LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · Claude蝎毒抗体研发Material2 min de lecturaEditorial de DisconfirmAI

Anthropic: Claude designs scorpion toxin binders, lab-validated

Anthropic reports that its model Claude designed protein binders against scorpion neurotoxins. Adaptyv Bio and Twist Bioscience lab-tested 211 designs, confirming 17 as effective binders. This demonstrates AI's potential to accelerate drug discovery for neglected diseases, though venom neutralization remains unconfirmed.

2026-10-20 08:00 GMT+8

US artificial intelligence company Anthropic published a research report on October 20, 2026, stating that its internal research model Claude successfully designed protein binders (minibinders) against scorpion neurotoxins. The initiative was developed in collaboration with financial investment research firm Citrini Research, aiming to explore whether AI could enable motivated non-experts to tackle genuine problems in human health.

Scorpion stings affect more than 1.2 million people globally each year, resulting in over 3,250 deaths, primarily in regions with limited medical access. Traditional antivenoms are slow to produce, expensive, and offer low commercial returns, leading to scorpion envenomation being classified as a neglected tropical disease. The Anthropic team used Claude to analyze structures of five scorpion neurotoxins from different regions and generated 318,484 candidate protein designs.

After filtering, the team submitted 211 designs to contract research organizations Adaptyv Bio and Twist Bioscience for experimental testing. Results showed that 17 of these designs successfully bound to their target toxins. These binders targeted four known dangerous scorpion neurotoxins. Notably, this outcome was not merely a computational simulation but was validated through independent wet-lab experiments.

Despite the progress, Anthropic explicitly stated that they have not confirmed whether these binders neutralize scorpion venom in a cellular environment, and therefore do not claim to have produced an antivenom. Two external experts—Susana Vázquez Torres, a Postdoctoral Researcher in Structural Biology at the Spanish National Cancer Research Centre (CNIO), and Timothy P. Jenkins—evaluated the work as a "promising first step."

Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

The core significance of this study lies in demonstrating a paradigm shift in AI-driven drug discovery: designing credible binders against multiple hard-to-target toxins in days, with laboratory confirmation within weeks. This offers a new speed advantage for developing therapies for neglected diseases such as snake bites and scorpion stings. However, significant challenges remain in translating these binders into safe, affordable, and widely accessible drugs.

Anthropic has released all 211 designs and their associated data as an open resource for the scientific community to further study and improve upon.

Fuentes

  • anthropic.com↗
Tema

Claude蝎毒抗体研发

美国人工智能公司 Anthropic 发布研究称,其模型 Claude 在 64 小时内设计了针对蝎子神经毒素的蛋白质结合体。在与投资研究机构 Citrini Research 合作下,团队筛选出 211 个候选分子,经 Adaptyv B…

3 pasos1 piezasActualizado 2026-10-21 11:53

Cómo llegó hasta aquí

  1. 2026-10-20Anthropic 发布博客与技术报告,宣布 Claude 设计了针对五种蝎毒神经毒素的蛋白质结合体,并公开全部 211 个设计数据。anthropic.com ↗
  2. 2026-10-20Hunterbrook 媒体披露调查细节,指出该研究由 Citrini Research 发起,旨在测试非专家利用 AI 解决公共卫生问题的能力,并强调了生物安全限制下的模型表现。hntrbrk.com ↗
  3. 2026-10-21多家中文科技媒体(如机器之心、新浪科技)转载报道,详细解读了 17 个成功结合体的具体分布(如 Cn2-B1/B2 的高亲和力)及未通过多毒素通用设计的局限。news.marsbit.co ↗

Lo que aún está pendiente

  • 这些 AI 设计的结合体能否在细胞或动物实验中证明具有真正的毒素中和能力?
  • AI 生成的低成本蛋白质方案如何克服传统抗毒血清的生产与分发瓶颈,实现大规模可及性?
  • 针对单一毒素的成功率(约 18%)是否足以支撑开发覆盖多种蝎毒的广谱抗毒制剂?
Leer el tema completo →
Continuar investigando →