Interpretable, flexible and spatially-aware integration of transcriptomics data from diverse sources

This seminar was delivered on 3 August 2026. For more information: https://spds.sydney.edu.au/ Title: Interpretable, flexible and spatially-aware integration of multiple spatial transcriptomics datasets from diverse sources Speaker: Dr Jia Zhao, Yale University Abstract: Recent advances in spatial transcriptomics 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. In this talk, we will present INSPIRE, a deep-learning method for interpretable, integrative analysis of multiple spatial transcriptomic 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. About the speaker: Dr Jia Zhao received her PhD in Mathematics from the Hong Kong University of Science and Technology under the supervision of Prof. Can Yang. She completed her postdoctoral training in the Department of Biostatistics at Yale University, mentored by Prof Hongyu Zhao and Prof Rui Chang. She will soon join the School of Mathematical Sciences at Shanghai Jiao Tong University as a faculty member. Her research focuses on developing computational methods to address analytical challenges arising from large-scale biomedical data. She has led the development of methods for integrative single-cell analysis, interpretable modeling of spatial omics data, and robust causal inference among complex traits. Her work has been published in leading journals, including Nature Genetics, Nature Machine Intelligence, Nature Computational Science, and PNAS.