Structural organization of the inactive X chromosome in the mouse

Abstract

X-chromosome inactivation (XCI) involves major reorganization of the X chromosome as it becomes silent and heterochromatic. During female mammalian development, XCI is triggered by upregulation of the non-coding Xist RNA from one of the two X chromosomes. Xist coats the chromosome in cis and induces silencing of almost all genes via its A-repeat region, although some genes (constitutive escapees) avoid silencing in most cell types, and others (facultative escapees) escape XCI only in specific contexts. A role for Xist in organizing the inactive X (Xi) chromosome has been proposed. Recent chromosome conformation capture approaches have revealed global loss of local structure on the Xi chromosome and formation of large mega-domains, separated by a region containing the DXZ4 macrosatellite. However, the molecular architecture of the Xi chromosome, in both the silent and expressed regions,remains unclear. Here we investigate the structure, chromatin accessibility and expression status of the mouse Xi chromosome in highly polymorphic clonal neural progenitors (NPCs) and embryonic stem cells. We demonstrate a crucial role for Xist and the DXZ4-containing boundary in shaping Xi chromosome structure using allele-specific genome-wide chromosome conformation capture (Hi-C) analysis, an assay for transposase-accessible chromatin with high throughput sequencing (ATAC-seq) and RNA sequencing. Deletion of the boundary disrupts mega-domain formation, and induction of Xist RNA initiates formation of the boundary and the loss of DNA accessibility. We also show that in NPCs, the Xi chromosome lacks active/inactive compartments and topologically associating domains (TADs), except around genes that escape XCI. Escapee gene clusters display TAD-like structures and retain DNA accessibility at promoter-proximal and CTCF-binding sites. Furthermore, altered patterns of facultative escape genes indifferent neural progenitor clones are associated with the presence of different TAD-like structures after XCI. These findings suggest a key role for transcription and CTCF in the formation of TADs in the context of the Xi chromosome in neural progenitors.

Extended Data Figure 1. Description of allele-specific Hi-C and ATAC–seq

a, Schematic of hybrid mouse strains used for all experiments. b, Top, scheme outlining differentiation of ES cells to NPCs and picking of clones. Bottom, scheme outlining CRISPR deletion of the mega-domain boundary in ES cells, differentiation to NPCs and the picking of clones. c, Schematic of Hi-C library generation. d, Schematic of the Hi-C alignment strategy. Paired-end reads are aligned to a ‘diploid’ genome consisting of 22 chromosomes from Cast, and 22 chromosomes from 129 (1–19 X, Y, M). The interaction row shows all possible paired-end read combinations between the 129, Cast and ambiguous (AMB) genomes. e, Schematic showing the re-assignment of a subset of ‘cis’ interactions. Paired-end reads in which one side uniquely aligned to an allele and the other side aligned equally to both alleles (AMB), were re-classified as allelic reads, only if both reads aligned to the same chromosome (cis). f, Cartoon explaining the re-assignment of 129:amb or cast:amb cis interactions. g, Scheme for ATAC–seq library preparation. Cells are lysed followed by incubation with adaptor-loaded hyperactive Tn5 transposase. The transposase integrates into accessible DNA, and these fragments are then directly amplified and sequenced. h, Scheme for allele-specific ATAC–seq data analysis. i, SNP-mapping simulation. For each SNP location on the X chromosome, all overlapping 50 bp reads were extracted (50 total) for each of the 129 and Cast alleles. All reads were then processed through the Hi-C and ATAC–seq mapping pipelines described in the Methods to measure assignment accuracy. Results are shown in the table.

Extended Data Figure 2. Structure of the Xa chromosome in ES cells, compartment analysis and characterization of interactions between genes that escape XCI

a, Allele-specific Hi-C contact maps for X chromosome in ES cells at 500-kb resolution (top), and for a ~40-Mb region centred around the DXZ4-containing locus at 40-kb resolution (bottom). The insulation score is plotted at the bottom of each 40-kb heat map as in Fig. 1a. Purple shaded areas indicate the IQR of insulation scores along the chromosome. b, Zoomed in view of three regions showing Hi-C interactions, RNA-seq and ATAC–seq signal on the Cast and 129 Xa chromosomes in ES cells. c, Compartment profiles of X chromosome in ES cells and NPCs. The first eigenvector (PC1) of each allele-specific Hi-C contact map, obtained with principal component analysis, is shown, together with the difference in chromosome-wide insulation score between the 129 and Cast allele. A/B-compartments are evident in ES cells and NPCs along both Xa (red and blue signal), whereas the first eigenvector corresponds to the two mega-domains for the Xi chromosome in NPCs. In ES cells, both Xa chromosomes display comparable insulation profiles (difference is close to 0 along the chromosome), whereas in NPCs large differences are observed (difference in insulation fluctuates along the chromosome). Grey areas indicate regions with low SNP density that were excluded from analysis. d, Same plots as in Fig. 2e for the same set of genes that escape XCI in NPCs, but using Hi-C data obtained in ES cells. e, As in d, where the interactions between loci that escape XCI on the wild-type Xi chromosome were divided in three different groups, according to whether pairs of loci belong to the same or different mega-domains. Interactions across the mega-domain boundary only occur on the wild-type Xi chromosome and are lost on the ΔFT Xi chromosome concomitant with loss of transcription of constitutive escapees.

