Functional Enhancers Shape Extrachromosomal Oncogene Amplifications

Abstract

Non-coding regions amplified beyond oncogene borders have largely been ignored. Using a computational approach, we find signatures of significant co-amplification of non-coding DNA beyond the boundaries of amplified oncogenes across five cancer types. In glioblastoma, EGFR is preferentially co-amplified with its two endogenous enhancer elements active in the cell type of origin. These regulatory elements, their contacts, and their contribution to cell fitness are preserved on high-level circular extrachromosomal DNA amplifications. Interrogating the locus with a CRISPR interference screening approach reveals a diversity of additional elements that impact cell fitness. The pattern of fitness dependencies mirrors the rearrangement of regulatory elements and accompanying rewiring of the chromatin topology on the extrachromosomal amplicon. Our studies indicate that oncogene amplifications are shaped by regulatory dependencies in the non-coding genome.

Keywords: EGFR; MYC; MYCN; double minute; enhancer; epigenetic; extrachromosomal DNA; glioblastoma; oncogene amplification.

Figure 1.. Skewing of EGFR focal amplifications to two upstream enhancer elements.

(a) Model for positive selection of functional elements on amplicons. (b) (From top-to-bottom) Green highlights region of skew from the Monte Carlo simulation (P < 0.0001). Heatmap depicting the EGFR amplicons across 174 glioblastoma samples. The aggregate heatmap summarizes the frequency of amplification across the cohort. (Bottom) magnified view of the co-amplified H3K27ac peaks (from an aggregate of six glioblastoma models) upstream of EGFR. (c) Copy number for the EGFR transcription start site (TSS) (x axis) versus copy number of each upstream enhancer (y axis) across EGFR-amplified glioblastoma samples. (d) H3K27ac ChlP-seq, ATAC-seq, POLR2A ChlP-seq, and RNA-seq signals at two EGFR enhancers for four glioblastoma lines (GBM3565, GBM3094, GSC23, G459). (e) Experimental scheme for EGFR repression by CRISPRi using a doxycycline-inducible KRAB-dCas9 construct designed to target EGFR enhancers and promoter in G361 glioblastoma cell cultures. (f) RT-qPCR EGFR expression in G361 with multiple sgRNAs targeting EGFR enhancers 1 and 2 and a comparison of the promoter in induced and uninduced cells (N=3 experiments per sgRNA with 2–3 technical replicates). (g) Cell viability as assayed by Alamar blue in induced and uninduced cells after 8 days of culture, following sgRNA targeting of the EGFR enhancers and promoter (N=3 experiments per sgRNA). A t-test was used for significance (* p≤0.05, ** p≤0.01, *** p≤0.001 compared to the untreated control using all technical replicates). See also Figure S1.

Figure 2.. Selection of tissue-specific enhancers by EGFR amplicons.

(a) Model of tissue specific enhancer analysis. (b) Pearson correlation to measure the similarity between the H3K27ac enhancer profiles within the region of skew of normal tissues and the profile of GSC23 for EGFR in glioblastoma. The top scoring tissues are labelled. (c) ChlP-seq tracks for H3K27ac and SOX2 in the EGFR region of skew in glioblastoma cell lines (aggregate track, MGGTPC) and neural stem cells (NSC194, neural progenitor cell). (Bottom) Zoom in of SOX2 signal for EGFR enhancer 1 and enhancer 2.

Figure 3.. Co-option of local and ectopic enhancers by EGFR extrachromosomal amplification events.

(a) Overview of experimental approach. (b) (Left) ChIP input control sequence tracks from EGFR-amplified and -unamplified glioblastoma cell models. (Right) Enlarged view of the EGFR 5’ upstream region H3K27ac ChlP-seq data. (c) Metaphase FISH of GBM3565 showing extrachromosomal EGFR amplification (red) at white arrows. The CEP7 probe depicted in green marks the centromere of chromosome 7. (60x original magnification) (d) (Left) Circular amplicon reconstruction based on paired-end reads. (Right) In silico reconstruction of the EGFR GBM3565 ecDNA showing supporting split reads. (e) In silico reconstruction of GBM3679, GBM1552, GBM2229, and GBM3565 ecDNA amplifications carrying the EGFR amplicon. (Top) Intrachromosomal (blue) rearrangements predicted by paired-end reads, input track from showing focal amplifications, and H3K27ac ChlP-seq track. (Bottom) Circular layout of EGFR amplicon. (Outside-inside) H3K27ac ChlP-seq track, refseq genes (in green), and chromosome 7 coordinates. See also Figure S2 and Figure S3.

