Repeat expansions confer WRN dependence in microsatellite-unstable cancers

Abstract

The RecQ DNA helicase WRN is a synthetic lethal target for cancer cells with microsatellite instability (MSI), a form of genetic hypermutability that arises from impaired mismatch repair^1-4. Depletion of WRN induces widespread DNA double-strand breaks in MSI cells, leading to cell cycle arrest and/or apoptosis. However, the mechanism by which WRN protects MSI-associated cancers from double-strand breaks remains unclear. Here we show that TA-dinucleotide repeats are highly unstable in MSI cells and undergo large-scale expansions, distinct from previously described insertion or deletion mutations of a few nucleotides⁵. Expanded TA repeats form non-B DNA secondary structures that stall replication forks, activate the ATR checkpoint kinase, and require unwinding by the WRN helicase. In the absence of WRN, the expanded TA-dinucleotide repeats are susceptible to cleavage by the MUS81 nuclease, leading to massive chromosome shattering. These findings identify a distinct biomarker that underlies the synthetic lethal dependence on WRN, and support the development of therapeutic agents that target WRN for MSI-associated cancers.

Extended Data Fig. 1 |. WRN depletion induces DNA damage in different MSI cell lines.

a, Western blot analysis of MLH1, MSH2, and GAPDH protein levels in HSECs after CRISPR–Cas9 knockout. sgLuc, control single-guide RNA (sgRNA) targeting luciferase; sgMLH1 and sgMSH2, sgRNAs targeting MLH1 and MSH2, respectively. For gel source data, see Supplementary Fig. 1. b, Relative viability 7 days after sgRNA transduction in HSECs. sgCh2.2 and sgCh2.4 denote negative controls targeting chromosome 2 intergenic sites; sgPolR2D denotes a pan-essential control. sgWRN2 and sgWRN3 denote experimental sgRNA targeting WRN. Data are mean and s.d. P values were determined using two-tailed Student’s t-test (n = 3). c, Example of flow cytometry gating strategy used in d and Extended Data Fig. 4c. d, Flow cytometry profiles for exponentially growing KM12-shWRN cells treated with DMSO (NT) or doxycycline (shWRN) for 72 h. EdU was added during the last 30 min before collecting cells. Percentage of cells in the gates is indicated. Data are representative of three independent experiments. e, Western blot analysis of WRN protein levels in KM12-shWRN and SW837-shWRN treated with DMSO or doxycycline for 72 h. Data are representative of three independent experiments. For gel source data, see Supplementary Fig. 1. f, Western blot analysis of WRN and pKAP1 protein levels in KM12-shWRN and KM12-shWRN. C911 (non-targeting shRNA) treated with DMSO or doxycycline for 72 h. Data are representative of three independent experiments. For gel source data, see Supplementary Fig. 1.

Extended Data Fig. 2 |. WRN depletion induces recurrent and overlapping DSBs in MSI cells.

