scPilot：基于大语言模型推理的单细胞分析自动化与发现探索

摘要

我们推出scPilot——首个实现组学原生推理的系统性框架：大型语言模型（LLM）能够以自然语言进行对话，同时直接检查单细胞RNA测序数据并按需调用生物信息学工具。scPilot将核心单细胞分析（即细胞类型注释、发育轨迹重建和转录因子靶向分析）转化为分步推理问题，要求模型必须解决、论证并在需要时根据新证据修正结论。为量化进展，我们发布scBench——包含9个专家精编数据集与评估器的测试套件，可准确评估scPilot相对于各LLM的组学原生推理能力。o1实验表明：通过迭代式组学原生推理，细胞类型注释的平均准确率提升11%；Gemini-2.5-Pro相较于单次提示将轨迹图编辑距离缩减30%，同时生成可解释标记基因歧义性与调控逻辑的透明推理轨迹。通过将LLM锚定于原始组学数据，scPilot实现了可审计、可解释且具诊断价值的单细胞分析。代码、数据及软件包详见：https://github.com/maitrix-org/scPilot

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

scPilot：基于大语言模型推理的单细胞分析自动化与发现探索

scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery

摘要

Support