Tracing cellular dynamic changes across conditions, time, and space is crucial for understanding the molecular mechanisms underlying complex biological systems. However, integrating multi-sample data in a unified and versatile way to explore cellular heterogeneity remains a major challenge.

Here, we present Stereopy, a flexible and scalable framework for modeling and dissecting comparative and spatiotemporal patterns in multi-sample spatial transcriptomics with interactive data visualization. To optimize this framework, we have devised a universal container, a scope controller, and an integrative transformer tailored for multi-sample multimodal data storage, management, and processing.

Stereopy showcases three transformative applications supported by pivotal algorithms. Firstly, the multi-sample cell community detection (CCD) algorithm introduces an innovative capability to detect specific cell communities and identify genes responsible for pathological changes in comparative studies. The second application features the spatially resolved temporal gene pattern inference (TGPI) algorithm, which advances the detection of spatiotemporal gene patterns by concurrently considering spatial and temporal features, which enhances the identification of genes, domains, and regulatory factors correlated with temporal tendencies. Finally, the 3D niche-based regulation inference tool, NicheReg3D, reconstructs the 3D cell niches to enable the inference of cell-gene interaction network within the spatial texture, thus bridging intercellular communications and intracellular regulations to unravel the intricate regulatory mechanisms that govern cellular behavior.

Overall, Stereopy serves as both a comprehensive bioinformatics toolbox and an extensible framework that empowers researchers with enhanced data interpretation abilities and new perspectives for mining multi-sample spatial transcriptomics data.