a, Genome browser screenshot displaying END-seq profiles as normalized read density (RPM) for HCT116-shWRN and KM12-shWRN cells treated with DMSO (NT) or doxycycline (shWRN), or transfected with non-targeting siRNAs (siCTRL) or WRN siRNAs (siWRN) for 72 h. b, Scatterplots of END-seq peak intensity between biological replicates of KM12-shWRN and HCT116-shWRN cells treated with doxycycline for 72 h. Pearson correlation coefficients are indicated. c, Venn diagrams showing overlap between peaks detected in HCT116-shWRN and KM12-shWRN cells treated with either doxycycline (shWRN) or WRN siRNAs (siWRN) for 72 h. n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s Exact test for both the Venn diagrams (P < 2.2 × 10⁻¹⁶ for both comparisons). d, Quantification of END-seq peak intensity for KM12-shWRN and SW837-shWRN cells treated with doxycycline for 72 h. n = 5,424 peaks were examined for statistical significance using one-sided Wilcoxon rank sum test. Box plots are as in Fig. 2a, b. ***P <2.2 × 10⁻¹⁶. e, Venn diagram showing overlap between peaks identified from END-seq and RPA-bound ssDNA ChIP–seq for KM12-shWRN cells treated with doxycycline for 72 h. n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s exact test (P < 2.2 × 10⁻¹⁶). f, Composite plot of END-seq (black: positive-strand reads, grey: negative-strand reads) and RPA-bound ssDNA ChIP–seq (blue: positive-strand reads, red: negative-strand reads) signal around DSB sites in KM12-shWRN cells treated with doxycycline for 72 h. g, Heat map displaying intensity of END-seq signal in KM12-shWRN cells treated with doxycycline for 72 h, relative to the centre of the gap between positive- and negative-strand peaks. Sites are ordered by the size of the gap, from smallest to largest. h, Calculated size distribution from the reference genome of (TA)_n repeats either located in gaps between positive and negative END-seq peaks (black, broken sites) or located elsewhere in the genome (grey, non-broken sites), determined from KM12-shWRN cells treated with doxycycline for 72 h.

Extended Data Fig. 3 |. WRN depletion induces DNA breakage in common fragile sites and palindromic TA-rich repeats in MSI cells.

a, Genome browser screenshot displaying END-seq profiles of common fragile sites FRA16D, FRA3B, FRA10B and FRA7I as normalized read density (RPM) for KM12-shWRN cells treated with DMSO (NT) or doxycycline (shWRN) for 72 h. The number of uninterrupted (TA)_n repeat units in the hg19 reference genome at DSB sites is indicated. b, Genome browser screenshot displaying END-seq profiles of PATRRs on chromosomes 11 and 22 as normalized read density (RPM) for KM12-shWRN cells treated with DMSO (NT) or doxycycline (shWRN) for 72 h.

Extended Data Fig. 4 |. (TA)_n repeat-forming repeats in MSI cell lines are substrates for MUS81–EME1.

a, Quantitative PCR with reverse transcription (qRT–PCR) analysis quantification (n = 1) of MUS81 and SLX4 mRNA levels in KM12-shWRN cells transfected with non-targeting siRNAs (siCTRL), MUS81 siRNAs (siMUS81), or SLX4 siRNAs (siSLX4). b, Representative images of metaphase spreads from KM12-shWRN cells treated with doxycycline (shWRN) and non-targeting siRNAs (siCTRL), MUS81 siRNAs (siMUS81), or SLX4 siRNAs (siSLX4) for 48 h. Data are representative of three independent experiments, n = 100 metaphases for each condition. c, Flow cytometric profiles for KAP1 phosphorylation in exponentially growing KM12-shWRN cells treated with doxycycline (shWRN), plus non-targeting siRNAs (siCTRL), MUS81 siRNAs (siMUS81), or SLX4 siRNAs (siSLX4) for 72 h. Data are representative of three independent experiments. d, Genome browser screenshot displaying END-seq profiles as normalized read density (RPM) for KM12-shWRN cells treated with doxycycline (shWRN), plus non-targeting siRNAs (siCTRL), MUS81 siRNAs (siMUS81), or SLX4 siRNAs (siSLX4) for 72 h. e, Schematic representation of DNA cruciform cleavage by MUS81–EME1 structure-specific endonuclease. f, Venn diagram displaying overlap of END-seq TA breaks between two biological replicates of DMSO-treated KM12-shWRN cells processed with purified recombinant MUS81–EME1 enzyme in situ (MUS81–EME1). n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s exact test (P < 2.2 × 10⁻¹⁶). g, Venn diagram showing overlap in TA breaks between KM12-shWRN cells treated with doxycycline (shWRN) for 72 h, and DMSO-treated cells processed with MUS81–EME1 enzyme in situ (MUS81–EME1). n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s exact test (P < 2.2 × 10⁻¹⁶). h, Venn diagram displaying overlap between TA breaks from KM12-shWRN and HCT116-shWRN genomic DNA processed in situ with MUS81–EME1 in situ (n = 1 for HCT116). n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s exact test (P < 2.2 × 10⁻¹⁶). i, Genome-wide aggregate analysis of END-seq signal around TA breaks from KM12-shWRN cells treated with doxycycline for 72 h (shWRN) (black denotes positive-strand reads, grey denotes negative-strand reads), or DMSO-treated KM12-shWRN cells processed with purified recombinant MUS81–EME1 enzyme in situ (blue denotes positive-strand reads, red denotes negative-strand reads). j, Genome browser screenshot displaying END-seq profiles for DMSO-treated KM12-shWRN cells (WRN proficient) processed in situ with either purified recombinant WRN, MUS81–EME1, or WRN followed by MUS81–EME1. For the latter, proteinase K digestion was performed between the two enzymatic treatments.

