Tumor cell villages define the co-dependency of tumor and microenvironment in liver cancer.

Spatial cellular context is crucial in shaping intratumor heterogeneity. However, understanding how each tumor establishes its unique spatial landscape and what factors drive the landscape for tumor fitness remains significantly challenging. Here, we analyzed over 2 million cells from 50 tumor biospecimens using spatial single-cell imaging and single-cell RNA sequencing. We developed a deep learning-based strategy to spatially map tumor cell states and the architecture surrounding them, which we referred to as Spatial Dynamics Network (SDN). We found that different tumor cell states may be organized into distinct clusters, or 'villages', each supported by unique SDNs. Notably, tumor cell villages exhibited village-specific molecular co-dependencies between tumor cells and their microenvironment and were associated with patient outcomes. Perturbation of molecular co-dependencies via random spatial shuffling of the microenvironment resulted in destabilization of the corresponding villages. This study provides new insights into understanding tumor spatial landscape and its impact on tumor aggressiveness.