Global reorganization of replication domains during embryonic stem cell differentiation

Abstract

DNA replication in mammals is regulated via the coordinate firing of clusters of replicons that duplicate megabase-sized chromosome segments at specific times during S-phase. Cytogenetic studies show that these "replicon clusters" coalesce as subchromosomal units that persist through multiple cell generations, but the molecular boundaries of such units have remained elusive. Moreover, the extent to which changes in replication timing occur during differentiation and their relationship to transcription changes has not been rigorously investigated. We have constructed high-resolution replication-timing profiles in mouse embryonic stem cells (mESCs) before and after differentiation to neural precursor cells. We demonstrate that chromosomes can be segmented into multimegabase domains of coordinate replication, which we call "replication domains," separated by transition regions whose replication kinetics are consistent with large originless segments. The molecular boundaries of replication domains are remarkably well conserved between distantly related ESC lines and induced pluripotent stem cells. Unexpectedly, ESC differentiation was accompanied by the consolidation of smaller differentially replicating domains into larger coordinately replicated units whose replication time was more aligned to isochore GC content and the density of LINE-1 transposable elements, but not gene density. Replication-timing changes were coordinated with transcription changes for weak promoters more than strong promoters, and were accompanied by rearrangements in subnuclear position. We conclude that replication profiles are cell-type specific, and changes in these profiles reveal chromosome segments that undergo large changes in organization during differentiation. Moreover, smaller replication domains and a higher density of timing transition regions that interrupt isochore replication timing define a novel characteristic of the pluripotent state.

Figure 1. Genome-Wide Analysis of Replication Timing in mESCs

(A) Protocol for genome-wide replication timing analysis using oligonucleotide microarrays with one probe every 5.8 kb. (B and C) Generating replication-timing profiles. An exemplary mESC replication-timing profile of a Chromosome 1 segment is shown. Raw values for probe log ratios [i.e., log₂(Early/Late)] along the chromosome revealed a clear demarcation between regions of coordinate replication (B), which is highlighted upon overlaying a local polynomial smoothing (loess) curve (C). (D) Analyses at a density of one probe per 5.8 kb or 100 bp show essentially identical smoothed replication-timing profiles.

Figure 2. Replication Domain Structure and Its Conservation between Three Independent mESC Lines

(A) Identification of replication domains (red lines) and their boundaries (dotted lines) by a segmentation algorithm [32]. (B) Box plots of early (E; log ratio > 0) and late (L; log ratio < 0) replication domain sizes. Horizontal bars represent the 10th, 25th, 50th (median), 75th, and 90th percentiles, respectively. (C and D) Three different mESC lines (D3, 46C, and TT2) showed remarkably similar replication domain organization, as revealed by visual inspection of a segment on Chromosome 1 (C) and high Pearson R ² values for pair-wise comparisons (D). (E) A scatter plot of replication-timing differential versus physical distance (Mb) between the ends of 75 randomly chosen pairs of adjacent replication domains (replication-timing transition regions) from Chromosomes 2, 11, and 16 (25 each) revealed a positive correlation with a slope that is consistent with mammalian replication fork speeds. A time scale is provided, based on the assumption that replication-timing ratio difference of three roughly corresponds to an approximately 10-h S-phase.

Figure 3. Global Reorganization of Replication Domains upon Differentiation of ESCs to NPCs

(A) Replication domain profiles change dramatically upon differentiation of ESCs to NPCs. An exemplary Chromosome 7 segment is shown. (B and C) NPCs derived from distinct neural differentiation schemes and three independent mESC lines showed fairly similar replication timing profiles, both by visual inspection (B) and high Pearson R ² values for pair-wise comparisons of NPCs (C). The low R ² values for pair-wise comparisons of ESCs and NPCs confirm that substantial changes occurred upon differentiation (C). (D–G) Exemplary EtoL (Early-to-Late) (D and E) and LtoE (Late-to-Early) (F and G) consolidation. (H) Schematic representation of domain consolidation, boundary shift, and isolation. (I) Summary of replication domain properties in ESCs and NPCs. (J) Replication domain sizes by chromosome. Chromosome Y was underrepresented on the microarray and was excluded from the analysis. (K) Box plots of sizes of domains that changed replication timing (EtoL and LtoE), as well as early- and late-replicating domains in NPCs. EtoL and LtoE domains show smaller and tighter distribution than domains in NPCs or ESCs (Figure 2B).

Figure 4. Domain Consolidation Aligns Replication Timing to GC/LINE-1 Content but Not Gene Density

(A and B) Loess-smoothed replication-timing profiles of ESCs (blue) and NPCs (green) were overlaid with moving averages of 500-kb windows of GC (A) and LINE-1 (B) content for a segment on Chromosome 8. Grey highlighted areas show regions where differentiation aligns replication timing to GC/LINE-1 content. (C–F) Average replication-timing ratios of replication domains in ESCs (C and E) and NPCs (D and F) were plotted against their GC content (C and D) and LINE-1 content (E and F). Pearson's R ² values are shown. (G) EtoL and LtoE domains have an unusual combination of GC/LINE-1 content and gene density. Domains with the 5% greatest replication-timing changes were defined as EtoL and LtoE, whereas those with the least changes (lowest 20%) that maintained replication timing ratio of above 0.5 or below −0.5 were defined as EtoE and LtoL, respectively. Genes/Mb refers to RefSeq gene density. (H) Correlation of gene density and replication timing at the level of domains in ESCs and NPCs. Pearson R ² values are shown. (I) Scatter plot of GC content and gene density shows that EtoE, LtoL, LtoE, and EtoL domains are generally GC rich/gene rich, GC poor/gene poor, GC rich/gene poor, and GC poor/gene rich, respectively. (J and K) Replication domain structure of iPS cells matches that of ESCs both by visual inspection (J) and high Pearson R ² values for pair-wise comparisons of iPS to ESCs (K).

