MAD: Microenvironment-Aware Distillation -- A Pretraining Strategy for Virtual Spatial Omics from Microscopy
This provides a scalable pretraining strategy for enabling virtual spatial omics from microscopy, addressing a bottleneck in bridging imaging and molecular data for biological research.
The paper tackled the problem of learning cell-centric embeddings from microscopy images to predict molecular states without costly omics technologies, achieving state-of-the-art performance on tasks like cell subtyping and transcriptomic prediction, even outperforming larger foundation models.
Bridging microscopy and omics would allow us to read molecular states from images-at single-cell resolution and tissue scale-without the cost and throughput limits of omics technologies. Self-supervised pretraining offers a scalable approach with minimal labels, yet how to encode single-cell identity within tissue environments-and the extent of biological information such models can capture-remains an open question. Here, we introduce MAD (microenvironment-aware distillation), a pretraining strategy that learns cell-centric embeddings by jointly self-distilling the morphology view and the microenvironment view of the same indexed cell into a unified embedding space. Across diverse tissues and imaging modalities, MAD achieves state-of-the-art prediction performance on downstream tasks including cell subtyping, transcriptomic prediction, and bioinformatic inference. MAD even outperforms foundation models with a similar number of model parameters that have been trained on substantially larger datasets. These results demonstrate that MAD's dual-view joint self-distillation effectively captures the complexity and diversity of cells within tissues. Together, this establishes MAD as a general tool for representation learning in microscopy, enabling virtual spatial omics and biological insights from vast microscopy datasets.