Extended Data Fig. 5 |. Structure-forming repeats in MSI cells activate ATR.

a, Genome browser screenshot displaying END-seq profiles for DMSO-treated KM12, HCT116, SW837 and RPE-1 cells containing an inducible shWRN cassette processed in situ with purified recombinant MUS81–EME1. Cells are indicated as MSI (red) or MSS (blue, n = 1). b, Quantification of END-seq peak intensity for libraries displayed in a. Box plots are as in Fig. 2a, b. c, Western blot analysis of WRN and pKAP1 levels in HCT116 cells expressing wild-type WRN, or ATR phosphorylation mutants WRN(3A) or WRN(6A). Endogenous WRN was depleted using an siRNA targeting the WRN 5′ UTR. Data are representative of three independent experiments. For gel source data, see Supplementary Fig. 1. d, Genome browser screenshot displaying END-seq profiles within FRA3B on chromosome 3 as normalized read density (RPM) for KM12-shWRN, HCT116-shWRN, RPE-1-shWRN, and eHAP-shWRN cells treated with doxycycline (shWRN) for 72 h or APH plus ATRi for 8 h. e, Venn diagrams displaying overlap of DSBs detected after WRN depletion or APH plus ATRi treatment in KM12 and HCT116 cells. n = 1,000 random datasets were generated to test significance of overlap using one-sided Fisher’s exact test for both the Venn diagrams (P < 2.2 × 10⁻¹⁶).

Extended Data Fig. 6 |. (TA)_n repeat sequences are underrepresented in whole-genome sequencing data from MSI cells.

a, Bar plots indicating the percentage of recurrent mutations in different classes of repeats (left; mono, di, tri and tetra) and a bar plot (right) showing the number of various dinucleotide repeats in the 1,000 altered loci. The plots were based on sequencing analysis from, which considered microsatellites smaller than 40 bp. b, Agarose gels showing PCR fragments (or lack thereof) of sites of different (TA)_n repeats in one MSS and four MSI cell lines. Broken sites B1–B8 were chosen based on the presence of END-seq peaks after WRN depletion in KM12 cells. Sites NB1–NB3 were chosen with similar (TA)− repeat lengths as broken sites, but were not broken after WRN depletion in KM12 cells. Fragment sizes (in bp) are displayed. Data are representative of three independent experiments. For gel source data, see Supplementary Fig. 1. c, Genome browser screenshots of short read PCR-free whole genome sequencing reads, indicating coverage, in KM12 and HCT116 cell lines (n = 1). Shown are two regions containing (TA)_n repeats, one that displays END-seq peaks after WRN depletion in KM12 (site B2), and one that does not (site NB3). Regions correspond to equivalent PCR sites in Fig. 4a and Extended Data Fig. 5b. d, Box plots displaying coverage at different classes of mono- and di-nucleotide repeats in PCR-free whole-genome sequencing libraries made from HCT116 cells. (TA)_n repeats are split into those that overlap END-seq peaks after shWRN induction, and those that do not contain DSBs. Dotted red lines indicate the average coverage over the genome.

