Multi-modal insights of spatially distributed cells with associations of diseases and drug response - Project Summary Spatial cellular heterogeneity contributes to the complexity of diseases, therapeutic treatment, and drug response, which commonly involve the interplay between different molecular levels including genetic, epigenetic, and cellular levels. Recent technological advances of spatial technologies have enabled the elucidation of single cell heterogeneity with rich information and spatial locations that offer remarkable opportunities to understand biological processes and molecular interplays involved in disease and therapeutics. Moreover, traditional approaches mostly focus on a single type of data that cannot fully address this complexity and heterogeneity. Therefore, there is a lack of integrative approaches that leverage the strengths of data from multiple sources (e.g., genomics, epigenomics, clinical data) to achieve full insights into the pathobiology of complex disease and drug response. Given these challenges and my unique multi-disciplinary training, the overall goals of my research program are to develop a novel class of machine learning, statistical and deep learning approaches for the enhancement, prioritization and interpretation of spatially organized cells in complex tissue, to better understand the molecular mechanisms underpinning diseases and drug response, which will empower precision medicine by identifying individualized biomarkers for disease prevention, diagnosis and treatment. Specifically, in the next five years, my team will (i) develop a novel transfer learning approach to impute the transcriptomics and epigenomics profiles in spatial slices; (ii) develop a computational framework to reveal disease-associated phenotypes in spatially distributed cells, through leveraging Genome-Wide Association Studies (GWAS) studies; (iii) develop a novel domain adaptation method to predict drug responses of spatial cells, using pharmacogenomics knowledge base; (iv) develop a novel class of statistical methods for the joint analysis of spatial transcriptomics and single-cell multi-omics data, thus unveil the underlying regulatory mechanisms in diseases and drug response. In the meantime, supported by Wake Forest Comprehensive Cancer Center, we will apply the methodologies to different studies such as Brain Metastasis and Alzheimer’s Disease for novel scientific findings. We will work closely with collaborating biostatisticians and biologists to interpret the biological discoveries. Importantly, we will work with experimental labs to validate the findings. In line with our previous work, we will continue to make all developed methods into open-source software tools that are accessible and useful to the biomedical research community.
