Claude 自主设计蛋白结合剂，命中率约为人类两倍
This is interesting: Claude is already achieving roughly twice the protein-desig…
This is interesting: Claude is already achieving roughly twice the protein-design hit rate of conventional human-led workflows. 27% hit rate in autonomous protein binder design, roughly twice the typical 10–15% rate reported in the field.
这很有意思：Claude 在蛋白质设计命中率上已经达到传统人工工作流程的两倍左右。在自主蛋白质结合剂设计中，命中率为27%，大约是领域内通常报告的10-15%的两倍。
Working from one expert-written protocol, Claude designed binders against 14 of 15 measurable targets. Independent labs confirmed that 354 of 1,320 designs bound successfully.
基于一份专家编写的协议，Claude 针对14个可测量靶标中的15个设计了结合剂。独立实验室确认，1320个设计中354个成功结合。
Depending on the setup, Claude’s hit rate ranged from 22.6% to 35.1%. Its top-ranked design bound in 49% of campaigns.
根据设置不同，Claude 的命中率介于22.6%到35.1%之间。其排名最高的设计在49%的活动中成功结合。
This is not yet fully autonomous drug research, but it is another important building block in that direction.
这还不是完全自主的药物研究，但它是朝这个方向迈出的又一个重要基石。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力