Decoding the fine-scale structure of a breast cancer genome and transcriptome

Abstract

A comprehensive understanding of cancer is predicated upon knowledge of the structure of malignant genomes underlying its many variant forms and the molecular mechanisms giving rise to them. It is well established that solid tumor genomes accumulate a large number of genome rearrangements during tumorigenesis. End Sequence Profiling (ESP) maps and clones genome breakpoints associated with all types of genome rearrangements elucidating the structural organization of tumor genomes. Here we extend the ESP methodology in several directions using the breast cancer cell line MCF-7. First, targeted ESP is applied to multiple amplified loci, revealing a complex process of rearrangement and co-amplification in these regions reminiscent of breakage/fusion/bridge cycles. Second, genome breakpoints identified by ESP are confirmed using a combination of DNA sequencing and PCR. Third, in vitro functional studies assign biological function to a rearranged tumor BAC clone, demonstrating that it encodes anti-apoptotic activity. Finally, ESP is extended to the transcriptome identifying four novel fusion transcripts and providing evidence that expression of fusion genes may be common in tumors. These results demonstrate the distinct advantages of ESP including: (1) the ability to detect all types of rearrangements and copy number changes; (2) straightforward integration of ESP data with the annotated genome sequence; (3) immortalization of the genome; (4) ability to generate tumor-specific reagents for in vitro and in vivo functional studies. Given these properties, ESP could play an important role in a tumor genome project.

Figure 1.

(A) The result of targeted ESP on amplicons mapping to chromosomes 1,3,17, and 20. A total of 434 end-sequence pairs were mapped onto the normal human genome sequence (represented as a horizontal line along the top). The dark-green plot represents the number of end sequences per 1-Mb interval. BAC end pairs with ends mapping to different chromosomes are shown as horizontal red lines. BAC clones with ends in the wrong orientation (not pointing toward each other) are shown in blue. BAC clones with ends mapping more than three standard deviations farther apart than the average BAC insert are shown in light green. A complete display with all mapped clones is at http://shark.ucsf.edu/~stas/ESP2/esp2.html, and a more detailed description can be found in Volik et al. (2003). (B) Chromosome 20 end-sequence density and end-sequence pair plots. (C) PCR confirmation of genome breakpoints in clones MCF7_1-37_E22 (1), MCF7_1-94_M14 (2), and MCF7_1-23_I06 (3). A shotgun library was constructed from the insert of each of these clones, and 96 plasmid subclones end sequenced. Plasmids with end sequences mapping to distant genomic loci were identified, and primers straddling the putative breakpoint were designed. In subpanels 1–3, the first lane is DNA from the corresponding BAC clone, the second lane is MCF-7 genomic DNA, the third lane is normal genomic DNA, the fourth lane is negative control, and the fifth lane is 1-kb ladder (Gibco-BRL).

Figure 2.

Using tumor-derived BAC clones for phenotype screens. (A) Confirmation of retrofitting BAC MCF-7_1-3F5 for transfection studies. Arrows mark new bands in the vector resulting from insertion of pRetroES plasmid. (B) PCR-based control for transfection of EPH4 cells with retrofitted BAC clone. (Lane 1) Nontransfected cells; (lane 2) transfected cells; (lane 3) positive control (BAC DNA); (lane 4) negative control. (C) Increase in resistance of EPH4 cells to doxorubicin. Note the decrease in the number of apoptotic cells as demonstrated by the annexin assay.

Figure 3.

Analysis of the MCF-7 cDNA library and transcript ESP. (A) The results of normalization of the MCF-7 cDNA (top) and of PCR-based sizing of 11 randomly selected cDNA clones (bottom). (B) The results of the ESP analysis of 5000 end-sequenced cDNA clones. See Figure 1 for the detailed description of this panel with four validated clones boxed. (C) The results of the PCR validation of these clones on two independent preparations of MCF-7 cDNA using clone-specific primers spanning breakpoints (Table 1). In each panel, lane 1 is the 1-kb ladder (GIBCO-BRL); lane 2 is clone DNA; lane 3 is independent preparation of MCF-7 cDNA; lane 4 is normal breast cDNA (Stratagene adult human female, breast first strand cDNA cat# 780602); lane 5 is negative control.