Figure 5. Replication Timing and Transcription Changes during Differentiation

(A and B) Average replication-timing ratios of replication domains were plotted against their “present” (i.e., transcriptionally active) gene density for ESCs (A) and NPCs (B). Pearson R ² values are shown. (C and D) Correlation between early replication and the probability of expression. Genes were ranked by their replication-timing ratio and divided into bins of 100 genes, the height of which represents the percentage of active (i.e., ”present”) genes within each bin. The width and position of each bin represents its range of replication-timing ratios. Logistic regression (inner line) and 95% confidence intervals (outer lines) reveal a clear correlation in both ESCs (C) and NPCs (D). By the Likelihood Ratio test (a goodness-of-fit test), the fitted model is significantly different (p < 2 × 10⁻¹⁶ for both ESCs and NPCs) from that of a null hypothesis in which replication timing has no correlation to transcription. (E) Box plots showing the fold changes in transcription [i.e., log₂(NPC/ESC)] of LtoE, EtoL, LtoL, and EtoE genes. RefSeq genes with the 5% greatest replication timing changes were defined as EtoL and LtoE, whereas those with the least changes (lowest 20%) that maintained replication timing ratio of above 0.5 or below −0.5 were defined as EtoE and LtoL, respectively. (F) Percentage of 2-fold up- or down-regulated genes within LtoE, EtoL, LtoL, and EtoE domains defined in Figure 4G. (G) Summary of expression patterns of genes within LtoE, EtoL, LtoL, and EtoE domains. Definitions are as follows: “Up” and “Down,” above 2-fold up- and down-regulation, respectively; “Unchanged,” below 2-fold up-/down-regulation; “Unchanged Only,” domains with both active and silent genes that do not change by 2-fold; and “Silent Only,” domains with only silent genes in both states. (H) LINE-1 transposable elements are actively transcribed in ESCs but become inactive in NPCs as assayed by RNA-FISH. Mean and standard error of mean (SEM) of the number of RNA-FISH signals per nucleus is shown (n = 30 from two biological replicates). The p-value was obtained from a two-tailed t-test for comparison of two unpaired groups.

Figure 6. Relationship between Replication Timing and Histone Modifications

(A and B) Correlation between replication timing and H3K4me3 of RefSeq gene promoters. The graphical format is the same as in Figure 5C and 5D, except that the heights of bins represent the percentages of H3K4me3-positive genes within each bin. Logistic regression (inner line) and 95% confidence intervals (outer lines) reveal a clear correlation in both ESCs (A) and NPCs (B) (p < 2 × 10⁻¹⁶ by the Likelihood Ratio test). H3K4me3 data were based on Mikkelsen et al [51]. (C) Relationship between replication timing and histone modifications at the level of replication domains. Densities of different histone modifications (total intensity/domain size) based on a ChIP-Seq study [51] were calculated for all replication domains in a given state (ESC or NPC) and Pearson R ² values between replication timing and different histone modification densities were obtained. (D) Comparison of replication timing and different histone modifications in four exemplary 5-Mb genomic regions in ESCs and NPCs. (E) Box plots showing the distribution of replication-timing changes of “bivalently” modified genes (i.e., K4K27) in ESCs that change to four different modification state (K4K27, K27, K4, or none) in NPCs. Genes that remained “bivalent” showed a distribution similar to the three other classes. The p-values were obtained from a two-tailed t-test for comparison of two unpaired groups.

Figure 7. Transcription from Low, But Not High, CpG Density Promoters Is Coordinated with Late Replication

(A) Box plots showing the expression level of transcriptionally active (“present”) genes with different promoter CpG density (HCP, ICP, and LCP as defined in [51]), based on Affymetrix GeneChip analysis of RefSeq genes. (B and C) Box plots showing the fold changes in transcription [i.e., log₂(NPC/ESC)] of LCP, ICP, and HCP genes among EtoL (B) and LtoE genes (C). The p-values were obtained from a two-tailed t-test for comparison of two unpaired groups.

Figure 8. Global Temporal Reorganization of Replication Domains Reflects Spatial Reorganization in the Nucleus

(A and B) Analysis of subnuclear positions of eight genomic regions by 3D-FISH in ESCs and NPCs. Box plots show radial distance to the nuclear periphery, where 0 and 1 represents the periphery and the center of the nucleus, respectively. Replication-timing profiles and the probe positions (red squares) are also displayed. Three EtoL domains (Rex1, Rex2, and Dppa2 domains) and three LtoE domains (Ptn, Akt3, and Ephb1 domains) move toward and away from the nuclear periphery, respectively, upon neural differentiation. Two EtoE domains (Oct4 and Nanog) do not change subnuclear positioning. Comparable results were obtained from two to four biological replicates, and the sum of all experiments is shown. A total of 90–234 alleles were measured per state. (B) Representative FISH photographs (Dppa2 and Ptn). Dotted lines represent the rim of nuclear DAPI signals. Arrowheads represent DNA-FISH signals. (C) A model for higher-order chromosomal organization in the nucleus during neural differentiation (see Discussion). Consider an example of two adjacent isochores, one GC rich (replicon clusters 1–4) and one AT rich (replicon clusters 5–9). In ESCs, replicon clusters with an unusual combination of GC content and gene density (clusters 3, 6, and 8) replicate differently and may be spatially separated from the rest of the isochore. During differentiation, there is an increased influence of isochore sequence features on replication timing, resulting in the temporal consolidation of these deviant domains and alignment of their replication timing to isochores, possibly accompanied by spatial reorganization.