Citrini Research uses internal Anthropic Claude model to design scorpion toxin binders
Investment research firm Citrini Research collaborated with Anthropic to autonomously design protein minibinders targeting scorpion neurotoxins, resulting in 17 lab-confirmed binding designs.
Investment research firm Citrini Research teamed up with AI developer Anthropic to test whether an unreleased bio-research model could autonomously design functional proteins for a scorpion antivenom. Citrini spent three months and $200,000 using the Claude model to engineer proteins, according to Quartz. Following the project's laboratory results, the hedge fund is now purchasing biotechnology stocks.[6][5][2]
Anthropic granted Citrini access to its internal Claude research model to generate protein minibinders targeting scorpion neurotoxins. Armed with a starting prompt, follow-up directions, and specialized tools, the model generated 300 sub-agents and autonomously ran a design campaign. Over roughly 64 hours, Claude evaluated docking targets, produced more than 318,000 protein candidates, and determined which designs warranted physical experimentation.[1][2][3][4]
Physical laboratories evaluated 211 candidate proteins, including options added with human assistance. The testing confirmed that 17 designed proteins successfully attached to target molecules, with binders acting across four toxins. Anthropic framed the collaboration as a continuation of its protein engineering work, noting it had demonstrated Claude designing protein minibinders from a single prompt in August.[1][2][3][4][6]
Key facts
- Citrini Research spent three months and $200,000 using Anthropic's Claude to design proteins targeting scorpion toxins.
- Citrini Research is buying biotech stocks following the protein design experiment, according to Quartz.
- Anthropic provided Citrini with access to an unreleased internal bio-research model to design novel proteins for a scorpion antivenom.
- Claude generated more than 318,000 protein candidates in 64 hours, spawned 300 sub-agents, and coordinated specialized research tools.
- Laboratories tested 211 candidate protein designs against scorpion neurotoxins.
- Seventeen tested protein candidates successfully bound to target toxins in physical lab experiments.
Sources · 6 sources
- TE
Techmeme@TechmemePost on X ·
Anthropic and Citrini Research use an internal Claude model to autonomously generate protein minibinders against five scorpion neurotoxins, testing 211 designs (Anthropic) (Visit Techmeme dot com for the link and full context!)
Open source - AC
Andrew Curran@AndrewCurran_Post on X ·
Anthropic gave Citrini access to an unreleased internal bio-research model. Using a 35-page prompt, Claude generated 300 sub-agents and autonomously ran a design campaign, generating 318k candidates and selecting 211 for testing. 17 designs bound across four toxins. https://t.co/nBaTJKq0ma
Open source - CH
Chubby♨️@kimmonismusPost on X ·
Anthropic’s internal Claude research model carried out much of a research project on its own, with results confirmed in the lab. This is the beginning of autonomous AI scientists making their own discoveries. Given a starting prompt and four follow-ups, Claude used specialized tools to generate more than 318,000 protein designs in 64 hours. It chose where they should attach to scorpion toxins and selected candidates for testing. Labs tested 211 candidates, including additions made with human help. Seventeen successfully attached to their target toxins. These are "binders", small proteins that latch onto another molecule. Claude handled a substantial stretch of research: choosing an approach, coordinating tools and deciding what deserved a physical experiment. From here on it only gets more autonomous. I am so excited!
Open source - TE
TechmemeArticle ·
Anthropic and Citrini Research use an internal Claude model to autonomously generate protein minibinders against five scorpion neurotoxins, testing 211 designs (Anthropic) Anthropic : Anthropic and Citrini Research use an internal Claude model to autonomously generate protein minibinders against five scorpion neurotoxins, testing 211 designs — In August, we showed how Claude designed protein minibinders after being given a single prompt.
Open source - MT
MTS@MTSlivePost on X ·
SITUATION DETECTED: Investment research firm Citrini Research used an internal unreleased research model from Anthropic to autonomously design novel proteins for a scorpion antivenom.
Open source - QU
Quartz@qzPost on X ·
A hedge fund used Claude to design proteins — now it's buying biotech stocks Citrini Research spent three months and $200K using Anthropic's AI to design proteins targeting scorpion toxins, and 17 of them actually bound to their targets. #AIBiology #LifeSciences #ProteinDesign https://t.co/NJnmtVWraC
Open source