Tag
The paper introduces PhenoAIR, a reliability-aware multi-agent framework that reformulates Cell Painting-based mechanism of action prediction as calibrated evidence reasoning rather than simple nearest-neighbor retrieval, evaluated on a new JUMP Cell Painting MOA benchmark where it outperforms representation-matching and LLM baselines.
This paper extends the MoCoP method by using deep-learning-based morphology profiles to improve molecular embeddings for QSAR predictions and toxicity assessment in drug discovery.
CP-Agent is a multimodal large language model that interprets cellular morphological changes under chemical perturbations using context-aware alignment (CP-CLIP), enabling interpretable and scalable phenotypic screening for drug discovery.