用精心标注的药物资产库，让AI发现新药的速度快3.2倍
Curated AI beats frontier LLMs at pharma asset discovery
- 用结构化药物资产数据替代通用网络搜索
- 每查询发现药物数量是顶尖模型的3.2倍，且全对无漏
- 适合医药研发人员快速定位长尾管线中的候选药
通用大模型结合网络搜索正被用于挖掘制药管线的竞争格局。我们对比了戈塞特（Gosset）——一个基于聊天界面、内置靶点、作用方式和适应症级药物资产标注的AI平台——与四种前沿系统（Claude Opus 4.7、GPT 5.5、Gemini 3.1 Pro、Perplexity sonar-pro）在十个人类罕见肿瘤/免疫学靶点上的表现，这些靶点中大多数管线处于临床前及亚洲开发的长尾阶段。所有系统接收相同自然语言查询和相同JSON输出格式。在十个靶点上，戈塞特返回的经验证药物数量是最佳前沿系统的3.2倍，且精确率完美、召回率100%（相对于各系统联合验证药物集）。该标注索引亦可作为戈塞特MCP服务器供任意前沿模型调用，表明只需将通用网络搜索替换为该结构化索引，即可显著缩小召回差距。
原文摘要 · Abstract (English)
General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。