Analysis of chromatin accessibility in decidualizing human endometrial stromal cells

Abstract

Spontaneous decidualization of the endometrium in response to progesterone signaling is confined to menstruating species, including humans and other higher primates. During this process, endometrial stromal cells (EnSCs) differentiate into specialized decidual cells that control embryo implantation. We subjected undifferentiated and decidualizing human EnSCs to an assay for transposase accessible chromatin with sequencing (ATAC-seq) to map the underlying chromatin changes. A total of 185,084 open DNA loci were mapped accurately in EnSCs. Altered chromatin accessibility upon decidualization was strongly associated with differential gene expression. Analysis of 1533 opening and closing chromatin regions revealed over-representation of DNA binding motifs for known decidual transcription factors (TFs) and identified putative new regulators. ATAC-seq footprint analysis provided evidence of TF binding at specific motifs. One of the largest footprints involved the most enriched motif-basic leucine zipper-as part of a triple motif that also comprised the estrogen receptor and Pax domain binding sites. Without exception, triple motifs were located within Alu elements, which suggests a role for this primate-specific transposable element (TE) in the evolution of decidual genes. Although other TEs were generally under-represented in open chromatin of undifferentiated EnSCs, several classes contributed to the regulatory DNA landscape that underpins decidual gene expression.-Vrljicak, P., Lucas, E. S., Lansdowne, L., Lucciola, R., Muter, J., Dyer, N. P., Brosens, J. J., Ott, S. Analysis of chromatin accessibility in decidualizing human endometrial stromal cells.

Keywords: decidualization; endometrium; gene regulation; open chromatin; transposable elements.

Figure 1.

ATAC-seq analysis of decidualizing EnSCs. A) Dynamic chromatin changes at key decidual marker genes in differentiating EnSCs. ATAC-seq signals in undifferentiated and decidualizing cells are shown in black and red, respectively. Proximal promoters of PRL (prolactin; upper panel) and IGFBP1 (IGF binding protein-1; lower panel) exhibit chromatin opening upon decidualization. IGFBP1 has additional regions of opening chromatin that are upstream of the TSS and downstream of the termination site. B) Dynamic chromatin changes in decidualizing EnSCs correlate with differential gene expression. Box plots show differential expression of 100 genes nearby (within 10 kb of TSS) the most opening or closing regions. Log2 fold change in expression is shown on the y axis: +ve and −ve values represent genes that are up- and down-regulated, respectively. ATAC-seq peaks were grouped according to whether they open, close, or remain unchanged upon decidualization. Red asterisk shows mean log₂-fold change.

Figure 2.

Gain and loss of TF binding motifs in dynamic chromatin regions. A) Top 5 most enriched TF binding motifs in opening and closing chromatin regions (see Supplemental Fig. 2 for full lists). The frequency (%) of opening or closing peaks featuring a given motif is shown relative to randomly selected genomic regions (±50 kb from TSSs, matching size, and GC/CpG content). On the basis of expression data and motif specificity, the most plausible TF for each motif is shown. B) The frequency of the 10 motifs was also determined across 185,084 open chromatin peaks in EnSCs. The y axis indicates the frequency of each motif across bins of 10,000 ATAC-seq peaks that are ranked on the x axis from the most opening (1) to the most closing peak (185,084). Nonshaded bars indicate expected frequency on the basis of genomic background frequency. C) Footprint analysis. Average ATAC-seq signals were calculated within 200-bp windows that were centered on enriched motifs in opening and closing ATAC-seq peaks. Red and blue indicate positive and negative strand cuts, respectively. A deep notch in the aggregated ATAC-seq signal at the motif, together with increased positive and negative strand reads at the 5′ and 3′ flanking regions, respectively, indicates occupancy by a DNA-binding factor. Footprints were present at all motifs, with the exception of closing motif 1 (M1). CEBP, CCAAT/enhancer binding protein; STAT3, signal transducer and activator of transcription; RUNX, runt-related transcription factor; SOX, SRY-box 12; TCF, transcription factor 3; TEAD, TEA domain transcription factor.

Figure 3.

Triple motif in Alu elements. A) Short-sequence motif-finding analysis on 50-bp windows across opening motif 1 revealed a triple motif that consisted of ESR1, bZIP and Pax-like domain binding sequences. B) Triple motif is part of the 3′-end of Alu repetitive elements. Every triple motif in the genome overlaps with the right arm of Alu repetitive elements. C) Conservation, measured as entropy, of full-length Alu sequences in the genome was analyzed together with flanking sequences. Higher entropy, denoted as natural units of information (Nats), indicates higher conservation. D) Aggregated ATAC-seq signals across Alu sequences of at least 300 bp in length, together with 50 bp of surrounding sequence. Red and blue indicate positive and negative strand cuts, respectively. ATAC-seq peaks are enriched over the triple motif region, but are depleted in A-rich regions. E) Frequency of overlap of individual positions within the Alu elements and open chromatin regions. The 3′ end of Alu elements more frequently coincides with open chromatin than does the 5′ end.

Figure 4.

Alu conservation and co-option in primate species. Heat map shows the conservation of Alu elements across primate species. Only Alus that were associated with genes (within 10 kb of TSSs) were examined. Green indicates presence, red absence, and gray inconclusive. Alu conservation decreases with evolutionary distance.

Figure 5.

Involvement of TEs in dynamic chromatin changes upon decidualization. A) Relative frequency of ATAC-seq peaks overlapping repetitive elements identified by RepeatMasker. Of the six most abundant TE families in ATAC-seq peaks, only one [chicken repeat 1 (CR1)] exceeds the frequency that is expected by chance. B) The frequency of TE families was also determined across 180,000 open chromatin peaks. The y axis indicates the frequency of each family across bins of 10,000 peaks that are ranked on the x axis from the most opening (1) to the most closing peak (185,084).