Extended Data Fig. 7 |. (TA)_n repeats undergo large-scale expansions in MSI cells.

a, Cumulative fraction of expanded (TA)_n repeats in KM12 and HCT116, based on ExpansionHunter analysis of PCR-free whole genome sequencing data. (TA)_n repeats were split into broken (red) and non-broken (black) based on presence or absence of END-seq peaks after WRN depletion in KM12 cells. b, Graphical representation of a (TA)_n repeat expansion in HCT116. This site has 33 (TA)_n repeat units in the reference genome; ExpansionHunter identified an expansion to 86–87 repeat units based on PCR-free whole-genome sequencing of HCT116. c, Empirical cumulative distribution function based on the length by which each read overlaps the (TA)_n repeat shown in b as identified by exSTRa. d, Southern blots for two different genomic regions containing non-broken (TA)_n repeats corresponding to the same sites in Fig. 4a and Extended Data Fig. 6b. Red markers and dotted lines represent expected fragment sizes. For gel source data, see Supplementary Fig. 1. e, Southern blots for broken (TA)_n repeat B2 (top) and non-broken (TA)_n repeat NB3 (bottom) in MSS (blue) and MSI (red) cell lines, confirming expansion of broken (TA)_n repeats in MSI cell lines. Red markers and dotted lines represent expected fragment sizes based on the reference genome. For gel source data, see Supplementary Fig. 1. f, Box plots displaying coverage at different classes of repeats in long-read sequencing libraries made from MSI (red) and MSS (blue) cells (n = 1). g, Motif analysis for sequence enrichment at broken (TA)_n in the KM12 cell line from long-read sequencing data.

Extended Data Fig. 8 |. Large-scale expansions occur at long, uninterrupted (TA)_n repeat sequences.

(a) Boxplot showing, in the hg19 reference genome, the proportion of (TA)_n repeat units found within the full annotated sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 59,729 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. b, Box plot showing, in the hg19 reference genome, the proportion of the longest run of uninterrupted (TA)_n within the full annotated sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 59,729 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. c, Box plot showing, in the hg19 reference genome, the length (bp) of the longest uninterrupted (TA)_n dinucleotide repeats within the full annotated sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 59,729 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. d, Box plot showing, in long read sequencing data, the proportion of (TA)_n repeat units found within the full sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 61,244 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. e, Box plot showing, in long-read sequencing data, the proportion of the longest run of uninterrupted (TA)_n within the full sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 61,244 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. f, Boxplot showing, in long-read sequencing data, the length (bp) of the longest uninterrupted (TA)_n dinucleotide repeat within the full sequence at broken or non-broken (TA)_n repeats in KM12 cells. n = 5,400 (broken) and n = 61,244 (non-broken) sites were examined for statistical significance using one-sided Wilcoxon rank sum test. ***P < 2.2 × 10⁻¹⁶. g, Multiple linear regression model predicting END-seq peak intensity of KM12-shWRN cells treated with doxycycline (shWRN) for 72 h derived from END-seq intensity of MUS81–EME1 cleavage in situ, replication timing, and expanded length of broken (TA)_n. The Pearson correlation coefficient is indicated (see i). h, END-seq intensity of broken (TA)_n repeats in KM12-shWRN cells treated with doxycycline for 72 h grouped by replication timing values from late replicating to early replicating. i, Multiple linear regression was performed to predict END-seq peak intensity of KM12-shWRN cells treated with doxycycline for 72 h based on following parameters: END-seq intensity of MUS81–EME1 cleavage in situ, replication timing, and expanded length of broken (TA)_n. END-seq intensity upon shWRN induction and MUS81–EME1 cleavage were calculated using RPKM in ±1 kb window around broken (TA)_n. Mean value was used for replication timing quantification. Expanded lengths were identified from long read sequencing data. Estimates of the standardized regression coefficients (β) are shown, along with t-statistics and P values based on the standardized coefficients. j, Model for MSI cell dependence on WRN. Large-scale expansions of (TA)_n repeats are associated with MSI in MMR-deficient cells. When (TA)_n reach above a critical length, they extrude into cruciform-like structures, which stall replication forks and activate ATR kinase, which in turn phosphorylates WRN and other substrates to complete DNA replication. In the absence of WRN, MUS81–EME1 or SLX4 cleaves secondary structures at (TA)_n repeats, thereby shattering the chromosomes. All box plots are as in Fig. 2a, b.

