TADs are 3D structural units of higher-order chromosome organization in Drosophila

Abstract

Deciphering the rules of genome folding in the cell nucleus is essential to understand its functions. Recent chromosome conformation capture (Hi-C) studies have revealed that the genome is partitioned into topologically associating domains (TADs), which demarcate functional epigenetic domains defined by combinations of specific chromatin marks. However, whether TADs are true physical units in each cell nucleus or whether they reflect statistical frequencies of measured interactions within cell populations is unclear. Using a combination of Hi-C, three-dimensional (3D) fluorescent in situ hybridization, super-resolution microscopy, and polymer modeling, we provide an integrative view of chromatin folding in Drosophila. We observed that repressed TADs form a succession of discrete nanocompartments, interspersed by less condensed active regions. Single-cell analysis revealed a consistent TAD-based physical compartmentalization of the chromatin fiber, with some degree of heterogeneity in intra-TAD conformations and in cis and trans inter-TAD contact events. These results indicate that TADs are fundamental 3D genome units that engage in dynamic higher-order inter-TAD connections. This domain-based architecture is likely to play a major role in regulatory transactions during DNA-dependent processes.

Fig. 1. Super-resolution microscopy reveals chromatin organization into discrete nanocompartments.

(A) S2R+ Hi-C map of the labeled 3-Mb region with chromatin immunoprecipitation (ChIP) tracks of Pc and H3K4me3. Colored bars denote the positions of probes designed to label specific epigenetic domains (Blue, Black, and Red). (B) 3D-SIM image of an S2R+ nucleus labeled with the 3-Mb probe (DAPI in gray). (C) Intensity distribution (maximum projection) of the 3-Mb probe in (B). (D) Orthogonal views of the 3-Mb probe labeling in (B). (E) Schematic representation of the dual FISH Oligopaint labeling strategy. gDNA, genomic DNA. (F) Examples of dual FISH labeling (maximum projections) with the 3-Mb probe and a single epigenetic domain (Blue1, Black2, or Red1, indicated with arrowheads). Right: Intensity distributions of the two probes along the yellow line. A.U., arbitrary units. (G) Pearson’s correlation coefficient (PCC) between the 3-Mb and the single-domain probe signals. Twenty nuclei were analyzed per conditions, and PCC distributions from all repressed domains were significantly different from those of active domains (at least P < 0.01) using Kruskal-Wallis and Dunn’s multiple comparisons tests. (H) Oligopaint density (probe genomic size over 3D-segmented volume) of the single-domain probes. At least 57 nuclei were analyzed per condition, and density distributions from all repressed domains were significantly different from those of active domains (at least P < 0.05) using Kruskal-Wallis and Dunn’s multiple comparisons tests. Scale bars, 1 μm.

Fig. 2. Repressed TADs form 3D chromosomal units with dynamic contact events.

(A) Examples of chromatin labeling (single Black1 TAD, R2, R3, R4, and 3-Mb probe, maximum projections) in (top) tetraploid S2R+ and (bottom) diploid embryonic cells. (B) Number of nanocompartments counted per nucleus in S2R+ and embryonic cells for the different labeling (P < 0.0001 in all conditions with two-tailed Mann-Whitney test). Bottom: Ratio of the means (indicated with red circles) between the two conditions. n indicates the number of nuclei analyzed. (C) Examples of chromatin labeling (single Blue1 TAD, R2, R3, R4, and 3-Mb probe, maximum projections) in tetraploid S2R+ cells in (top) G₁ and (bottom) G₂ phases of the cell cycle. (D) Number of nanocompartments counted per nucleus in S2R+ cells in G₁ and G₂ phases for the different labeling (P < 0.0001 in all conditions with two-tailed Mann-Whitney test, except for R2, P < 0.01). Bottom: Ratio of the means (indicated with red circles) between the two conditions. n indicates the number of nuclei analyzed. (E) Mean (±SD) number of nanocompartments counted per S2R+ cells in G₁ phase (top) or in embryonic cells (bottom) as a function of the number of TADs for Black1, R2, R3, and R4 labeling. R² values of linear regressions are indicated. (F) 3D view of single chromosome copies labeled with the 3-Mb probe. Nanocompartment positions are represented with 150-nm-diameter beads. (G) Pairwise distances between all nanocompartments identified in the individual chromosomes shown in (F) (one boxplot corresponds to one chromosome). Right: Averaged distance distribution from all the single chromosomes. (H) Number of nanocompartments counted for single chromosomes (n = 19). Scale bars, 1 μm.

Fig. 3. Single-cell analysis of haploid chromosome reveals consistent TAD-based chromatin compartmentalization.

