ecDNA hubs drive cooperative intermolecular oncogene expression

Abstract

Extrachromosomal DNA (ecDNA) is prevalent in human cancers and mediates high expression of oncogenes through gene amplification and altered gene regulation¹. Gene induction typically involves cis-regulatory elements that contact and activate genes on the same chromosome^2,3. Here we show that ecDNA hubs-clusters of around 10-100 ecDNAs within the nucleus-enable intermolecular enhancer-gene interactions to promote oncogene overexpression. ecDNAs that encode multiple distinct oncogenes form hubs in diverse cancer cell types and primary tumours. Each ecDNA is more likely to transcribe the oncogene when spatially clustered with additional ecDNAs. ecDNA hubs are tethered by the bromodomain and extraterminal domain (BET) protein BRD4 in a MYC-amplified colorectal cancer cell line. The BET inhibitor JQ1 disperses ecDNA hubs and preferentially inhibits ecDNA-derived-oncogene transcription. The BRD4-bound PVT1 promoter is ectopically fused to MYC and duplicated in ecDNA, receiving promiscuous enhancer input to drive potent expression of MYC. Furthermore, the PVT1 promoter on an exogenous episome suffices to mediate gene activation in trans by ecDNA hubs in a JQ1-sensitive manner. Systematic silencing of ecDNA enhancers by CRISPR interference reveals intermolecular enhancer-gene activation among multiple oncogene loci that are amplified on distinct ecDNAs. Thus, protein-tethered ecDNA hubs enable intermolecular transcriptional regulation and may serve as units of oncogene function and cooperative evolution and as potential targets for cancer therapy.

Extended Data Figure 1.. ecDNA FISH strategies and copy number estimation.

(a) WGS tracks with DNA FISH probe locations. For COLO320-DM and PC3, a 1.5 Mb MYC FISH probe (Figure 1a,b), a 100 kb MYC FISH probe (Figure 1d,e,f), or a 1.5 Mb chromosome 8 FISH probe was used. Commercial probes were used in SNU16 and HK359 cells. (b) Representative DNA FISH image using chromosomal and 1.5 Mb MYC probes in non-ecDNA amplified HCC1569 showing paired signals as expected from the chromosomal loci. (c) ecDNA clustering of individual COLO320-DM cells by autocorrelation g(r). (d) Representative FISH images showing ecDNA clustering in primary neuroblastoma tumors (Patients 11 and 17). (e) ecDNA clustering of individual primary tumor cells from all three patients using autocorrelation g(r). (f) Comparison of MYC copy number in COLO320-DM calculated based on WGS (n=7 genomic bins overlapping with DNA FISH probes), metaphase FISH (n=82 cells) and interphase FISH (n=47 cells). P-values determined by two-sided Wilcoxon test. (g) Representative images of nascent MYC RNA FISH showing overlap of nascent RNA (intronic) and total RNA (exonic) FISH probes in PC3 cells (independently repeated twice). (h) Representative images from combined DNA FISH for MYC ecDNA (100 kb probe) and chromosomal DNA with nascent MYC RNA FISH in COLO320-DM cells (independently repeated four times). (i) MYC transcription probability measured by nascent RNA FISH normalized to DNA copy number by FISH comparing singleton ecDNAs to those found in hubs in COLO320-DM (box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). To control for noise in transcriptional probability for small numbers of ecDNAs, we randomly re-sampled RNA FISH data grouped by hub size and calculated transcription probability. The violin plot represents transcriptional probability per ecDNA hub based on the hub size matched sampling. P-value determined by two-sided Wilcoxon test.

Extended Data Figure 2.. Generation of TetR-GFP COLO320-DM cells for ecDNA imaging in live cells.

