CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
2026-06-02 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed CP-Agent, a smart computer model that helps understand how drugs change cells by looking at detailed images and experimental details together. Unlike previous methods that mostly focused on the drug molecules alone, CP-Agent also uses information about the experiment setup, which helps it better explain how drugs work. It creates easy-to-understand reports about how cells respond to drugs, which can help scientists design better experiments and speed up drug discovery. Their model performs well at distinguishing drug effects and mechanisms from cell images and data.
Cell Paintinghigh-content imagingmechanism-of-actiondrug perturbationmultimodal learningCP-CLIPphenotypic screeningexperimental metadataF1-scoredrug discovery
Authors
Yuxin Zhang, Yiyao Li, Ping Shu Ho, Simon See, Zhenqin Wu, Kevin Tsia
Abstract
Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstream tasks such as mechanism-of-action (MoA) inference, toxicity prediction, and construction of drug-disease atlases. However, existing workflows are slow, costly and difficult to interpret. Approaches for drug screening modeling predominantly focus on molecular representation learning, while neglecting actual experimental context (e.g., cell line, dosing schedule, etc.), limiting generalization and MoA resolution. We introduce CP-Agent, an agentic multimodal large language model (MLLM) capable of generating mechanism-relevant, human-interpretable rationales for cell morphological changes under drug perturbations. At its core, CP-Agent leverages a context-aware alignment module, CP-CLIP, that jointly embeds high-content images and experimental metadata to enable robust treatment and MoA discrimination (achieving a maximum F1-score of 0.896). By integrating CP-CLIP outputs with agentic tool usage and reasoning, CP-Agent compiles rationales into a structured report to guide experimental design and hypothesis refinement. These capabilities highlight CP-Agent's potential to accelerate drug discovery by enabling more interpretable, scalable, and context-aware phenotypic screening -- streamlining iterative cycles of hypothesis generation in drug discovery.