Cell morphology profiling drops segmentation: self-supervised models retrieve about a third more mechanism classes than CellProfiler across labs
Cell morphology profiling has relied on cell segmentation and handcrafted features, which are annotation-hungry and hard to reuse across laboratories. Researchers pretrained four self-supervised models on 119,876 unannotated compounds and about 1.77 million JUMP–CP images, then froze the weights and extracted image embeddings directly. On 2,464 EU-OPENSCREEN Bioactives compounds, DINO and DINOv2 beat CellProfiler by 31–37% in site-averaged mean average precision for mechanism-of-action retrieval and consistently surpassed masked-based models.