Extended Data Figure 3. Comparison of allele-specific Hi-C maps of chromosomes X and 13 in ES cells, NPCs and boundary-mutant ΔFT NPCs

a, Hi-C data, insulation scores, and the difference in insulation scores (129 Cast) are shown for ES cells, NPCs and mutant ΔFT NPCs for both alleles (Cast and 129) for the X chromosome. Large dips in the insulation vector are found at TAD boundaries. Peaks in the insulation vector are found towards the centre of each TAD. The insulation difference plot highlights areas of differential TAD structure between the alleles (many differences along the X chromosome in NPCs as compared to the allelic differences along autosomes, see b). b, Same as a for chromosome 13. The insulation difference plot highlights areas of differential TAD structure between the alleles (rare).

Extended Data Figure 4. Quantitative analysis of 3D DNA FISH on the Xa and Xi chromosomes

a, Top left, scheme of the procedure used to quantify the Pearson correlation. A background is generated for each xy plane in a three-dimensional z-stack by morphological opening the image with a circle of 5 pixels in radius, and subtracted from it. Pearson correlation between red and green pixel intensities is measured inside a fixed-size region of 40 × 40 × 20 pixels (5.16 × 5.16 × 4 μm) centred on each FISH signal. To demonstrate that background subtraction does not affect the measured correlations, we show here a line-scan of 10 μm across a typical DNA FISH signal (top right). The shape of the signals along the line scan, as well as their relative intensities, is not affected by background subtraction (bottom). Pre- and post- refer to line scans taken on images before and after background subtraction, respectively. b, In more than 80% of nuclei in NPCs, Pearson correlations are higher on the Xi than on the Xa chromosome. Shown is NPC clone C2 (the same where Hi-C was performed). c, Same quantification as in Fig. 1c (and b) for an independent NPC clone (E1) where the active X is on the 129 allele and the inactive X chromosome on the Cast, and in astrocytes derived from NPC clone C2. n denotes the number of cells analysed in DNA FISH. Centre lines represent medians; crosses denote experimental points that were considered as outliers (larger than (q3 + 1.5 × (q3 − q1) or smaller than q1 − w(q3 − q1), where q1 and q3 are the twenty-fifth and seventy-fifth percentiles of the data distribution, respectively). d, Scheme of the gyration tensor based analysis of FISH volumes (see Methods). e, Left, gyration radii of DNA FISH signals from probes a, b and c. Probe b was used in combination with both probes a and c separately in two independent experiments. Statistical significance was assessed by Wilcoxon’s rank sum test (*P < 0.05, **P < 1 × 10⁻⁵). The mean gyration radii for Xa and Xi chromosome signals are indicated by dotted lines as a guide for the eye. On the Xi chromosome, the mean gyration radius is approximately 6% smaller than on the Xa chromosome corresponding to approximately 20% smaller volume. Right, representative images of probe a, showing smaller size and increased roundness of the Xi chromosome signals. f, Left, scheme of the thresholding-based method for volume quantification. Thirty increasing threshold levels were imposed, starting from the residual grayscale background level surrounding the signal, up to the minimum between the red and green channel grayscale maxima. For each of these thresholds we determined the number of voxels in each channel, where the greyscale intensity was higher than the threshold. Centre, the fraction of cells where the Xa chromosome signal is larger than the Xi chromosome is between 60% and 80% in the entire threshold range. Right, in a wide range of thresholds, the volume of Xa chromosome signals is approximately 25% bigger than Xi chromosome signals. Results are shown here for probes a and b; the same holds for probe c (not shown). n denotes the number of cells analysed in DNA FISH. Centre lines: medians. Boxes: middle 50% of data points. Two biological replicates were analysed for each experiment.

