Presentation Information
[MS16-03]Deciphering tissue structure from single-cell sequencing data by density ratio transfer
*Jifan Shi1 (1. Fudan Univ. (China))
Keywords:
scRNA-seq data analysis,Transfer learning
Single-cell omics, particularly spatial transcriptomics, has emerged as one of the most rapidly advancing frontier biotechnologies in recent years. By leveraging various single-cell measurement techniques, researchers can explore the evolutionary processes of cellular differentiation and tissue heterogeneity from multiple perspectives. However, scRNA-seq data often lose explicit information such as developmental time and spatial location during the experimental process. Meanwhile, large-scale spatiotemporal transcriptomics can be prohibitively expensive or challenging to achieve with high throughput. This talk will introduce several mathematical models and computational algorithms designed to infer dynamic processes of single-cell differentiation and tissue development through data modeling and analysis. Furthermore, we will demonstrate the application of these models in both simulated cases and real biomedical datasets, showcasing their potential significance in biomedical research.