(a) ecDNA imaging based on TetO array knock-in and labeling with TetR-eGFP (left). Representative images of TetR-eGFP signal in TetO-eGFP COLO320-DM cells at indicated timepoints in a time course (right; independently repeated twice). (b) GFP signal in ecDNA-TetO COLO320-DM cells. TetR-eGFP and monomeric TetR-A206K-GFP labeled ecDNA hubs appear to be smaller in living cells than in DNA FISH studies of fixed cells likely because the TetO array is not integrated in all ecDNA molecules and there are potential differences caused by denaturation during DNA FISH and eGFP dimerization. (c) ecDNA hub diameter in microns (box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). P-value determined by two-sided Wilcoxon test. (d) ecDNA hub number per cell. Line represents median. P-value determined by two-sided Wilcoxon test. (e) TetR-eGFP signal in chr8-chromosomal-TetO (chr8:116860000–118680000, left) and ecDNA-TetO (TetO-eGFP COLO320-DM, right) COLO320-DM cells. (f) Fluorescence intensity for chr8-chromosomal-TetO and ecDNA-TetO foci. (g, h) Inferred ecDNA copy number per foci (g; n = number of foci/cell) and per cell (h; n = number of cells) for ecDNA-TetO labeled cells based on summed fluorescence intensity relative to chr8-chromosomal-TetO foci. Line represents median. (i) Representative images of TetR-GFP signal in parental COLO320-DM without TetO array integration which shows minimal TetR-GFP foci. (j) Mean fluorescence intensities for ecDNA (TetO-eGFP) and BRD4 (HaloTag) foci across a line drawn across the center of the largest ecDNA (TetO-eGFP) signal. Data are mean ± SEM for n=5 ecDNA foci. (k) Representative image of TetR-eGFP signal in COLO320-DM cells without TetO array integration overlaid with BRD4-HaloTag signal. Dashed line indicates nucleus boundary. We noted cytoplasmic TetR-eGFP signal in a subset of COLO320-DM cells without TetO array integration but it did not colocalize with BRD4-HaloTag. (l) MYC RNA measured by RT-qPCR for parental COLO320-DM and BRD4-HaloTag COLO320-DM cells treated with DMSO or 500 nM JQ1 for 6 hours which shows similar levels of MYC transcription and sensitivity to JQ1 inhibition following epitope tagging of BRD4. Data are mean ± SD between 3 biological replicates. P-values determined by two-sided student’s t-test.

Extended Data Figure 3.. BET inhibition leads to ecDNA hub dispersal.

(a) Representative metaphase FISH images and schematic showing ecDNA in COLO320-DM and chromosomal HSRs in COLO320-HSR (independently repeated twice for COLO320-DM and not repeated for COLO320-HSR). (b) Ranked BRD4 ChIP-seq signal. Peaks in ecDNA or HSR amplifications are highlighted and labeled with nearest gene. (c) ATAC-seq, BRD4 ChIP-seq, H3K27ac ChIP-seq and WGS at amplified MYC locus. (d) Number of ecDNA locations (including ecDNA hubs with >1 ecDNA and singleton ecDNAs) from interphase FISH imaging for individual COLO320-DM cells after treatment with DMSO or 500 nM JQ1 for 6 hours. N = number of cells quantified per condition. P-value determined by two-sided Wilcoxon test. (e) ecDNA copies in each ecDNA location from interphase FISH imaging in COLO320-DM after treatment with DMSO or 500 nM JQ1 for 6 hours (box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). N = number of ecDNA locations quantified per condition. P-value determined by two-sided Wilcoxon test. (f) Representative live images of TetR-eGFP-labeled ecDNA after treatment with DMSO or 500 nM JQ1 at indicated timepoints in a time course (top; independently repeated twice) and ecDNA hub zoom-ins (bottom). (g) Representative image from combined DNA/RNA FISH in COLO320-DM cells treated with DMSO, 500 nM JQ1, or 1% 1,6-hexanediol for 6 hours. (h) MYC transcription probability measured by dual DNA/RNA FISH after treatment with DMSO, 1% 1,6-hexanediol, or 100 μg/mL alpha-amanitin for 6 hours (box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range; n = number of cells). P-values determined by two-sided Wilcoxon test. (i) Representative DNA FISH images for MYC ecDNA in interphase COLO320-DM treated with either 1% 1,6-hexanediol or 100 μg/mL alpha-amanitin for 6 hours. (j) ecDNA clustering in interphase cells by autocorrelation g(r) for COLO320-DM treated with DMSO, 1% 1,6-hexanediol, or 100 μg/mL alpha-amanitin for 6 hours. Data are mean ± SEM (n = 10 cells quantified per condition). (k) Averaged BRD4 ChIP-seq signal and heatmap over all BRD4 peaks for cells treated with DMSO or 500 nM JQ1 for 6 hours. (l) Cell viability after treatment with different JQ1 concentrations for 48 hours normalized to DMSO-treated cells. Data are mean ± SD between 3 biological replicates. P-values determined by two-sided student’s t-test. (m) Cell proliferation after treatment with different JQ1 concentrations over 72 hours. Data are mean ± SD between 3 biological replicates. (n) Cell doubling times after treatment with different JQ1 concentrations over 72 hours in hours (top) or after normalization to DMSO-treated cells (bottom). Data are mean ± SD between 3 biological replicates. P-values determined by two-sided student’s t-test. (o) MYC RNA measured by RT-qPCR after treatment with indicated inhibitors for 6 hours (top; each point represents a biological replicate, n=6 for DMSO and JQ1 treatments, n=3 for all other drug treatments). Data are mean ± SD. P-values determined by two-sided student’s t-test. Details of inhibitor panel, protein target, significance of effect on MYC transcription, and comparison of effect on ecDNA and HSR transcription (bottom). (p,q) Representative DNA FISH images (p) and clustering by autocorrelation g(r) (q) for MYC ecDNAs in COLO320-DM treated with DMSO or 500 nM MS645 for 6 hours. Data are mean ± SEM. P-value determined by two-sided Wilcoxon test at radius = 0.