Extended Data Figure 5. Integrative analysis of allele-specific Hi-C, RNA-seq and ATAC–seq

a, X-chromosome-wide ATAC–seq and RNA-seq in ES cells and NPCs. ATAC shows signal for ambiguous, 129- and Cast-specific reads in ES cells and NPCs. RNA-seq shows total signal as well as expressed gene calls. ATAC–seq shows global loss of chromatin accessibility and expression on the Xi chromosome, except at specific locations that mostly overlap with escape genes. Dotted line denotes megadomain boundary. Position of constitutive escapees was adapted from ref. . b, Escape genes on the Xi chromosome (as determined by RNA-seq) fall within regions with high ATAC–seq signal (Kolmogorov–Smirnov test P < 2.2 × 10⁻¹⁶). c, Pie charts showing the distribution of peaks that escape XCI versus the peaks that are unique to the Xa chromosome. Peaks are classified into those that are promoter-proximal (within 5 kb of TSS) and distal (>5 kb from TSS). Annotations are based on binding sites identified by ChIP–seq^,. d, Scatter plot showing the relationship between TAD signal (insulation score) and number of expressed genes of the wild-type NPC 129 (Xi) Hi-C data set. The y axis shows the mean insulation score in a 480-kb window with a 40-kb step size. The x axis shows the number of expressed genes in a 480-kb window with a 40-kb step size. The Pearson R value (0.395) is shown above and is calculated on only the middle 90% (red points) of the residuals. Outliers are shown in black (bottom 5% and top 5% of residuals)

Extended Data Figure 6. Analysis of wild-type and boundary-mutant ΔFT NPCs by FISH and RT–PCR followed by pyrosequencing

a, Scheme of the strategy used to delete the mega-domain boundary region in ES cells and to derive ΔFT NPCs. b, RNA FISH against constitutive and facultative escapees confirms RNA-seq and ATAC–seq results in the ΔFT NPC clone D9B2. Top, the positions of BAC probes (RP23-328M22 and RP23-436K) are shown relative to the escape genes that they span. Coloured gene names correspond to transcripts that were detected with specific fosmid probes. Bottom, sample RNA FISH images showing that expression of facultative (Mecp2 and BAC probes) but not constitutive (Jaridlc) escapees is lost on the ΔFT Xi chromosome. c, Quantification of the RNA FISH experiment in b. d, RT–PCR followed by pyrosequencing of Xist, two facultative escape genes (Huwel and Mecp2) and the constitutive escapee Jaridlc indicate the percentage of expression from the 129 allele (red) or the Cast allele (blue) in 56 wild-type and 17 ΔFT NPC clones. Absence of Mecp2 and Huwel escape is observed in a moderately higher proportion of ΔFT than wild-type clones. Absence of Jaridlc escape is never observed.

Extended Data Figure 7. Allele-specific Hi-C analysis of wild-type and boundary-mutant ΔFT NPCs

a, Hi-C data, insulation scores, and the difference in insulation scores are shown to compare the wild-type Xi chromosome (NPC 129) and the ΔFT Xi chromosome (NPC 129). Top, the Cast allele (Xa chromosome) for both samples. Bottom, the 129 allele (Xi chromosome) for both samples. Large dips in the insulation vector are indicative of TAD boundaries. Peaks in the insulation vector are found towards the centre of each TAD. The insulation difference plot highlights areas of differential TAD structure between the wild-type and ΔFT NPCs. b, Cumulative plots of TAD strength at the wild-type expressed versus the wild-type silenced genes on Cast and 129 chromosomes, for ES cells, wild-type and ΔFT NPCs. Escapee genes on the Xi chromosome (NPC 129, ΔFT NPC 129) show higher insulation scores as compared to silenced genes.

Extended Data Figure 8. 3D DNA FISH and integrative ATAC–seq/RNA-seq analysis in ΔFT NPCs

a, Top left, scheme of the DNA FISH probe sets (a–b: inside the same mega-domain, b–c: across the boundary). Bottom, loci detected by probe set b–c are more interacting in the ΔFT than in the wild-type Xi chromosome both in Hi-C (left) and in 3D-DNA FISH (right), showing loss of mega-domain boundary. *P < 2 × 10⁻⁴, **P < 1 × 10⁻⁵ (Wilcoxon’s rank sum test corrected with Bonferroni for multiple hypothesis testing). Right, sample RNA/DNA FISH images showing that signals from probe set b–c are more overlapping on the ΔFT Xi than on the wild-type Xi chromosome. Two biological replicates were analysed. b, Chromosome-wide ATAC–seq and RNA-seq signal generated with ambiguous (mm9), 129- and Cast-specific reads in wild-type NPCs and ΔFT NPCs, showing global loss of chromatin accessibility on the ΔFT Xi chromosome except at the X-inactivation centre (Xic) region and constitutive escape genes. Dotted line indicates the position of the mega-domain boundary. c, Zoomed-in view of a region on the ΔFT Xi chromosome encompassing the Xic showing Hi-C interactions, RNA-seq and ATAC–seq signal. ATAC–seq from wild-type NPCs is included for reference (previously shown in Fig. 1).

