Nucleosomes are well positioned in exons and carry characteristic histone modifications

Abstract

The genomes of higher organisms are packaged in nucleosomes with functional histone modifications. Until now, genome-wide nucleosome and histone modification studies have focused on transcription start sites (TSSs) where nucleosomes in RNA polymerase II (RNAPII) occupied genes are well positioned and have histone modifications that are characteristic of expression status. Using public data, we here show that there is a higher nucleosome-positioning signal in internal human exons and that this positioning is independent of expression. We observed a similarly strong nucleosome-positioning signal in internal exons of Caenorhabditis elegans. Among the 38 histone modifications analyzed in man, H3K36me3, H3K79me1, H2BK5me1, H3K27me1, H3K27me2, and H3K27me3 had evidently higher signals in internal exons than in the following introns and were clearly related to exon expression. These observations are suggestive of roles in splicing. Thus, exons are not only characterized by their coding capacity, but also by their nucleosome organization, which seems evolutionarily conserved since it is present in both primates and nematodes.

Figure 1.

Nucleosomes are well positioned at internal exons. (A) Footprints of normalized nucleosome signal in human T-cells and C. elegans in a ±1-kb window. Signals were normalized for the total number of sequenced bases and genome size. The windows are centered, from top to bottom, on transcription start sites, intron/exon junctions of internal exons, intron/exon junctions of last exons, and 3′ ends of genes. (B) Partial footprints (left) of nucleosome signal in human (black) and C. elegans (green) at internal exon starts and ends split into six groups according to exon length (bp intervals given in brackets). In the pie charts (right), the percentage of the total number of exons in each exon size category is shown for human (black) and C. elegans (green). Included exons have flanking introns that are at least 100-bp long. (C) Footprints of human nucleosome signals for the same exon categories as in A but divided according to gene expression.

Figure 2.

H3K36me3 signal is high at internal exons of highly expressed genes. Footprints of normalized (see Fig. 1) H3K36me3 (solid line) and nucleosome (dashed line) signal in human T-cells in a ±1-kb window centered at intron/exon junctions of internal exons in genes with high, medium, and low expression.

Figure 3.

H3K36me3 signal is overrepresented at internal exons with respect to succeeding introns. (A–D) Example of nucleosome (black), H3K36me3 (red), and H3K4me3 (blue) signal in the human PRRC1 (A), UHRF1BP1 (B), EXOSC9 (C), and PKM2 (D) genes. Ensembl transcripts and corresponding exons are shown below the H3K4me3 signals. Most H3K36me3 signal peaks coincide with the location of exons. (E,F) Median (dots) and interquartile ranges (vertical lines) of average normalized (see Fig. 1) H3K36me3 signal in highly expressed genes in exons (black) and the corresponding succeeding introns (gray) (left vertical axes) in human T-cells (E) and mouse embryonic stem cells (F). The exons are grouped with corresponding succeeding introns in exon–intron pairs. In each exon–intron pair, say, 3, we assure that no exon of lower rank, i.e., 1 or 2, occurs in any annotated Ensembl transcript (see Methods for details). We depict in red (right vertical axes) paired Wilcoxon signed rank test P-values on the alternative hypothesis that signal in exons is higher than in corresponding succeeding introns. The dashed red line indicates a P-value of 0.001.

Figure 4.

Some histone mark signals are higher in internal exons than in introns in a transcription-dependent manner. (A) For highly expressed genes, the average histone mark signal in exon-expression groups (low and high) (see Fig. 1) was compared to the respective medium-expressed exons to determine whether the signal was above (yellow), below (green) or at the same level (gray). The classes were determined by calculating the fold change (log₂) of the average signals in the high-expression and low-expression categories to the average signal in the medium-expression one and then further discretized to above (>0.25), below (<–0.25) or at medium (between –0.25 and 0.25) level. (B) For the alternative hypothesis, that the signal in exons (in each exon-expression group) is higher than in corresponding succeeding introns, paired Wilcoxon signed rank test P-values (-log₁₀) are depicted below each histone mark. Asterisks indicate significant (<0.001, horizontal black line) P-values. Highly relevant histone marks showing (1) any of the major identified trends in A; (2) significantly higher signal in exons than introns (B); and (3) lack of preferential accumulation at TSS-proximal regions (manual inspection) are highlighted (A). (C) Footprints of H3K36me3 (red) and H3K27me3 (blue) signals (±1-kb window) in human T-cells centered on intron/exon junctions of internal exons in highly expressed genes in the three exon-expression groups: high, medium, and low. (D) Median values and interquartile ranges of the exon average signals in the exon-expression groups high, medium, and low in Class 1 (H3K36me3, H3K79me1, and H2BK5me1), Class 2 (H3K27me2 and H3K27me3), and Class 3 (H3K27me1). Significant differences in distributions were tested for the high/medium- and low/medium-expression groups. An asterisk below or above the interquartile ranges indicates significantly (Wilcoxon rank sum test P-value < 10⁻⁵) lower or greater signal distribution compared to medium-expressed exons.

Figure 5.

Histone modifications are highly dependent on exon-expression level. Histone modification signals over gene bodies (A,C,E,G,I,K,M) and internal exons (B,D,F,H,J,L,N) related to gene- and exon-expression bins, respectively, for H3K36me3 (A,B), H3K79me1 (C,D), H2BK5me1 (E,F), H3K27me1 (G,H), H3K27me2 (I,J), H3K27me3 (K,L), and H3K4me3 (M,N). The Hoeffding's D statistic (indicated above each plot) measures the dependency of histone modification signal on expression level (see Methods for details).

Figure 6.

H3K36me3 and H3K79me1 are found at exonic nucleosomes and have a higher signal at highly expressed exons. Heat maps of nucleosome (A), H3K36me3 (B), and H3K79me1 (C) signal patterns at individual human internal exons. Rows in the heat maps correspond to 2-kb windows centered on intron/exon junctions (I/E junctions) of internal exons in highly expressed genes. Only internal exons with lengths between 100 and 300 bp and with flanking introns with lengths of at least 100 bp are shown. Each window (row in the heat map) was split into subwindows of 100 bp and the average signal calculated. The exons (rows in the heat map) are ordered according to exon expression. The gray tones were assigned using the signal quantiles of considered windows for H3K36me3, H3K79me1, and nucleosome separately. The groups of high-, medium-, and low-expressed exons (Fig. 4) are indicated with black boxes.