Extended Data Figure 4.. Reconstruction of COLO320-DM ecDNA amplicon structure.

(a) Structural variant (SV) view of AmpliconArchitect (AA) reconstruction of the MYC amplicon in COLO320-DM cells. (b) Nanopore sequencing of COLO320-DM cells (left) and distribution of read lengths. (c) WGS for COLO320-DM with junctions detected by WGS and nanopore sequencing. (d) Molecule lengths used for optical mapping and statistics. (e) Reconstructed COLO320-DM ecDNA after integrating WGS, optical mapping, and in-vitro ecDNA digestion. Chromosomes of origin and corresponding coordinates (hg19) are labeled. Three inner circular tracks (light tan, slate and brown in color; guides A, B and C, respectively) representing expected fragments as a result of Cas9 cleavage using three distinct sgRNAs and their expected sizes. Guide sequences are in Supplementary Table 2 (PFGE_guide_A-C). (f) In-vitro Cas9 digestion of COLO320-DM ecDNA followed by PFGE (left). Fragment sizes were determined based on H. wingei and S. cerevisiae ladders. Uncropped gel image is in Supplementary Figure 1. Middle panel shows short-read sequencing of the MYC ecDNA amplicon for all isolated fragments, ordered by fragment size. Right panel shows concordance of expected fragment sizes by optical mapping reconstruction, and observed fragment sizes by in-vitro Cas9 digestion (discordant fragments circled). Each sgRNA digestion was performed in one independent experiment. (g) Metaphase FISH images showing colocalization of MYC, PCAT1 and PLUT as predicted by optical mapping and in-vitro digestion. N = 20 cells and 1,270 ecDNAs quantified for MYC/PCAT1 DNA FISH and n = 15 cells and 678 ecDNAs for MYC/PLUT DNA FISH from one experiment. (h) RNA expression measured by RT-qPCR for indicated transcripts in COLO320-DM cells stably expressing dCas9-KRAB and indicated sgRNAs (n=2 biological replicates). Canonical MYC was amplified with primers MYC_exon1_fw and MYC_exon2_rv; fusion PVT1-MYC was amplified with PVT1_exon1_fw and MYC_exon2_rv; total MYC was amplified with total_MYC_exon2_fw and total_MYC_exon2_rv. All primer sequences are in Supplementary Table 1 and guide sequences are in Supplementary Table 2. (i) Alignment of junction reads at the PVT1-MYC breakpoint.

Extended Data Figure 5.. Single-cell multiomic analysis reveals combinatorial and heterogeneous ecDNA regulatory element activities associated with MYC expression.