Extended Data Figure 9. 3D DNA FISH and integrative Hi-C/ATAC-seq analysis of inducible Xist ES cell lines

a, Left, schematic representation of TXY and TXY:ΔA male cell lines, carrying a tetracycline-inducible wild-type and A-repeat mutant Xist, respectively, at the endogenous Xist locus. Centre right, RNA FISH against G6pdx and a group of genes recognized by the RP23-436K BAC (see Extended Data Fig. 6b) showing that expression of X-chromosome-linked genes is lost upon induction of wild-type but not A-repeat mutant Xist in male ES cells. TXY and TXY: ΔA were treated with doxycycline for 48 h. b, Representative images from RNA/DNA FISH experiments in TXY and TXY: ΔA male ES cell lines, showing increased overlap of probes a–b on the Xist-coated X chromosome after 48 h of wild-type, but not ΔA Xist induction. c, Left, schematic representation of TX1072 female ES cells in which Xist expression can be induced via a tetracycline-responsive promoter at one of the two endogenous Xist loci. Center right, RNA/DNA FISH in TX1072 cells treated for 3 days with doxycycline. Probes a–b overlap more on the Xist-coated than on the wild-type X chromosome, whereas signals from b–c show lower overlap and partitioning of the Xist-coated chromosome into two separate domains. *P < 1 × 10⁻⁷ (Wilcoxon’s rank sum test corrected with Bonferroni for multiple hypothesis testing). n denotes the number of cells analysed in DNA FISH. Centre lines: medians. Boxes: middle 50% of data points. Two biological replicates were analysed. d, Correlation between changes in Hi-C interactions and ATAC–seq signal following 48-h wild-type Xist induction in male ES cells (TXY cell line). log₂(+dox/−dox) was calculated for bins of 40 kb (left), 100 kb (middle), and 500 kb (right). e, Model of mega-domain boundary-mediated control of chromosome folding and facultative escape. Xist coating causes gene silencing and initiates chromosome-wide conformational changes in a manner dependent on its A-repeat region, which result in formation of mega-domains, overall compaction of chromosome folding, and loss of TADs. During differentiation, transient interactions with the megadomain boundary may occur and may contribute to facultative escape and re-establishment of TADs at facultative escape loci, although the presence of residual TADs at escapee loci on the Xi chromosome is not necessarily due to the mega-domain boundary.

Figure 1. The distinct conformation of the Xi and Xa chromosomes

a, Allele-specific Hi-C maps of the Xa and Xi chromosomes in NPCs (left), and two increasingly smaller regions centred around DXZ4 (centre and right). Purple areas in the insulation score plots indicate the interquantile range (IQR) of insulation scores over the entire X chromosome, to illustrate reduced insulation scores along the Xi chromosome (indicating loss of TADs). Black arrow: position of a residual TAD. Red arrow: position of DXZ4. b, Top, scheme of DNA FISH probes. Bottom, probes a–b (within the same mega-domain) are more overlapping and spherical on the Xi than on the Xa chromosome, whereas signals from b–c (across the mega-domain boundary) show partitioning on the Xi chromosome into two separate domains. c, Loci detected by probes a–b are more interacting than b–c on the Xi chromosome, in both Hi-C (top) and 3D-DNA FISH (bottom). *P < 8 × 10⁻¹⁷ (Wilcoxon’s rank sum test corrected with Bonferroni). NS, not significant. n denotes number of cells analysed in DNA FISH. Centre lines: medians, all experiments were performed in biological duplicates.