Extended Data Fig. 9 |. Deletion breakpoints in MSI cancers are enriched at (TA)_n repeats.

a, Genome browser screenshot of a broken (TA)_n (defined from KM12), MSI deletion (derived from a patient sample), and END-seq profile (in WRN-depleted KM12 cells). The sequences around the breakpoints are shown in the inset. b, Junctions associated with six different MSI deletions from patients. Seq1 represents the sequence from −50 bp to left breakpoint and Seq2 represents the sequence from right breakpoint to +50 bp. c, Enrichment of simple repeats, broken and non-broken (TA)_n, and long interspersed nuclear element (LINE), short interspersed nuclear element (SINE) and long terminal repeat (LTR) elements at patient deletion breakpoints relative to their overlap with random deletion breakpoints of the same size (enrichment value = 1). B(TA)_n–B(TA)_n represents cases in which both breakpoints overlap with broken (TA)_n repeats; B(TA)_n– represents cases in which only one breakpoint overlaps with a broken (TA)_n repeat. B(TA)_n, broken TA repeat; NB(TA)_n, non-broken TA repeat.

Extended Data Fig. 10 |. DNA breaks within DCC gene body.

a, Genome browser screenshots within DCC gene displaying END-seq profiles as normalized read density (RPM) for KM12-shWRN cells treated DMSO (NT), doxycycline (shWRN) for 72 h, or MUS81–EME1 in situ. b, Zoom-in view of region including exons 6 and 7 of DCC gene, containing two (TA)_n repeats displaying END-seq peaks. The highlighted sequences below were extracted from long read sequencing reads in KM12 cells. The (TA)_n repeat in intron 7 is where Vogelstein and colleagues previously detected an insertion.

Fig. 1 |. WRN depletion in MSI cells induces recurrent DSBs at (TA)_n dinucleotide repeats.

a, Representative metaphase spreads from KM12 and SW837 cells containing an inducible WRN shRNA (shWRN) cassette. Cells were treated with DMSO (NT) or doxycycline (shWRN) for 48 h. Data are representative of three independent experiments, n = 100 metaphases for each condition. b, Genome browser screenshots displaying END-seq (n = 5) and RPA-bound ssDNA ChIP–seq (n = 1) profiles as normalized read density (reads per million, RPM) for KM12-shWRN cells. Positive- and negative-strand END-seq reads are displayed in black and grey, and positive- and negative-strand RPA–ssDNA ChIP–seq reads are in blue and red, respectively. c, Genome browser screenshot zoomed in on the highlighted region in b (orange box). The light-blue shading indicates the gap region between the left and right ends of the DSB. d, Motif analysis for sequence enrichment in the gap between positive and negative END-seq peaks in KM12-shWRN cells. e, Fraction of END-seq peaks occurring at sites of (TA)_n repeats for KM12-shWRN and HCT116-shWRN cells treated with either doxycycline (shWRN, n = 2 for HCT116) or WRN siRNAs (siWRN, n = 1) for 72 h. Numbers in parentheses indicate number of peaks identified by peak-calling.