(a) Joint single-cell RNA and ATAC-seq for simultaneously assaying gene expression and chromatin accessibility and identifying regulatory elements associated with MYC expression. (b) Unique ATAC-seq fragments and RNA features for cells passing filter (both log2-transformed). (c) Correlation between MYC accessibility score and normalized RNA expression. (d) UMAP from the RNA or the ATAC-seq data (left). Log-normalized and scaled MYC RNA expression (top right) and MYC accessibility scores (bottom right) were visualized on the ATAC-seq UMAP. (e) Gene expression scores (using Seurat in R) of MYC-upregulated genes (Gene Set M6506, Molecular Signatures Database; MSigDB) across all MYC RNA quantile bins. Horizontal line marks median. Population variances for all individual cells are shown (top). P-value determined by two-sided F-test. (f) MYC expression levels of top and bottom bins (left). Normalized ATAC-seq coverages are shown (right). (g) Number of variable elements identified on COLO320-DM ecDNAs compared to chromosomal HSRs in COLO320-HSR (left). 45 variable elements were uniquely observed on ecDNA. All variable elements on ecDNA are shown on the right (y-axis shows −log10(FDR) and dot size represents log2 fold change. Five most significantly variable elements are highlighted and named based on relative position in kilobases to the MYC TSS (negative, 5’; positive, 3’). (h) Correlation between estimated MYC copy numbers and normalized log2-transformed MYC expression of all individual cells showing a high level of copy number variability. (i) Estimated MYC amplicon copy number of all cell bins. (j) Zoom-ins of the ATAC-seq coverage of each of the five most significantly variable elements identified in (g) (marked by dashed boxes). (k) Similar distributions of TSS enrichment in the high and low cell bins. (l) Mean copy number regressed, log-normalized, scaled ATAC-seq coverage of the differential peaks against mean MYC RNA (log-normalized, mean-centered, scaled) for each cell bin in orange. Same number of random non-differential peaks from the same amplicon interval and shown in grey. Error bands show 95% confidence intervals for the linear models. (m) Cumulative probability of MYC amplicon copy number distributions (mean-centered, scaled) of single-cell ATAC-seq data and DNA FISH data. P-values determined by Kolmogorov-Smirnov test (1000 bootstrap simulations).

Extended Data Figure 6.. Endogenous enhancer connectome of COLO320-DM MYC ecDNA amplicon and effect of promoter sequence, cis enhancers, and BET inhibition on episomal reporter activation.

(a) Top to bottom: COLO320-DM H3K27ac HiChIP contact map (KR-normalized read counts, 10 kb resolution), reconstructed COLO320-DM amplicon, H3K27ac ChIP-seq signal, BRD4 ChIP-seq signal, WGS coverage, interaction profile of PVT1 and MYC promoters at 10kb resolution with FitHiChIP loops shown below, colored by adjusted p-value. Active elements identified by scATAC and overlapping H3K27ac HiChIP contacts named by genomic distance to MYC start site: −1132E, −1087E, −679E, −655E, −401E, −328E, −85E. (b) Comparison of HiChIP matrix normalization for COLO320-DM H3K27ac HiChIP at 10kb resolution. HiChIP signal is robust to different normalization methods. (c) Quantification of NanoLuc luciferase signal for plasmids with PVT1p-, minp-, or MYCp-driven NanoLuc reporter expression. Luciferase signal was calculated by normalizing NanoLuc readings to Firefly readings. Bar plot shows mean ± SEM. P values were calculated using a two-sided student’s t-test (n=3 biological replicates). (d) Violin plots showing mean fluorescence intensities and signal sizes of the NanoLuc reporter RNA in PVT1p-reporter and minp-reporter transfected cells. P-values were calculated a two-sided Wilcoxon test. (e) Schematic of PVT1 promoter-driven luciferase reporter plasmid with a cis-enhancer. Details of cis-enhancer are in Methods. (f) Bar plot showing luciferase signal driven by PVT1p, MYCp or the constitutive TKp with or without a cis-enhancer (mean ± SEM). All values are normalized to the corresponding promoter-only construct without a cis-enhancer. P values were calculated using a two-sided student’s t-test (n=3 biological replicates). (g) Dot plots showing fold change in luciferase signal (Firefly-normalized NanoLuc signal) in JQ1-treated over DMSO-treated COLO320-DM and COLO320-HSR cells after transfection with the PVT1p or the MYCp plasmid with or without a cis-enhancer. P values were calculated using a two-sided student’s t-test (n=3 biological replicates).

Extended Data Figure 7.. Generation of monoclonal SNU16-dCas9-KRAB with reduced ecDNA fusions.

