OpenAI、PerturbAI 和斯克利普斯研究所动用近 2000 个 AI 智能体，在 32 分钟内完成了一项大规模小鼠脑数据集的分析。
OpenAI, PerturbAI and Scripps Research have used close to 2,000 AI agents to analyse a large mouse brain dataset in 32 minutes.
该团队估计，研究人员若手工完成同等分析，将需要数月至一年的时间。OpenAI 于周三发布了该成果。
The team estimates that researchers working by hand would need months to a year for the same analysis, which OpenAI published on Wednesday.
这些智能体运行在 OpenAI 的 GPT-Rosalind 模型上，该模型专为生命科学研究而构建。相关结果已发表在 bioRxiv 预印本平台上，尚未经过同行评审。
The agents ran on OpenAI’s GPT-Rosalind, a model built for life sciences research. The results are set out in a bioRxiv preprint, which has not yet been peer-reviewed.
数据源自 PerturbAI 构建的全脑 CRISPR 图谱。CRISPR 是一种基因编辑工具，此处被用于在小鼠体内逐个敲除基因，以展示每种基因变化对不同类型脑细胞的影响。
The data comes from a whole-brain CRISPR atlas built by PerturbAI. CRISPR is a gene-editing tool, and here it was used to switch off single genes in mice, showing how each change affects different types of brain cells.
每个智能体负责分析一种基因变化。它研究细胞的响应情况，检索科学文献，并提出可能的解释。
Each agent took one of these gene changes. It studied how the cells responded, searched the scientific literature, and suggested possible explanations.
随后，团队将所有报告整合为一个统一的推理图谱，将基因、细胞效应、文献及可能的机制关联起来。
The team then merged all the reports into a single reasoning atlas that links genes, cell effects, papers, and likely mechanisms.
据 OpenAI 介绍，这些智能体复现了早期人工分析的发现，同时也挖掘出新的线索。在盲测中，专家更倾向于这种分工协作方式生成的报告，而非单一智能体生成的报告，偏好比例达 75%。
According to OpenAI, the agents reproduced findings from earlier human analyses and also found new leads. In blinded tests, experts preferred the reports from this split approach over those from a single agent 75% of the time.
这种分工方式在更大规模的工作负载下优势更为明显。在最大工作负载下，多个智能体合计引用了 700 多篇参考文献，而单一智能体仅引用 11 篇。
The split approachmore widely. At the largest workload, the many agents together cited more than 700 references, compared with 11 for a single agent.
其中一条线索涉及两个基因 Tsc1 和 Tsc2，两者均参与调控细胞生长。敲除 Tsc2 导致小脑中数十个与神经细胞通讯相关的基因发生改变，而敲除 Tsc1 几乎未引起变化。这种差异可能对结节性硬化症（一种罕见遗传疾病）具有重要意义。
One lead involves two genes, Tsc1 and Tsc2, which both help control cell growth. Switching off Tsc2 changed dozens of genes linked to communication between nerve cells in the cerebellum, while switching off Tsc1 changed little. That gap may matter for tuberous sclerosis, a rare genetic disorder.
另一案例中，敲除与罕见脑部疾病佩里综合征相关的 Dctn1 基因，导致合成胆固醇的基因活性升高。智能体建议开展实验室实验，以检验这一变化是否参与了神经细胞损伤。
In another case, switching off Dctn1, a gene linked to the rare brain disease Perry syndrome, raised the activity of genes that make cholesterol. The agents suggested lab experiments to test whether this plays a part in nerve cell damage.
“我们构建细胞图谱，是为了让其他科学家能够做出我们尚未想象到的发现，”剑桥大学干细胞医学讲席教授莎拉·泰希曼（Sarah Teichmann）表示。
“We build cell atlases so that other scientists can make discoveries we haven’t imagined yet,” said Sarah Teichmann, chair in stem cell medicine at the University of Cambridge.
推理图谱现已在 GitHub 上发布，底层数据集则托管在 Hugging Face 上。
The reasoning atlas is now available on GitHub, and the underlying dataset is on Hugging Face.