Genome-wide studies highlight indirect links between human replication origins and gene regulation

Abstract

To get insights into the regulation of replication initiation, we systematically mapped replication origins along 1% of the human genome in HeLa cells. We identified 283 origins, 10 times more than previously known. Origin density is strongly correlated with genomic landscapes, with clusters of closely spaced origins in GC-rich regions and no origins in large GC-poor regions. Origin sequences are evolutionarily conserved, and half of them map within or near CpG islands. Most of the origins overlap transcriptional regulatory elements, providing further evidence of a connection with gene regulation. Moreover, we identify c-JUN and c-FOS as important regulators of origin selection. Half of the identified replication initiation sites do not have an open chromatin configuration, showing the absence of a direct link with gene regulation. Replication timing analyses coupled with our origin mapping suggest that a relatively strict origin-timing program regulates the replication of the human genome.

Fig. 1.

Strong origins are not evenly distributed along the genome, and a subset of origins is associated with CpG islands. (A) Histogram of the interorigin distances (median = 36080; n = 245). Four interorigin distances greater than 260 kb (333, 411, 453, and 480 Kb) are not shown on the graph. (B) Origin density within ENCODE regions correlates with GC richness. The density of origins within each ENCODE region (number of origins per 100 kb) is plotted against the GC percent of the whole region. (C) Origins are enriched in and near CpG islands. The histogram shows the distribution of origin centers relative to CpG islands (CGI). Negative values correspond to origin centers located within CpG islands. The line shows the distribution of the bootstrap sample. (D) Segments containing non-CpG island origins are not enriched in GC. For each ENCODE region, the GC percentage of replication origin segments within CpG islands (red) and outside CpG islands (blue) is plotted against the GC percentage of the whole ENCODE region.

Fig. 2.

Origins are strongly associated with regulatory elements but are not favored by open chromatin structure.(A) Chromosomal features corresponding to open chromatin structures are enriched inside origins. This graph shows the percentage of replication origin segments (blue) and bootstrap segments (red) overlapping CpG islands (CGI), HS sites, H3ac, H4ac, H3K4me1 (K4me1), H3K4me2 (K4me2), and H3K4me3 (K4me3) segments. (B) H3K4me3 is not associated preferentially with replication origins. The Venn diagram shows the overlap between replication origin segments, CpG islands (CGI), and H3K4me3 regions. The number of segments found in each group is shown between brackets, and the number of overlapping elements is in intersected regions. (C) Origins of replication are found mostly inside regulatory elements. This graph shows the cumulative percentage of segments overlapping HS sites found in 7 cell lines. The HS sites were added in the following order: HeLa-specific sites (TS H), HeLa (H), GM06990 (H + 1), CD4, HepG2, H9, IMR 90, and K562 cells. The blue and the red lines represent the overlap with origin segments and with 283 random segments, respectively. (D) c-JUN and c-FOS binding sites are enriched inside origins. This graph shows the percentage of replication origin segments (blue) and bootstrap segments (red) overlapping with c-JUN and c-FOS segments. (E) CpG islands (CGI) bound by c-JUN are good substrates for replication initiation. The Venn diagram shows the overlap between replication origin segments, CGI, and c-JUN regions. The number of segments found in each group is shown between brackets, and the number of overlapping elements is given in the intersected regions. (F) c-JUN origins are associated with open and closed chromatin. The 55 c-JUN origins were intersected with CpG islands (CGI), HS sites, and H3K4me3 regions. The histogram shows the number of c-JUN origins in each of the 8 possible classes ranged from the largest to the smallest.

Fig. 3.

Isolated origins and clusters of closely spaced origins are activated at all stages in S phase. (A) Replication timing profiles obtained after BrdU pulse labeling, cell sorting, and quantitative PCR were classified into 5 groups according to the enrichment found in fractions S1 to S4. Typical early (E), mid-early (ME), middle (M), mid-late (ML), and late (L) profiles are shown. (B) Timing analysis of highly dense and isolated origins. ENCODE regions, primer pair coordinates used for qPCR, replication timing, and origin class are indicated