(a) Representative DNA FISH images showing extrachromosomal single-positive MYC and FGFR2 amplifications (top left and top middle) and double-positive MYC and FGFR2 amplifications in metaphase spreads in parental SNU16 cells (top right) with zoom in (top right). N = 42 cells and 8,222 ecDNAs. Representative DNA FISH images showing distinct extrachromosomal MYC and FGFR2 amplifications in metaphase spreads in SNU16-dCas9-KRAB cells (bottom). N = 29 cells and 3,893 ecDNAs. (b) Ranked plot showing number of junction reads supporting each breakpoint in AmpliconArchitect. Breakpoints are colored based on whether they span regions from the same amplicon (MYC/FGFR2) or regions from two distinct amplicons. (c) HiChIP contact matrices at 10kb resolution with KR normalization for parental SNU16 cell line (left) and SNU16-dCas9-KRAB cell line (right). Contact matrix for parental cells contains regions of increased cis contact frequency between chr8 and chr10 as indicated, as compared to SNU16-dCas9-KRAB cells with highly reduced contact cis frequency between chr8 and chr10. Regions of increased focal interaction overlapping low frequency structural rearrangements between chr8 and chr10 described in panel (a) indicated with boxes.

Extended Data Figure 8.. Perturbations of ecDNA enhancers via CRISPRi revealed functional intermolecular enhancer-gene interactions.

(a) CRISPRi experiments perturbing candidate enhancers in SNU16-dCas9-KRAB cells. Single-guide RNAs (sgRNAs) were designed to target candidate enhancers on FGFR2 and MYC ecDNAs based on chromatin accessibility. (b) Experimental workflow for pooled CRISPRi repression of putative enhancers. Stable SNU16-dCas9-KRAB cells were generated from a single cell clone. Cells were transduced with a lentiviral pool of sgRNAs, selected with antibiotics and oncogene RNA was assessed by flowFISH. Cells were sorted into six bins by fluorescence-activated cell sorting (FACS) based on oncogene expression. sgRNAs were quantified for cells in each bin. (c) FACS gating strategy. (d) Log2 fold changes of sgRNAs for each candidate enhancer element compared to unsorted cells for CRISPRi libraries targeting either MYC or FGFR2 ecDNAs, followed by cell sorting based on expression levels of MYC or FGFR2. Each dot represents the mean log2 fold change of 20 sgRNAs targeting a candidate element. Elements negatively correlated with oncogene expression as compared to the negative control sgRNA distributions in the same pools are marked in red. (e) Barplot showing significance of CRISPRi repression of candidate enhancer elements as in Figure 4e (top). Significant in-trans and in-cis enhancers are colored as indicated. SNU16-dCas9-KRAB H3K27ac HiChIP 1D signal track and interaction profiles of FGFR2 and MYC promoters at 10kb resolution with cis FitHiChIP loops shown below. Interaction profiles in cis shown in purple and in trans shown in orange. (f) Spearman correlations of individual sgRNAs that target MYC TSS across fluorescence bins corresponding to MYC and FGFR2 expression. P values using the lower-tailed t-test comparing target sgRNAs with negative control sgRNAs (negcontrols) are shown. Each dot represents an independent sgRNA.

Extended Data Figure 9.. Intermolecular enhancers and MYC are located on distinct molecules for the vast majority of ecDNAs.

(a) Top: two-color DNA FISH on metaphase spreads for quantifying the frequency of colocalization of the MYC gene and intermolecular enhancers shown in Figure 4e. Above-random colocalization would indicate fusion events. Bottom: representative DNA FISH images. DNA FISH probes target the following hg19 genomic coordinates: E1, chr10:122635712–122782544 (RP11–95I16; n = 11 cells); E2, chr10:122973293–123129601 (RP11-57H2; n = 12 cells); E3/E4/E5, chr10:123300005–123474433 (RP11–1024G22; n = 10 cells). (b) Top: numbers of distinct and colocalized FISH signals. To estimate random colocalization, 100 simulated images were generated with matched numbers of signals and mean simulated frequencies were compared with observed colocalization. P values determined by two-sided t-test (Bonferroni-adjusted). Bottom: number of colocalized signals significantly above random chance. Colocalization above simulated random distributions is the sum of colocalized molecules in excess of random means in all FISH images in which total colocalization was above the random mean plus 95% confidence interval (100 simulated images per FISH image). (c) in-vitro Cas9 digestion of MYC-containing ecDNA in SNU16-dCas9-KRAB followed by PFGE (one independent experiment). Fragment sizes were determined based on H. wingei and S. cerevisiae ladders. Uncropped gel image is in Supplementary Figure 1. MYC CDS guide corresponds to guide B in Supplementary Table 2. (d) Enrichment of enhancer DNA sequences in isolated MYC ecDNAs bands from (c) over background (DNA isolated from a separate PFGE lane in the corresponding size range resulting from undigested genomic DNA) based on normalized reads in 5kb windows. Each dot represents DNA from a distinct gel band. Red indicates fold change above 4. (e) Sequencing track for a gel-purified MYC ecDNA showing enrichment of the MYC amplicon and depletion of the FGFR2 amplicon containing enhancers E1–E5.

