用大模型直接分析单细胞数据，自动完成细胞注释与发育轨迹推断。
scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
- 大模型直接读取原始单细胞数据，分步推理并修正分析过程。
- 相比一次性提示，迭代推理使细胞注释准确率提升11%，轨迹重建误差降低30%。
- 生成可解释的推理链条，适合生物学家和算法研究者使用。
我们提出scPilot，首个实现组学原生推理的系统：大语言模型（LLM）以自然语言对话方式，直接分析单细胞RNA测序数据及按需调用生信工具。scPilot将核心单细胞分析任务——细胞类型注释、发育轨迹重建、转录因子靶向——转化为逐步推理问题，要求模型给出解释，并在新证据下修正判断。为评估进展，我们发布scBench，包含9个专家标注的数据集与评分器，用于衡量不同LLM在组学原生推理上的表现。实验显示，o1模型通过迭代推理使细胞注释平均准确率提升11%；Gemini-2.5-Pro相比一次性提示，轨迹图编辑距离减少30%。同时生成透明推理轨迹，解释标记基因模糊性与调控逻辑。通过将大模型扎根于原始组学数据，scPilot实现可审计、可解释、具诊断价值的单细胞分析。代码、数据与包已开源。
原文摘要 · Abstract (English)
We present scPilot, the first systematic framework to practice omics-native reasoning: a large language model (LLM) converses in natural language while directly inspecting single-cell RNA-seq data and on-demand bioinformatics tools. scPilot converts core single-cell analyses, i.e., cell-type annotation, developmental-trajectory reconstruction, and transcription-factor targeting, into step-by-step reasoning problems that the model must solve, justify, and, when needed, revise with new evidence. To measure progress, we release scBench, a suite of 9 expertly curated datasets and graders that faithfully evaluate the omics-native reasoning capability of scPilot w.r.t various LLMs. Experiments with o1 show that iterative omics-native reasoning lifts average accuracy by 11% for cell-type annotation and Gemini-2.5-Pro cuts trajectory graph-edit distance by 30% versus one-shot prompting, while generating transparent reasoning traces explain marker gene ambiguity and regulatory logic. By grounding LLMs in raw omics data, scPilot enables auditable, interpretable, and diagnostically informative single-cell analyses. Code, data, and package are available at https://github.com/maitrix-org/scPilot
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。