Spatial Modeling of Single-Cell Data Using Deep Learning

Watch a research presentation from the Computational Genomics Summer Institute that explores advanced deep learning approaches for spatial modeling of single-cell data. Delve into cutting-edge methodologies including GrapHiC for imputing missing Hi-C reads, scGrapHiC for Hi-C deconvolution using single-cell gene expression, and scNODE for temporal single-cell transcriptomic data prediction. Learn about integrative graph-based approaches and generative models that are advancing our understanding of cellular spatial organization and temporal dynamics at the single-cell level. Examine the practical applications and implications of these computational methods through discussion of three related research papers that demonstrate the evolution and implementation of these techniques in genomic analysis.