Genome-wide analysis reveals the unique stem cell identity of human amniocytes

Abstract

Human amniotic fluid contains cells that potentially have important stem cell characteristics, yet the programs controlling their developmental potency are unclear. Here, we provide evidence that amniocytes derived from multiple patients are marked by heterogeneity and variability in expression levels of pluripotency markers. Clonal analysis from multiple patients indicates that amniocytes have large pools of self-renewing cells that have an inherent property to give rise to a distinct amniocyte phenotype with a heterogeneity of pluripotent markers. Significant to their therapeutic potential, genome-wide profiles are distinct at different gestational ages and times in culture, but do not differ between genders. Based on hierarchical clustering and differential expression analyses of the entire transcriptome, amniocytes express canonical regulators associated with pluripotency and stem cell repression. Their profiles are distinct from human embryonic stem cells (ESCs), induced-pluripotent stem cells (iPSCs), and newborn foreskin fibroblasts. Amniocytes have a complex molecular signature, coexpressing trophoblastic, ectodermal, mesodermal, and endodermal cell-type-specific regulators. In contrast to the current view of the ground state of stem cells, ESCs and iPSCs also express high levels of a wide range of cell-type-specific regulators. The coexpression of multilineage differentiation markers combined with the strong expression of a subset of ES cell repressors in amniocytes suggests that these cells have a distinct phenotype that is unlike any other known cell-type or lineage.

Figure 1. Amniocytes have properties of pluripotent stem cells.

(A–E) Confocal images of amniocytes immunostained (green) for transcription factors as indicated. Hoechst dye was used to label nuclei (cyan-colored insets) in all panels and cells in panel C were stained with α-actinin to visualize the lateral cell border and cytoskeletal remodeling (red in panel C). 6,143 cells were counted for all conditions. (F–J) Confocal images of amniocytes co-stained for cell surface antigens as indicated. (H) SSEA4 and Tra-1-60 staining in an (H) undifferentiated population and (J) staining from clonal analysis reveals that individual amniocyte clones give rise to a heterogeneous population of progeny that had similar properties to the parent population. (H–J) Each of these panels show two cells, both expressing SSEA4 but only one coexpressing Tra-1-60. (K) Amniocyte isolates that are positive for transcriptional markers associated with pluripotency express these markers in >90% of nuclei. 19,010 cells were counted for all conditions. (L) The average percent amniocytes per isolate co-expressing surface stem cell markers, ± standard error of the mean. More than 60% of amniocytes stained positive for SSEA4, whereas far fewer cells co-stained for SSEA1 (2.1%, N = 11 isolates), Tra-1-60 (8.5%, N = 7 isolates), and Tra-1-81 (7.1%, N = 7 isolates). Amniocytes exhibit a high rate of proliferation (4.3%), as counted by anti-phospho-histoneH3 (PH3; N = 7 isolates). (M) FACS analysis of SSEA1/SSEA4 amniocytes reveals three distinct populations: low-to-high expressing SSEA4-positive (red circle); high-expressing SSEA1-positive (green circle); and high-expressing double-stained SSEA1+/SSEA4-positive (yellow circle). Percent of cells are indicated in each quadrant.

Figure 2. Core stem cell markers are variably expressed, depending on GA and time in culture.

(A–B) Dot plots of (A) RNA-seq and (B) qPCR results reveal significant variability in transcript levels for key genes known to be required for establishment and maintenance of pluripotency. (A) RNA-seq measurements for 37 datasets are presented as variance-stabilized read counts. The string of horizontal dots at the lower detection limit for genes Oct4, Sox2 and cKit indicates samples that had no reads in those genes. (B) qPCR units for 17 datasets are presented as normalized Cp values (Cp value of target gene minus Cp value of reference gene Gapdh). (C–E) Hierarchical clustering of C) qPCR results for eight genes; (D) qPCR results for 17 patients; and (E) RNA-seq results for 37 datasets using measurements of 250 stem cell markers. Clustering similarities in transcript levels were calculated by Pearson's r² correlation coefficient as a measure of dendrogramatic distance and bootstrapping values were calculated from 10,000 random replications. (E) Culture time point T1 was taken on average from 1.3 days (0–8 range), T2 was taken on average from 15.2 days (13–22 range), and T3 was taken on average from 28.0 days (24–36 range).

Figure 3. Amniocyte genome-wide transcriptional profile varies depending on GA and time in culture.

