Comparative Hi-C reveals that CTCF underlies evolution of chromosomal domain architecture

Abstract

Topological domains are key architectural building blocks of chromosomes, but their functional importance and evolutionary dynamics are not well defined. We performed comparative high-throughput chromosome conformation capture (Hi-C) in four mammals and characterized the conservation and divergence of chromosomal contact insulation and the resulting domain architectures within distantly related genomes. We show that the modular organization of chromosomes is robustly conserved in syntenic regions and that this is compatible with conservation of the binding landscape of the insulator protein CTCF. Specifically, conserved CTCF sites are co-localized with cohesin, are enriched at strong topological domain borders, and bind to DNA motifs with orientations that define the directionality of CTCF's long-range interactions. Conversely, divergent CTCF binding between species is correlated with divergence of internal domain structure, likely driven by local CTCF binding sequence changes, demonstrating how genome evolution can be linked to a continuous flux of local conformation changes. We also show that large-scale domains are reorganized during genome evolution as intact modules.

Graphical abstract

Figure 1

Evolution of CTCF Binding Correlates with Hi-C Domain Structure (A) Representative CTCF ChIP-seq tracks on mouse (Mmus) chromosome 5; dog (Cfam) and macaque (Mmul) tracks are shown after liftOver to the mouse genome (mm10). Sites conserved across all three species (arrowhead) or specific to a single species (asterisks) are indicated as examples. (B) A pairwise comparison of mouse CTCF ChIP and dog CTCF ChIP (liftOver track), identifying conserved or divergent binding sites (see Experimental Procedures). (C) A comparison of the interspecies difference in CTCF ChIP signal against the difference in CTCF motif affinity in mouse versus dog. Scatterplots are highlighted for conserved (Mmus+/Cfam+, blue), mouse-divergent (Mmus+/Cfam−, black), and dog-divergent sites (Mmus−/Cfam+, green). (D) A representative 2-Mb region from chromosome 5 of the mouse Hi-C contact maps. Also shown are the mouse (Mmus) CTCF ChIP track and conserved (Mmus+/Cfam+, blue) and divergent (Mmus+/Cfam−, gray) CTCF sites. (E) Genome-wide relative position of conserved and divergent CTCF sites within mouse Hi-C domains. (F) Contact insulation analysis for conserved (Mmus+/Cfam+) and mouse-divergent (Mmus+/Cfam−) CTCF sites in the mouse Hi-C data. See also Figure S1.

Figure 2

Chromosomal Domain Structure Is Robustly Conserved in Mammals (A) Representative Hi-C contact maps of a 9-Mb syntenic region from mouse (Mmus), rabbit (Ocun), macaque (Mmul), and dog (Cfam). Maps are colored according to technically corrected contact enrichment. For scale purposes, the same size region is shown for all species, but in the macaque and dog genome, the syntenic region is reduced in size. The portion of the map that is outside of the synteny boundary is shaded out. Shown above each map is the quantification of contacts for distance bands of 160–480 kb (crossover 160 kb) and 80–240 kb (crossover 80 kb), as well as a track of orthologous genes, highlighting their conserved distribution in chromosomal domains. (B) A zoom in of the domain highlighted with a white dashed box in (A) reveals differences in its internal organization across species. (C) Global quantification of the correlation between the maps. Genome-wide contact enrichments between elements separated by 160–480 kb in rabbit, macaque, and dog were compared to the mouse genome after liftOver. Spearman correlation values are shown inside the plots. Axes units are contact enrichments [log₂(observed/expected)]. See also Figures S2 and S3.

Figure 3

Conserved and Divergent CTCF Sites Show Differential Contact Insulation Behavior (A) Representative Hi-C contact maps for a 2-Mb syntenic region in mouse (left panel) and dog (right panel). Also shown are the CTCF ChIP-seq tracks in each species as well as the conserved (Mmus+/Cfam+, blue) and divergent (Mmus+/Cfam−, gray or Mmus−/Cfam+, green) CTCF sites. (B) Average contact insulation analysis at conserved (Mmus+/Cfam+) CTCF sites in mouse (leftmost panel) and dog (rightmost panel) Hi-C datasets. Arrows indicate liftOver of sites. (C) Same as for (B), but for mouse-divergent (Mmus+/Cfam−) and dog-divergent (Mmus−/Cfam+) sites in both genomes. Divergent sites appear to mediate weaker, shorter-range insulation that disappears in the species where the site is not bound. (D) Distribution of the difference in contact insulation between mouse and dog at conserved or divergent CTCF sites at 20–60 kb (left panel, 20-kb band) or 80–240 kb (right panel, 80-kb band) scales. Divergent sites exhibit a significant (Kolmogorov-Smirnov test, p < 1 × 10⁻¹², marked by an asterisk) shift in their distributions in the 20-kb band, but not in the 80-kb band, compatible with them mediating insulation at a local scale, but not at higher ranges. See also Figure S5.

Figure 4

Conserved CTCF Sites Engage in Strong, Directional Interactions with Other Conserved Sites (A) Average contact insulation analysis in both Mmus and Cfam genomes for conserved (Mmus+/Cfam+) CTCF binding sites grouped according to the orientation of their binding motif. The consensus motif shown was generated from mouse binding sites. (B) Genome-wide relative position within chromosomal domains of Mmus+/Cfam+ conserved CTCF sites grouped according to the orientation of their binding motif as above. (C and D) (C) 4C-seq analysis and Hi-C maps of a 1.2-Mb syntenic region in the mouse and (D) dog genomes. Shown are 4C-seq viewpoints designed to four conserved (Mmus+/Cfam+) CTCF binding sites proximal to Hi-C domain borders and one 4C-seq viewpoint located at a mouse-divergent (Mmus+/Cfam−) CTCF site. The symbol above each 4C-seq bait indicates the strand (and orientation) of each viewpoint. Each 4C-seq experiment is represented by the median normalized 4C-seq coverage in a sliding window of 5 kb (top) and a multi-scale domainogram indicating normalized mean coverage in windows ranging between 2 kb and 50 kb. (E) Relative intra-domain contact enrichment between CTCF sites (solid lines) as a function of distance when the two sites are <5 kb away from a CTCF binding site (solid lines) or where only one site is <5 kb away from a CTCF site (dotted lines). Shown are the relative contact enrichments within repressive domains for conserved (Mmus+/Cfam+, blue), mouse-divergent (Mmus+/Cfam−, gray) and dog-divergent (Mmus−/Cfam+, green) CTCF sites in mouse Hi-C (left) and dog Hi-C (right).

Figure 5

Chromosomal Domains Evolve as Modular Units (A) A schematic of the rearrangement between mouse (gray) and dog (green). (B) Hi-C maps from a syntenic region in mouse (left) and dog (right). Shown also are CTCF ChIP tracks, conserved and divergent sites, and genes in the region. A cluster of non-orthologous Skint genes (black dots) has been inserted in mouse between the orthologous genes Slc5a9 and Trabd2b (highlighted as red dots). The inserted region (bordered in yellow) forms its own nested chromosomal domain structure, probably as a result of gene-duplication events. Highlighted in blue are other orthologous genes in the region. See also Figures S7 and S8.