(A) Sixteen- to 18-hour male embryo Hi-C map with H3K4me3 ChIP-seq profile (14- to 16-hour embryos) and FISH probe positions. (B) Representative examples of triple FISH-labeled nuclei (confocal microscopy, z slices) with probes 1 (green), 2 (red), and 3 (blue) and 3D distance distributions (from 115 nuclei) between the probes. (C) Scatter plot of paired distances between probes 2 and 1 (x axis) and probes 2 and 3 (y axis). The proportions of intra-TAD (2-1) distances shorter or larger than inter-TAD (2-3) distances are indicated (75 and 25%, respectively). (D) Representative examples of 3D-SIM images (maximum projections) of TAD 1, TAD 2, spanning, and full probes. (E) Number of FISH local maxima detected per nucleus with the different probes (at least 102 nuclei were analyzed per condition). (F) Representative examples of 3D-SIM images (maximum projections) of TAD 1 and TAD 2 double FISH experiments and quantification of the overlap fraction between TAD 1 and TAD 2 probes (38 nuclei were analyzed). Statistics were performed with Kruskal-Wallis and Dunn’s multiple comparisons tests. ***P < 0.0001. Scale bars, 1 μm.

Fig. 4. Integrative view of chromosome conformation with polymer modeling.

(A) Inferred (top) and experimental (bottom) contact probability maps. (B) Distributions of the differences between the paired distances (D) (2-1) and (2-3) from FISH experiments (red) and inferred model (gray). Values on the left of the dashed line indicate shorter intra-TAD than inter-TAD distances. (C) Cumulative distribution of the overlap fraction between TAD 1 and TAD 2 obtained from simulated conformations (full line) and from conformations when the inter-TAD distance (2-3) is smaller than the intra-TAD (2-1) distance (dashed line). (D) Representative examples of configurations of the inferred model, with the inter-TAD distance (2-3) larger (left) or smaller (right) than the intra-TAD (2-1) distance. Probe 1, 2, and 3 positions are represented with monomers in green, red, and blue, respectively; TAD 1 and TAD 2 are represented with magenta and cyan monomers, respectively.

Fig. 5. Large-scale chromatin folding reflects heterogeneous, discrete, and specific interdomain contacts.

(A) Sixteen- to 18-hour embryo Hi-C map of a 14-Mb region, along with ChIP-seq profiles of Pc and H3K4me3 (14- to 16-hour embryos). We designed a set of epigenetic state-specific probes (Blue, Black, and Red domains, indicated with colored bars) to perform two-color labeling of domains of the same type that were consecutive along the linear scale of the chromosome (that is, Blue-Blue, Black-Black, and Red-Red) or for different combinations of chromatin type (that is, Blue-Black, Blue-Red, and Black-Red). (B) 3D-SIM images from different two-color FISH labeling combinations in embryonic cells (maximum projections). Scale bar, 1 μm. (C) Distribution of all the pairwise distances between all differentially labeled domains in the different FISH combinations. Each line of the heat maps represents distance distribution within single-cell (color-coded in the percentage of all the distances within the cell). On top of each heat map, the distribution of the distances for the whole cell population is plotted, and dashed line indicates median. On the right of each heat map, the number of distances is <150 nm per cell (n contacts). Twenty nuclei (>1800 distances in total) were analyzed per condition. The broad distributions in all FISH combinations indicate a limited extensive clustering of the domains of the same epigenetic status. (D) Nearest-neighbor distance distributions for each labeling combination in wild-type (WT) and ph^del 12- to 16-hour embryos. The x axis is split into 150-nm bins. n indicates the number of distances (measured in at least 30 nuclei) for each condition. Statistics were performed using Kolmogorov-Smirnov tests; ***P < 0.001, **P < 0.01, *P < 0.05. The depletion of very short range distances in Blue-Red and Black-Red distributions suggests that active chromatin is spatially segregated from inactive chromatin at the nanoscale. NS, not significant. (E) Percentages of nearest-neighbor distances <150 nm in WT embryos versus ph⁵⁰⁵ embryos, showing the specific loss of contacts between Blue domains. Statistics were performed using two-tailed Fisher’s exact tests, ***P < 0.0001. (F) Genome-wide differential Hi-C contact scores (log₂ ph⁵⁰⁵/WT normalized scores) between the chromatin domains in WT male versus ph⁵⁰⁵ male embryos show the specific loss of contacts between Blue domains. (G) Side-by-side Hi-C map of WT male (top) and ph⁵⁰⁵ male embryos (bottom) showing specific loss of contacts between Blue TADs in ph⁵⁰⁵ (indicated with circles). The contact enrichment color scale is the same as in (A).