创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

Claude展现蛋白质序列预测能力

AI 总结

研究人员报告称,Claude Fable 5.2和Claude Opus 5.5预测低研究度细菌和古菌蛋白质中氨基酸顺序的能力优于其他受测前沿模型。Fable 5.2对真实序列的下一个氨基酸预测准确率为54%,打乱序列后降至9%,并超过研究者评估的所有开放蛋白质语言模型。Opus 5.5对真实序列的准确率为34.9%,打乱后为7.5%;按序列顺序带来的准确率差值比较,它与ProtGPT3-10B相当。Anthropic官方介绍未说明训练数据,因此“这些模型使用了大规模蛋白质序列训练”仍是根据表现作出的推断,而非已确认事实。

深度见解

结果表明,Fable 5.2可能具备针对特定蛋白质序列的生物学知识,并超过专门的开放蛋白质语言模型。这也引发了对前沿模型训练数据构成的疑问,但Anthropic尚未证实这一解释。

The latest Claude models were trained on protein sequences, at scale. Give Claude Fable 5.2 or Claude Opus 5.5 the start of a little-studied bacterial protein and they predict the next amino acid. Shuffle the protein and they can’t. No other model we tested can do this. Like a protein language model, they do better on bigger protein families, and they do it even in families with no papers at all. Fable 5.2 beats every open protein language model we ran, and Opus 5.5 is level with ProtGPT3-10B, the largest of them.

Update, 18 November 2026. Since the first version:

  • Proteins published after the training cutoff. With Leo Tianlai Chen, 56 proteins first made public in August 2026, with no earlier relative at 50% identity or more. The latest Claude models still predict them (Appendix G).
  • More protein language models. ProGen3-3B is the strongest open one we ran, and Fable 5.2 still beats it; Prot-xLSTM is in Appendix C.
  • More GPT models. GPT-6.2 Sol and Astra show no sign of it either.

Motivation

Frontier LLMs have started to look good at protein tasks. Atharv Jayprakash showed GPT-6 Astra ranking SOD1 variants as well as ESM-2, and PG-LLM found the same across many proteins. Did these models learn from protein sequence databases such as UniProt, or from what is written about proteins?

#Anthropic#Claude Fable 5.2#Claude Opus 5.5#UniProt#ProGen3-3B#ProtGPT3-10B#ESM-2#GPT-6.2 Sol#Gemini 4 Carbon

原文约 15 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。