 candidates, and the team added 31 more. Of the 211 designs tested in the lab, 17 met the criteria for a binder. The two strongest bound extremely tightly to Cn2, a toxin from the Mexican scorpion. Lab tests suggest they dock at or near the same site as an antibody known to neutralize Cn2 in mice. Whether they actually work as an antivenom hasn't been tested yet.
What this means in practice
The research team used Claude Science, Anthropic's AI environment for researchers, to generate and refine the protein binder designs. The AI's ability to autonomously create and evaluate a large number of designs highlights its potential for drug discovery and toxin neutralization. External experts Susana Vázquez Torres and Timothy P. Jenkins called the work a promising first step. Two independent labs confirmed the results. In an earlier study, Claude had already designed mini-binders against 14 of 15 target proteins, with hit rates of 22 to 35 percent compared to the typical 10 to 15 percent.
Limitations and availability
The supplied announcement does not specify whether the protein binders are available for use as antivenom or in further clinical trials. The research team has not tested whether the binders work as an antivenom. The work remains in the laboratory phase, with further testing required before potential medical applications can be explored.
