从检索到推理：基于细胞绘画图谱的智能体机制预测
From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles
浏览论文内容
中文总结 AI 辅助
针对细胞绘画MOA预测中检索证据噪声问题，提出可靠性感知多智能体框架PhenoAIR，通过校准证据推理和候选中心记忆，在JUMP基准上全面超越现有基线。
中文摘要 AI 辅助
细胞绘画是一种高内涵形态学分析测定方法，广泛用于基于表型的生物学推断，其中作用机制（MOA）预测是核心应用。现有方法大多将基于细胞绘画的推断表述为表征匹配，从形态学特征空间中邻近的参考扰动中分配预测结果。然而，由于批次效应、非特异性细胞毒性、表型趋同以及来源依赖性变异，检索到的邻近样本往往是嘈杂且部分具有误导性的证据。我们将基于细胞绘画的MOA预测重新表述为一个校准的证据推理问题，其中检索到的邻近样本被视为不确定的观察结果，在支持机制性结论之前必须对其进行评估、比较，有时还需予以拒绝。我们提出了PhenoAIR，一个可靠性感知的多智能体框架，该框架维护一个以候选者为中心的证据记忆，并对表型和机制侧证据进行控制器引导的细化。PhenoAIR使用离线参考集校准，根据来源可靠性、表型稳定性和机制级混淆对证据进行加权。我们在由JUMP细胞绘画图谱和注释构建的基准上评估了PhenoAIR，涵盖了受控、现实和面向发现的开放世界MOA预测设置。在所有设置中，PhenoAIR均优于表征匹配和基于LLM的基线方法。
英文摘要
Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) prediction as a central application. Existing approaches largely formulate Cell Painting-based inference as representation matching, assigning predictions from nearby reference perturbations in morphological feature space. However, retrieved neighbors are often noisy and partially misleading evidence due to batch effects, non-specific cytotoxicity, phenotypic convergence, and source-dependent variability. We reformulate Cell Painting-based MOA prediction as a calibrated evidence reasoning problem, where retrieved neighbors are treated as uncertain observations that must be evaluated, compared, and sometimes rejected before supporting a mechanistic conclusion. We propose PhenoAIR, a reliability-aware multi-agent framework that maintains a candidate-centric evidence memory and performs controller-guided refinement over phenotype- and mechanism-side evidence. PhenoAIR uses offline reference-set calibration to weight evidence by source reliability, phenotype stability, and mechanism-level confusion. We evaluate PhenoAIR on a benchmark constructed from JUMP Cell Painting profiles and annotations, covering controlled, realistic, and discovery-oriented open-world MOA prediction settings. PhenoAIR outperforms representation-matching and LLM-based baselines across all settings.
发表机构
- The Ohio State University（俄亥俄州立大学）
- Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。
