Please note: This seminar will take place online.
Jia Zhao, Postdoctoral Associate
Department of Biostatistics, Yale University
Single-cell and spatial omics technologies are generating massive datasets that enable characterization of cellular heterogeneity within spatial context, across both health and disease. In this talk, I will present a suite of scalable and interpretable machine learning and AI methods for integrating, modeling, and extracting biological insight from such data.
The presentation will highlight three complementary advances: (i) a machine learning framework for integrative single-cell analysis that enables efficient knowledge transfer across atlas-scale, heterogeneous datasets; (ii) a deep learning approach that combines single-cell references with multiple parallel 2D tissue sections to reconstruct 3D tissue architectures and infer spatial cellular organization; and (iii) an interpretable deep learning framework for spatial omics modeling that reveals context-specific tissue organization by integrating modern AI’s representational capacity with the interpretability of statistical modeling. Together, these methods demonstrate how principled computational approaches can support reliable discovery in complex biological systems, advance biomedical understanding, and ultimately contribute to precision medicine.
Bio: Dr. Jia Zhao is a Postdoctoral Associate in the Department of Biostatistics at Yale University, mentored by Professors Hongyu Zhao and Rui Chang. Her research lies at the intersection of artificial intelligence, machine learning, statistics, and bioinformatics, with a focus on developing innovative computational methods to address the analytical challenges posed by large-scale biomedical data, including single-cell, spatial omics, and genetic data. She has led the development of methods for integrative single-cell analysis, interpretable modeling of spatial omics data, and reliable causal inference among complex traits. Her work has been published in leading journals such as Nature Machine Intelligence, Nature Computational Science, and PNAS.