(A) Hierarchical clustering of 11 independent amniocyte isolates at different times in culture (37 RNA-seq datasets; 24,609 ensemble genes per dataset). Four major clusters correlate with gestational age and culture time since amniocentesis. (B–D) Volcano plots display the results of differential expression analyses using these three variables (n = 49,235 Ensembl genes). Genes plotted above the red line have adjusted p-values<0.05, and genes plotted outside of the green lines are >2-fold differentially expressed. Comparing (B) early vs. late gestational age revealed the most differentially expressed genes (n = 2,197), followed by (C) time in culture (n = 1039) and (D) gender (n = 208). (A, C) Culture time point T1 was taken on average from 1.3 days (0–8 range), T2 was taken on average from 15.2 days (13–22 range), and T3 was taken on average from 28.0 days (24–36 range).

Figure 4. Amniocytes are not transcriptionally similar to ESCs and iPSCs.

(A) Genome-wide scatterplots (49,235 Ensembl genes) confirm that ESC and iPSC cells lines are remarkably similar in gene expression profiles. (B–C) In contrast, genome-wide scatterplots comparing amniocytes to (B) ESC lines and (C) iPSC lines show weak similarity. (D–E) The transcriptomes of (D) iPSC cell lines and human newborn foreskin fibroblasts (NFF) are also weakly similar, (E) as are amniocytes and NFF. (F–J) Volcano plots (as in Figure 3) display the results of differential expression analyses. (K–O) Bar graphs show the number of genes that were expressed exclusively in either cell type.

Figure 5. Amniocytes have a distinct transcriptional profile for key pluripotency genes.

(A–M) Differential expression analysis of RNA-seq datasets reveals the transcriptional profile controlling the stem cell state in amniocytes conspicuously differs from well-characterized ESC or iPSC lines. The selected 135 genes (Table S2) were grouped into transcriptional regulatory circuits based on their major functional role. Dot plots show RNA-seq read counts (variance corrected) that were median centered for 37 amniocyte (red dots) isolates and 31 ESC and iPSC replicates (blue dots). Circles outlined in black indicate the median value for each group. Within each panel, genes were sorted raw RNA-seq counts first by variance correction, second by the difference between the group medians [median (stem cell samples) – median (amniocyte samples)] and third by ordering the values from highest difference to lowest. All panels use the same y-axis scale, but unused portions of panels K-M were cropped (over +5 and under −5 read counts) because these areas were blank. Asterisks indicate genes with read counts that are not statistically different between amniocytes and ESC/iPSC (defined as the adjusted p-value is greater than 0.05).

Figure 6. Amniocytes exist in a unique state of transcriptional repression compared to ESC and iPSC.

(A) Differential expression analysis of RNA-seq datasets reveals that the repressed state in amniocytes is distinct from ESC/iPSC. Dot plots show RNA-seq read counts analyzed as in Figure 5. Eighty-nine important ES cell repressors in mouse and human ES cells (Table S4) were sorted as in Figure 5. Asterisks = no statistical difference between amniocytes and ESC/iPSC (defined as the adjusted p-value is greater than 0.05).

Figure 7. Amniocytes coexpress a complex phenotype that partially differentiates along multiple lineages.

(A–C) Confocal images of amniocytes double-immunostained for well-defined lineage markers as indicated: Sox17; an endoderm marker, SM_22α; a smooth muscle marker for mesoderm, and Tubb3; a neuronal marker for ectoderm. Hoechst dye was used to label nuclei (cyan-colored insets) in all panels. (D) The average percent of amniocytes per isolate that co-expressed lineage markers, ± standard error of mean. Over 75% of amniocytes were double-positive for two disparate lineage markers in multiple independent patient isolates: Sox17+/SM_22α+(78.7%, n = 11); Tubb3+/SM_22α+(98.0%, n = 11); Tubb3+/Sox17+ (90.4, n = 8). 4,998 cells were counted for all conditions. (E–I) Amniocytes show partial differentiation into each of the four embryonic primary lineages that is distinct from the partial differentiation seen in ESC and iPSC. Differential expression analysis of RNA-seq datasets reveals that lineage specification and potential in amniocytes differs from ESC/iPSC. Dot plots show RNA-seq read counts analyzed as in Figure 5. We examined 150 genes known to specify the three germ layers (E) ectoderm, (F) mesoderm, (G) endoderm, as well as (H) mixed lineages (enriched in derivatives of more than one germ layer) and (I) trophectoderm in mouse and human ES cells (Table S5). Asterisks = no statistical difference between amniocytes and ESC/iPSC (defined as the adjusted p-value is greater than 0.05).