Extended Data Figure 10.. Reconstruction of four distinct amplicons in TR14 neuroblastoma cell line and intermolecular amplicon interaction patterns associated with H3K27ac marks.

(a) Top to bottom: long read-based reconstruction of four different amplicons; genome graph with long read-based structural variants of >10kb size and >20 supporting reads indicated by red edges; copy number variation and coverage from short-read whole-genome sequencing, positions of the selected genes. (b) A representative DNA FISH image of MYCN ecDNAs in interphase TR14 cells (top) and ecDNA clustering compared to DAPI control in the same cells assessed by autocorrelation g(r) (bottom). Data are mean ± SEM (n = 14 cells). (c) Custom Hi-C map of reconstructed TR14 amplicons. The MYCN/CDK4 amplicon and the MYCN ecDNA share sequences, which prevented an unambiguous short-read mapping in these regions and appear as white areas. Trans interactions appear locally elevated between MYCN ecDNA and ODC1 amplicon (indicated by arrows). Cis and trans contact frequencies are colored as indicated. (d) Read support for structural variants identified by long read sequencing overlapping amplicons. Only one structural variant between distinct amplicons (MYCN and MDM2 amplicons) was identified with 3 supporting reads. (e) Variant allele frequency for structural variants overlapping amplicons. (f) Trans-interaction pattern between enhancers on a MYCN amplicon fragment (vertical) and an ODC1 amplicon fragment (horizontal). Short-read WGS coverage (grey), H3K27ac ChIP-seq track showing mean fold change over input in 1kb bins (yellow) and Hi-C contact map showing (KR-normalized counts in 5kb bins). (g) Top to bottom: three amplicon reconstructions, virtual 4C interaction profile of the enhancer-rich HPCAL1 locus on the ODC1 amplicon with loci on other amplicons (red), and H3K27ac ChIP-seq (fold change over input; yellow). (h) Trans interaction between different amplicons (KR-normalized counts in 5kb bins) depending on H3K27ac signal of the interaction loci (left; box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). Trans interaction (KR-normalized counts in 5kb bins) separated by amplicon pair (right). H3K27ac High vs. Low denotes at least vs. less than 3-fold mean enrichment over input in 5kb bins. N = 114,636 H3K27ac Low + Low pairs, n = 11,990 H3K27ac High + Low pairs, n = 296 H3K27ac High + High pairs.

Figure 1.. ecDNA imaging correlates ecDNA clustering with transcriptional bursting.

(a) Representative FISH images of interphase ecDNA clustering. A chromosomal control was included for PC3 and COLO320-DM. (b) Interphase ecDNA clustering by autocorrelation g(r) (Methods). Data are mean ± SEM. P-values determined by two-sided Wilcoxon test at r=0 compared to random distribution. (c) Representative FISH image showing ecDNA clustering in a primary neuroblastoma tumor (MYCN ecDNA and chromosomal control, left). ecDNA clustering in three primary tumors using autocorrelation (right). Data are mean ± SEM. P-values determined by two-sided Wilcoxon test at r=0 compared to DAPI. (d) Representative image from combined DNA FISH for ecDNA, chromosomal control, and nascent RNA FISH in PC3 cells. (e) MYC transcription probability measured by joint DNA/RNA FISH (RNA normalized to DNA copy number; box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). P-values determined by two-sided Wilcoxon test. (f) Correlation between MYC transcription probability and ecDNA copy number or clustering (joint DNA/RNA FISH; clustering scores are autocorrelation at r = 0; Pearson’s R, two-sided test).

Figure 2.. BET proteins mediate ecDNA hub formation and transcription.

