DEEPsc uses a neural network to obtain a data-adaptive projection of cells in scRNA-seq to the corresponding spatial imaging or spatial transcriptomic data of the same tissue.

During early mammalian embryo development, a small number of cells make robust fate decisions at particular spatial locations in a tight time window to form inner cell mass (ICM), and later epiblast (Epi) and primitive endoderm (PE). While recent single-cell transcriptomics data allows scrutinization of heterogeneity of individual cells, consistent spatial and temporal mechanisms the early embryo utilize to robustly form the Epi/PE layers from ICM remain elusive. Here we build a multiscale three-dimensional model for mammalian embryo to recapitulate the observed patterning process from zygote to late blastocyst. By integrating the spatiotemporal information reconstructed from multiple single-cell transcriptomic datasets, the data-informed modeling analysis suggests two major processes critical to the formation of Epi/PE layers: a selective cell-cell adhesion mechanism (via EphA4/EphrinB2) for fate-location coordination and a temporal attenuation mechanism of cell signaling (via Fgf). Spatial imaging data and distinct subsets of single-cell gene expression data are then used to validate the predictions. Together, our study provides a multiscale framework that incorporates single-cell gene expression datasets to analyze gene regulations, cell-cell communications, and physical interactions among cells in complex geometries at single-cell resolution, with direct application to late-stage development of embryogenesis.

Inferring, clustering, and downstream analysis for cell-cell communications in scRNA-seq data.

scMC is an R toolkit for integrating and comparing multiple single cell genomic datasets from single cell RNA-seq and ATAC-seq experiments across different conditions, time points and tissues.

An unsupervised learning of single-cell transcriptomic data for identification of individual cells making transition between all cell states, and inference of genes that mark transitions.