用AI模仿专家标注单细胞类型，无需训练就能精准识别罕见新细胞。
CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis
- 基于大模型知识实时推理，不依赖预训练或固定标记数据库。
- 自动模式下准确率比最优基线高7.1%，人机协作提升至18.6%。
- 擅长识别稀有和未知细胞亚型，适合生物发现类研究者使用。
单细胞RNA测序（scRNA-seq）可实现复杂组织的全景式分析，揭示稀有谱系和瞬时状态。然而，赋予生物上合理的细胞身份仍是瓶颈，因标记物具有组织和状态特异性，且新状态缺乏参考。我们提出CellMaster，一种模仿专家行为的AI代理，实现零样本细胞类型注释。与现有自动化工具不同，CellMaster利用大语言模型（如GPT-4o）编码的知识，在无需预训练或固定标记数据库的情况下进行实时注释，并提供可解释的推理过程。在涵盖8个组织的9个数据集上，其自动模式下的准确率比最佳基线（包括CellTypist和scTab）提升7.1%。在人机协同优化下，优势扩大至18.6%，对亚群的提升达22.1%。该系统在基线常失败的稀有和新型细胞状态中表现尤为突出。源代码和网页应用已公开于https://github.com/AnonymousGym/CellMaster。
原文摘要 · Abstract (English)
Single-cell RNA-seq (scRNA-seq) enables atlas-scale profiling of complex tissues, revealing rare lineages and transient states. Yet, assigning biologically valid cell identities remains a bottleneck because markers are tissue- and state-dependent, and novel states lack references. We present CellMaster, an AI agent that mimics expert practice for zero-shot cell-type annotation. Unlike existing automated tools, CellMaster leverages LLM-encoded knowledge (e.g., GPT-4o) to perform on-the-fly annotation with interpretable rationales, without pre-training or fixed marker databases. Across 9 datasets spanning 8 tissues, CellMaster improved accuracy by 7.1% over best-performing baselines (including CellTypist and scTab) in automatic mode. With human-in-the-loop refinement, this advantage increased to 18.6%, with a 22.1% gain on subtype populations. The system demonstrates particular strength in rare and novel cell states where baselines often fail. Source code and the web application are available at \href{https://github.com/AnonymousGym/CellMaster}{https://github.com/AnonymousGym/CellMaster}.
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。