Figure 4.. Topology of the EGFR locus in unamplified and amplified glioblastoma.

(a) (Top) HiC contact map of unamplified glioblastoma model cell line G567. (Middle) CTCF ChlP-seq track of unamplified glioblastoma model cell line GSC23. The red and green arrows denote the orientation of the CTCF motif. (Bottom) Schematic of the boundaries of the loop domain. (b) 4C-seq profiles anchored from near the EGFR transcription start site (dotted line) showing interactions to the EGFR enhancers (boxed) for GSC23 (unamplified). Red arcs denote regions with strong distal interactions with EGFR at a 12 kb window thresholded at a 0.12 interaction frequency. H3K27ac ChIP-seq tracks accompany the 4C-seq data. The 4C-seq tracks consist of a main trend of the chromatin interactions based on a 5 kb window and domainogram colored by interaction frequency. Right side depicts a model for the toplogy of the locus. (c) Same as (b) for GBM3565 (EGFR amplified). See also Figure S4.

Figure 5.. The contribution of enhancers on EGFR amplicons to cell fitness.

(a) Overview of CRISPRi screen design. (b) Genomic annotations for the EGFR locus. We show enhancer 1 and enhancer 2 as E1 and E2 and additional enhancers as E3–5. (c) CRISPRi fitness plots for unamplified (GSC23) and amplified (GBM3565) glioblastoma. CRISPRi score (red) represents −log10(p value) based on the 20 sgRNA rolling average. High CRISPRi scores represent depletion. Peaks above the dashed threshold line are significant at a Benjamini-Hochberg FDR < 0.01. H3K27ac ChIP-seq tracks and 4C-seq strong interactions are shown about the CRISPRi scores. Colored circles above the peaks denote shared or unique significant enhancers. (d) Zoom ins for EGFR enhancer 4, 1, and the promoter. The tracks are the same as in (c) except for the addition of the log₂(fold change of day 21 compared to the plasmid library) of individual sgRNAs. See also Figure S5.

Figure 6.. Multi-cancer analysis of enhancer selection on oncogene amplicons.

(a) Solid tumors analyzed in this study. (b) Workflow for pan-cancer identification of oncogene-enhancer co-amplification. (c) Bar chart showing the proportion of samples containing a co-amplified enhancer. The most frequently co-amplified enhancer is plotted; other enhancers may be present at a lower frequency. (d) Oncogenes showing amplicon-skew in indicated cancers. (e) MYCN amplification skewing data for neuroblastoma showing inclusion of a downstream super-enhancer. (Top-bottom) Super-enhancers colored by recurrence number detected in MYCN-unamplified neuroblastoma cell lines and aggregated H3K27ac ChIP-seq data from these 12 lines (top). Copy number profile of 40 neuroblastoma tumors, with the region of skew indicated by the green bar (P < 0.0001 by Monte Carlo simulation) (bottom). (f) MYCN amplification skewing in Wilms tumor includes an upstream super-enhancer. (Top-bottom) Super-enhancers colored by recurrence number detected in MYCN-unamplified primary Wilms tumor samples and aggregated H3K27ac ChlP-seq data from samples of these 5 tumors (top). Copy-number profile of 15 Wilms tumors, with the region of skew indicated by the green bar (P < 0.0001 by Monte Carlo simulation) (bottom). (g) Pearson correlation to measure the similarity between the H3K27ac enhancer profiles within the region of skew of normal tissues and the profile of CLB-GA neuroblastoma cell line. The top scoring tissues are labelled. (h) ChlP-seq tracks for H3K27ac and the lineage-enriched factors MYCN, TWIST1, and GATA3 from the MYCN region of skew in neuroblastoma, as assessed within the neuroblastoma aggregate track, an embryonic adrenal sample from Roadmap Epigenomics data, and the MYCN-amplified neuroblastoma cell line BE(2)C. (i) Same as (g) except the normal tissues were compared to the profile of Wilms tumor 5. The top scoring tissues are labelled. (j) ChlP-seq tracks for H3K27ac and lineage-enriched factors SIX1 and SIX2 from the MYCN region of skew in Wilms tumor, as assessed in the Wilms tumor aggregate track and embryonic kidney samples. See also Figure S6.