Fig. 2 |. TA breaks are dependent on structure-specific endonucleases MUS81–EME1 and SLX4.

a, Quantification of metaphases displaying chromosome shattering (defined as the absence of intact chromosomes) in KM12-shWRN cells treated with doxycycline plus siRNAs against MUS81 (siMUS81) or SLX4 (siSLX4), or non-targeting control (siCtrl) siRNAs for 72 h (n = 3). The top, centre mark, and bottom hinges of the box plots, respectively, indicate the 75th, median, and 25th percentile values. Whiskers represent minimum and maximum values. P values were calculated using Student’s t-test. b, Quantification of END-seq signal intensity (n = 2) at broken TA repeats in KM12-shWRN cells with treatment as in a. n = 5,001 peaks were examined. Boxplots are as in a, with outliers beyond 1.5 times the interquartile range shown. ***P < 2.2 × 10⁻¹⁶, one-sided Wilcoxon rank sum. c, Genome browser screenshot for KM12-shWRN cells treated with doxycycline (shWRN, top), and DMSO-treated cells processed with purified recombinant MUS81–EME1 enzyme in situ (bottom, n = 2). d, Genome browser screenshot zoomed in on the highlighted region in c (orange box). e, Quantification of END-seq peak intensity for DMSO-treated KM12-shWRN cells processed in situ with purified recombinant MUS81–EME1, WRN or WRN followed by MUS81–EME1 (n = 2). For the latter, proteinase K digestion was performed between the two enzymatic treatments. n = 5,496 peaks were examined. Box plots are as in a and b. ***P < 2.2 × 10⁻¹⁶, one-sided Wilcoxon rank sum test.

Fig. 3 |. Replication stalling and collapse at (TA)_n repeats in MSI cell lines.

a, Composite plot of RPA-bound ssDNA ChIP–seq signal around broken (TA)_n repeats in KM12 cells treated with DMSO. b, Genome browser screenshot displaying END-seq profiles for KM12, HCT116, RPE-1, and eHAP cells containing an inducible shWRN cassette. Cells were treated with doxycycline (shWRN) for 72 h, or with a combination of aphidicolin (APH) and ATR inhibitor (ATRi) (n = 1) for 8 h. MSI cells are in red; MSS cell lines are in blue. c, Percentage of total DSBs located at (TA)_n repeats after treatment with APH plus ATRi, as shown in b. MSI cell are in red; MSS cell lines are in blue.

Fig. 4 |. (TA)_n repeats undergo large-scale expansion in MSI cell lines.

a, Agarose gels showing PCR fragments (or lack thereof) at (TA)_n repeats in KM12 (MSI) and SW837 (MSS) cells. B1–B8 were chosen based on the presence of END-seq peaks after WRN depletion in KM12 cells. NB1–NB3 were chosen for similar (TA)_n repeat lengths as broken sites without breakage after WRN depletion in KM12 cells. Ladder fragment sizes (in bp) are displayed. Data are representative of three independent experiments. For gel source data, see Supplementary Fig. 1. b, Box plots displaying coverage at different classes of repeats in WGS data from KM12 cells (n = 1). Dotted red lines indicate the average coverage over the genome. c, Cell lines plotted by their average WRN dependency score and sequencing coverage of broken (TA)_n loci. FPBM, fragments per base per million. Pearson correlation coefficients were used to calculate r values and two-sided P values. d, Southern blots (n = 2) for two different genomic regions containing broken (TA)_n repeats corresponding to the same sites in a. Red markers and dotted lines represent expected fragment sizes. For gel source data, see Supplementary Fig. 1. e, Box plot of long-read sequencing data (n = 1) demonstrating total length of broken and non-broken (TA)_n in indicated cell lines compared with the hg19 reference genome. MSI (red), MSS (blue). n = 5,400 (broken), n = 61,244 (non-broken). Box plots are as in Fig. 2a, b. ***P < 2.2 × 10⁻¹⁶, one-sided Wilcoxon rank sum test. NS, not significant. Wilcox testing for the alternative hypothesis that the broken (TA)_n has a greater group mean than the non-broken (TA)_n was used. P values were corrected for multiple testing using the Benjamini–Hochberg method.