DNA Topoisomerase I differentially modulates R-loops across the human genome

Abstract

Background: Co-transcriptional R-loops are abundant non-B DNA structures in mammalian genomes. DNA Topoisomerase I (Top1) is often thought to regulate R-loop formation owing to its ability to resolve both positive and negative supercoils. How Top1 regulates R-loop structures at a global level is unknown.

Results: Here, we perform high-resolution strand-specific R-loop mapping in human cells depleted for Top1 and find that Top1 depletion results in both R-loop gains and losses at thousands of transcribed loci, delineating two distinct gene classes. R-loop gains are characteristic for long, highly transcribed, genes located in gene-poor regions anchored to Lamin B1 domains and in proximity to H3K9me3-marked heterochromatic patches. R-loop losses, by contrast, occur in gene-rich regions overlapping H3K27me3-marked active replication initiation regions. Interestingly, Top1 depletion coincides with a block of the cell cycle in G0/G1 phase and a trend towards replication delay.

Conclusions: Our findings reveal new properties of Top1 in regulating R-loop homeostasis in a context-dependent manner and suggest a potential role for Top1 in modulating the replication process via R-loop formation.

Fig. 1

Topoisomerase 1 depletion instigates R-loop changes genome wide. a Western blot verifying Top1 depletion upon specific siRNA transfection compared to control β-actin. b Dot blot analysis of R-loop formation: two-fold serial dilutions of genomic DNA starting at 7.5 micrograms were arrayed on a membrane and probed using the S9.6 antibody. c Distribution of DRIPc peaks gains (left) and loss (right) upon Top1 depletion across several genomic compartments depicted below. Numbers indicate the percentage occupied by each compartment. The total genomic space covered by R-loop gains and losses is indicated. (TSS) transcription start site; (PAS) poly-adenylation site. d Top; total number of uniquely mapped reads overlapping with peaks of R-loop gains (left) and losses (right) in control and Top1-depleted samples. Bottom, the relative difference in reads between gains and losses indicates that gains predominate over losses. e DRIPc-seq signal profiles for control and Top1-depleted cells over rDNA region. Average signal over two replicates is shown as solid line with standard error (shaded). Structural features of the rDNA region are on top. The 5’ETS region shows significant R-loop increase (grey shade)

Fig. 2

R-loop gains and losses occur on genes with distinct categories. a Breakdown of genes according to their R-loop status upon Top1 depletion; numbers indicate gene numbers in each category. b Quartile plot depicting distribution of lengths for genes undergoing R-loop gains, losses, or no/mixed change (color code is indicated below the plot). Stars (*, **, and ***) indicate p-value less than 10^− 10, 10^− 25,10^− 40, respectively (Wilcoxon Mann-Whitney). c Gene length is plotted as a function of the fold R-loop signal change. Bins were chosen so they contain similar number of genes to avoid biased sampling. Median Pearson correlation coefficient and associated p-value are indicated. d, e Same as (b) except gene expression and gene distance are plotted. f XY plot between gene density measured on each individual chromosome (represented by a dot) and the ratio of gene numbers undergoing R-loop gains and R-loop losses upon Top1 depletion. The regression line along with 95% confidence interval and Pearson correlation coefficient are indicated. g Distribution of genes undergoing R-loop gains and losses according to the RNAP stalling and expression status of each gene. Color code is as in (b)

Fig. 3

R-loop signal at RLG genes are co-transcriptional. a Distribution of all peaks of R-loop gain and loss (p-adjusted < 0.1) along a gene metaplot, normalized by number of genes in each length category. Genes are broken down by length, as indicated at top. Genes were binned in 40 bins and peak counts reported by bin. b–c Metaplots of DRIPc-seq signal over RLG genes (b) and RLL genes (c) along a 20 kilobase window centered on their TSS at left, or PAS at right. Values are median and shown with standard deviation (shaded). Samples are color-coded as indicated

Fig. 4

RLG and RLL peaks show distinct epigenetic features. a Heatmap indicating the relative enrichment or depletion of RLG and RLL peaks over specific chromatin features shown at right. The ratio of observed over expected overlaps between RLG and RLL peaks and matched R-loop control peaks was measured over each chromatin feature (see Methods) and shown as a color-coded heatmap (shown at left). Stars indicate the extent of overlap between R-loop peaks and each chromatin feature (* 10–25%; ** 25–50%; *** > 50%; no star < 10%). All values are significant with p-value < 0.008 (Monte-Carlo). b Distance between RLG and RLL peaks and H3K9me3 peaks (top) or LADs (bottom) compared to matched controls. Statistical significance was measured by Wilcoxon test. c Distance between all R-loop peaks and H3K9me3 peaks (top) or LADs (bottom) after clustering R-loop peaks according to the strength of signal change upon Top1 depletion (color-coded as in Fig. 2c). d Promoter density plotted along a region centered on LAD boundaries (shaded) for promoters driving transcription away from the boundary (left) or towards it (right), as indicated by the arrow. Genes were broken down between RLG genes (top), control matched genes (middle) and all genes (bottom)

Fig. 5

RLL peaks are enriched for replication origins while RLG peaks are depleted. a Heatmap of enrichment or depletion of RLG and RLL peaks over specific chromatin features. Color codes and description are as Fig. 4a. b Distance between RLG and RLL peaks and replication origins compared to matched controls. Statistical significance was measured by Wilcoxon test. c Distance between replication origins and all R-loop peaks ranked by the strength of R-loop changes (color-coded). d SNS-seq signal plotted over promoter and terminal regions for RLL and RLG loci as well as matched controls. Data is shown as median with standard error (shaded). e SNS-seq replication signal of R-loop peaks ranked by the strength of R-loop gains and losses (color-coded). f Replication timing analysis for RLL, RLG and matched peaks according to phases of the cell cycle based on Repli-seq data. All comparisons to matched peaks are significant (p < 0.008, Monte-Carlo) except when indicated (NS)

Fig. 6

Top1 depletion triggers G0/G1 block and global replication timing delay. a Western blots showing the cellular response to Top1 depletion and camptothecin treatment with respect to γH2AX and markers of DNA damage signaling. b Total γH2AX immunofluorescence signal for control and Top1-depleted cells (n > 100 cells). c Cell cycle analysis for Top1-depleted cells and controls. Results are average of four experiments presented with standard deviation. d Representative images of ki-67 staining for Top1-depleted and control cells. Cells were counter-stained with DAPI. e Quantification of ki-67 staining (160 cells for each sample per experiment; two independent replicates). f Analysis of replication timing at a range of RLL loci in Top1-depleted cells and controls. The % of cells undergoing replication in each phase of the cell cycle was measured by the relative recovery of BrdU-labeled immunoprecipitated DNA across G1, early S (ES), late S (LS) and G2 phases. Error bars are SE of two replicates. Red and grey shading indicate genes with significant and non-significant replication timing delays, respectively. g Replication timing analysis of mitochondrial DNA