Single-Cell Landscape of Transcriptional Heterogeneity and Cell Fate Decisions during Mouse Early Gastrulation

Abstract

The mouse inner cell mass (ICM) segregates into the epiblast and primitive endoderm (PrE) lineages coincident with implantation of the embryo. The epiblast subsequently undergoes considerable expansion of cell numbers prior to gastrulation. To investigate underlying regulatory principles, we performed systematic single-cell RNA sequencing (seq) of conceptuses from E3.5 to E6.5. The epiblast shows reactivation and subsequent inactivation of the X chromosome, with Zfp57 expression associated with reactivation and inactivation together with other candidate regulators. At E6.5, the transition from epiblast to primitive streak is linked with decreased expression of polycomb subunits, suggesting a key regulatory role. Notably, our analyses suggest elevated transcriptional noise at E3.5 and within the non-committed epiblast at E6.5, coinciding with exit from pluripotency. By contrast, E6.5 primitive streak cells became highly synchronized and exhibit a shortened G1 cell-cycle phase, consistent with accelerated proliferation. Our study systematically charts transcriptional noise and uncovers molecular processes associated with early lineage decisions.

Keywords: X-chromosome; embryo; epiblast; gastrulation; primitive endoderm; primitive streak; single-cell RNA-seq; transcriptional noise.

Graphical abstract

Figure 1

Single-Cell mRNA-Seq of E3.5, E4.5, E5.6, and E6.5 Mouse Embryos (A) Table listing number of embryos and cells, along with representative images of embryos used at each stage. (B) Principal-component analysis (PCA) of cells that passed the quality and filtering criteria. (C) PCA of all cells colored by gene expression levels (log2 of counts per million) of selected marker genes - Nanog (ICM/epiblast), Gata6 (PrE/VE), Pou3f1 (primed pluripotency), and T (primitive streak). (D) Heatmap showing key genes distinguishing cell clusters (SC3 analysis). (E) Gene expression levels and variability of pluripotency factors classified into primed, naïve, and core genes (using previous classifications; Boroviak et al., 2014). The size of each dot represents relative expression levels, while variability is shown by color.

Figure 2

Dynamics of X Chromosome Reactivation and Silencing (A) Ratio of gene expression (median) between female and male embryos for the X chromosome and chromosomes 1, 4, and 6. (B) Total expression levels of the X chromosome visualized at a single-cell level. The y axis represents the proportion of X chromosome counts relative to all other chromosomes. (C) Overall X chromosome expression levels plotted across all stages. The matched expression levels for Pou5f1, Nanog, and Sox2 are also plotted underneath. (D) Plot representing pluripotency genes correlating or anticorrelating with X chromosome expression at each stage. Spearman’s correlation coefficient is represented by color and size. (E) Plot representing selected genes correlating or anticorrelating with X chromosome expression at each stage. The X represents absence of expression.

Figure 3

Transcriptional Noise across Each Developmental Stage (A) Cartoon illustrating the concept used to calculate transcriptional noise. The method is based on cell-cell correlations within homogeneous populations. (B) Plot showing transcriptional noise across all stages of epiblast development and the primitive streak (PS). (C) Plot showing transcriptional noise of cell-cycle genes across all stages of epiblast development and the primitive streak (PS). (D) Separation of cells at each stage or lineage by cell-cycle phase. Number of cells at each cell-cycle stage is shown in the inset.

Figure 4

Transcriptional Noise during Primitive Endoderm and Epiblast Formation (A) Heatmap showing expression of PrE and epiblast genes identified by differential expression at E4.5. A substantial number of genes are already expressed at E3.5, but genes do not segregate by lineage at E3.5. (B) Examples of PrE and epiblast genes at E3.5 and E4.5 indicating an initial co-expression before becoming lineage specific at E4.5. (C) Plot representing number of lineage-specific genes expressed in each E3.5 and E4.5 cell. (D) Overlay of expression levels of genes identified as correlated with the ratio of epiblast and PrE expressed genes. (E) Plot representing the ratio of H3K4me3 and H3K27me3 enrichment at binding sites classified as early or late lineage genes. Early genes show a higher ratio than their late counterparts (p < 0.001). (F) Cartoon showing the overall transition from a non-committed state to lineage commitment and genes associated with this shift.

Figure 5

Lineage Characteristics at E6.5 (A) Heatmap showing the expression of some differentially expressed genes between the primitive streak cluster and the epiblast. (B) Expression levels of polycomb components Suz12, Ezh2, and Jarid2 across the different epiblast subclusters and primitive streak (counts per million). (C) Plot representing H3K27me3 bound genes expressed in E6.5 epiblast and primitive streak cells using published in vivo datasets (Zylicz et al., 2015).