Interpretable, flexible and spatially aware integration of multiple spatial transcriptomics datasets from diverse sources

Recent advances in spatial transcriptomics (ST) have generated an expanding collection of heterogeneous datasets, offering unprecedented opportunities to investigate tissue organizations and functions. However, effective interpretation and integration of data originating from diverse sources and conditions remain a major challenge. We present INSPIRE, a deep-learning method for interpretable, integrative analysis of multiple ST datasets. INSPIRE adopts an adversarial learning strategy with graph neural networks to achieve spatially informed and adaptive data integration. By incorporating non-negative matrix factorization, INSPIRE identifies interpretable spatial factors and associated gene programs that characterize tissue architecture, cell-type organization and biological processes. Across a broad range of applications, INSPIRE demonstrates superior performance in resolving fine-grained biological signals, integrating complementary strengths across technologies, capturing condition-specific variation, uncovering tumor microenvironment heterogeneity, elucidating developmental dynamics and facilitating three-dimensional tissue reconstruction. INSPIRE also scales to extremely large datasets, as demonstrated by applications to Xenium-profiled human breast cancer and Stereo-seq mouse organogenesis datasets. INSPIRE addresses challenges to integrating diverse spatial transcriptomics datasets by combining deep learning with non-negative matrix factorization, revealing shared and context-specific spatial gene programs and tissue organization across scales.