Figure 2. Expression, chromatin accessibility and chromatin conformation along the Xi chromosome

a, Hi-C interactions, insulation score, ATAC–seq signal and location of expressed genes (via RNA-seq) in three regions of the Xa and Xi chromosome. Left to right: the cluster of facultative escape genes containing Mecp2, the Xist locus and the region encompassing Jaridlc. Hi-C data are shown at 40-kb resolution. b, Regions with increased TAD structure harbour promoters that are expressed and accessible on the Xi chromosome, as shown by analysis of Hi-C insulation (TAD structure), ATAC–seq read counts, and RNA-seq reads per kilobase of transcript per million mapped reads (RPKM). Each column represents a promoter, sorted by insulation score in the 40-kb interval containing the promoter, lowest-to-highest (weakest-to-strongest TAD signal). ATAC counts are extracted from promoters (TSS ± 500 base pairs (bp)). c, Xi-chromosome-expressed genes (escapees) fall within regions with higher insulation scores on the Xi chromosome as compared to Xi-chromosome-silenced genes (*P = 4.44 × 10⁻¹⁶, Fisher exact test test), despite having similar insulation scores on the Xa chromosome (P = 0.43114, Kolmogorov–Smirnov test). d, ATAC–seq peaks on the Xi chromosome tend to be closer to TSSs (within 5 kb) than peaks on autosomes and the Xa chromosome (statistical significance was assessed by Fisher exact test). e, Interaction pile-up maps showing mean Hi-C signal for all pairwise combinations of the 87 wild-type NPC Xi chromosome escapees on the both the Xa and the Xi chromosome.

Figure 3. Deletion of the mega-domain boundary leads to loss of bipartite folding

a, Hi-C contact maps for Xa (Cast) and Xi (129 ΔFT) chromosomes in mega-domain boundary mutant NPCs (left), and for increasingly smaller regions (centre and right). b, Two regions on the ΔFT Xi chromosome showing Hi-C, RNA-seq and ATAC–seq signal. The same regions as in Fig. 2a are shown. ATAC–seq and RNA-seq from the Xi chromosome in wild-type NPCs are included for reference (shown in Fig. 2a). c, Loss of TAD structure in ΔFT NPCs correlates with loss of accessibility (ATAC) and expression (RPKM). Each column represents a promoter. Heat maps are sorted by change in TAD strength (insulation score) from wild-type to ΔFT Xi in the 40-kb interval containing the promoter. ATAC counts are extracted from promoters (TSS ± 500 bp TSS). d, Interaction pile-up map showing mean interaction signal in ΔFT NPCs for all pairwise combinations of the 87 wild-type NPC Xi chromosome escapees. e, Quantification of ATAC–seq peaks in wild-type and ΔFT NPCs on the Xi chromosome. Of 224 Xi chromosome peaks in the wild type, 139 are lost in the mutant. f, Chromatin immunoprecipitation followed by sequencing (ChIP–seq) annotation of ATAC–seq peaks lost in ΔFT NPCS. g, Distance from TSS of ATAC–seq peaks that are lost, or do not change, after deletion of the mega-domain boundary. h, Distance from escapee TSS of CTCF peaks that are lost in ΔFT NPCs, do not change in ΔFT NPCs, and peaks on the Xa chromosome.

Figure 4. Xist-mediated silencing is sufficient to generate a boundary at DXZ4 in ES cells

a, Top, Hi-C analysis on the X chromosome in male ES cells expressing wild-type (WT) or A-repeat mutant (ΔA) Xist, before (−dox) and after (+dox) 48 h induction. dox, doxycycline. Bottom, correlation analysis of male X chromosome and NPC Xi chromosome Hi-C maps, showing increased similarity between the male Xist-coated X and Xi chromosomes after induction of wild-type, but not ΔA Xist. b, Alignment of structural changes detected in Hi-C and changes in chromatin accessibility measured by ATAC–seq after 48 h of wildtype or ΔA Xist expression. Dashed line: DXZ4 position. Arrowheads: increased interactions on either side of the mega-domain boundary. Asterisk: genomic position of Firre. c, RNA/DNA FISH showing increased overlap of probes a–b on the Xist-coated X chromosome after 48 h of wild-type, but not ΔA Xist induction. Probes b–c show lower overlap (indistinguishable from non-Xist coated chromosomes in cells where Xist expression was not induced after doxycycline treatment), in line with Hi-C predictions (see Methods). Xist− signals correspond to the −dox sample. *P < 0.05 (Wilcoxon’s rank sum test corrected with Bonferroni). n denotes number of cells analysed in DNA FISH. Centre lines: medians. Boxes: middle 50% of data points. Two biological replicates were analysed. d, Changes in Hi-C contact probability after 48 h of wild-type or ΔA Xist expression, indicating a wild-type Xist-specific increase in contact probability on the X chromosome. e, Changes in the ATAC–seq signal at X chromosome and autosomal peaks, indicating wild-type Xist-specific loss of chromatin accessibility on the X chromosome.