(a) Representative live cell image of ecDNA and BRD4-HaloTag signals in TetO-eGFP COLO320-DM cells (independently repeated twice; dashed line indicates nuclear boundary). (b) BRD4 ChIP-seq and WGS at MYC locus in COLO320-DM and COLO320-HSR cells. (c) Representative DNA FISH images for cells treated with DMSO or 500 nM JQ1 for 6 hours. (d) Clustering measured by autocorrelation g(r) for ecDNAs in COLO320-DM and HSRs in COLO320-HSR treated with DMSO or 500 nM JQ1 for 6 hours. Data are mean ± SEM. P-values determined by two-sided Wilcoxon test at r=0. (e) MYC transcription probability in COLO320-DM treated with DMSO or 500 nM JQ1 for 6 hours (joint DNA/RNA FISH; RNA normalized to ecDNA copy number; box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). P-values determined by two-sided Wilcoxon test. (f) MYC RNA measured by RT-qPCR for COLO320-DM and COLO320-HSR cells treated either with DMSO or 500 nM JQ1 for 6 hours. Data are mean ± SD between 3 biological replicates. P-values determined by two-sided student’s t-test. (g) Representative live cell images of TetR-eGFP-labeled ecDNAs in TetO-eGFP COLO320-DM cells treated with DMSO or 500 nM JQ1 at indicated timepoints through cell division (independently repeated twice for each condition). H2B-SNAP (top) labels histone H2B in mitotic chromosomes.

Figure 3.. Intermolecular activation of an episomal luciferase reporter in ecDNA hubs.

(a) RNA-seq from COLO320-DM with exon-exon junction spanning read counts shown (left). Relative abundance of full-length MYC and fusion PVT1-MYC transcripts using read count supporting either junction (right). (b) PVT1 promoter-driven luciferase reporter system. (c) Luciferase reporter activity driven by either minp or PVT1p with DMSO or JQ1 treatment (500 nM, 6 hours). Data are mean ± SD between 3 biological replicates. P-values determined by two-sided student’s t-test (Bonferroni adjusted). (d) Representative images of PVT1p or minp reporter transcriptional activity and endogenous ecDNA hubs in COLO320-DM visualized by DNA and RNA FISH (independently repeated 3 times). (e) Fluorescence intensities on a line drawn across the center of the largest NanoLuc RNA signal in images in (d). (f) Number of nuclear NanoLuc signals that colocalize with ecDNA hubs.

Figure 4.. ecDNA hubs mediate intermolecular enhancer-gene interactions.

(a) Representative DNA FISH image showing clustering of MYC and FGFR2 ecDNAs in interphase SNU16 (left). MYC and FGFR2 colocalization in SNU16 (right; box center line, median; box limits, upper and lower quartiles; box whiskers, 1.5x interquartile range). P-value determined by two-sided Wilcoxon test. (b) Oncogene RNA measured by RT-qPCR in SNU16 treated with DMSO or 500 nM JQ1 for 6 hours. Data are mean ± SD between 3 biological replicates. P-value determined by two-sided student’s t-test. (c) Representative metaphase FISH image in SNU16-dCas9-KRAB. Quantification summarizes 30 cells from one experiment. (d) H3K27ac HiChIP contact matrix (10 kb resolution, KR-normalized read counts) in SNU16-dCas9-KRAB showing cis- and trans- interactions. (e) Top: significance of enhancer CRISPRi effects on oncogene repression (Benjamini-Hochberg adjusted; n=40 negative control sgRNAs, n=20 target sgRNAs; Methods, Extended Data Figure 8). Dashed lines mark FDR < 0.05 for cis-interactions and FDR < 0.1 for trans-interactions; significant enhancers are colored and connected to target genes by loops (E1, FDR = 0.048; E2, FDR = 0.052; E3, FDR = 0.048; E4, FDR = 0.052; E5, FDR = 0.052). All datasets contain two independent experiments except the in-trans dataset for the MYC-targeting sgRNA pool, which contains one independent experiment. Bottom: ATAC-seq, BRD4 ChIP-seq, H3K27ac ChIP-seq, and WGS tracks. (f) Correlations between individual sgRNAs and oncogene expression (Methods). P-values determined by lower-tailed t-test compared to negative controls. Each dot represents an independent sgRNA (n=40 negative control sgRNAs, n=20 target sgRNAs). (g) Cross-regulation between MYC and FGFR2 elements in ecDNA hubs. (h) Top to bottom: Hi-C contact map (KR-normalized read counts in 25kb bins) showing cis- and trans- contacts, reconstructed amplicons, H3K27ac ChIP-seq (mean fold-change over input), copy number and WGS in TR14. (i) ecDNA hub model for intermolecular cooperation.