用检索增强框架让大模型生成可审计的细胞形态学假说。
Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology
- 结合形态差异与文献证据，生成带溯源的生物假说。
- 验证测试显示假说与形态变化一致，强度越高越可信。
- 适合研究辐射等慢性刺激的生物机制探索者。
高内涵细胞形态分析（Cell Painting）能捕捉细胞状态的敏感、高维特征，但将长期形态轨迹转化为可解释的生物学意义仍具挑战，尤其针对低剂量率电离辐射等弱而持续的扰动。大语言模型（LLM）可整合异质证据生成生物叙事，但其科学应用需量化审计。本文提出一种评估优先、检索增强的纵向细胞形态分析框架，应用于9周RPE-1时间序列实验，覆盖0.003–6.0 mGy/hr五种剂量率。通过匹配时间点的处理-对照形态差值，结合检索到的扰动邻近样本、通路背景及文献证据，并使用稳定证据标识符，使LLM生成结构化、可追溯的假说，同时保留层级摘要与来源。引入两项量化审计测试：V1引用有效性，验证引文标识符是否存在于提示中；V2基于代理的形态兼容性，评估预测生物过程与最显著形态变化的一致性。实验中V1未发现无效引用，V2显示形态兼容性随扰动强度上升，且与独立的形态漂移总结正相关。该框架生成可审计、可证伪的生物假说，如低剂量率（0.003–0.3 mGy/hr）下代谢重编程与蛋白稳态压力相关的适应性表型。当前局限包括代理评估方式及缺乏真实机制标签。
原文摘要 · Abstract (English)
High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.
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。