Chromosome rearrangements via template switching between diverged repeated sequences

Abstract

Recent high-resolution genome analyses of cancer and other diseases have revealed the occurrence of microhomology-mediated chromosome rearrangements and copy number changes. Although some of these rearrangements appear to involve nonhomologous end-joining, many must have involved mechanisms requiring new DNA synthesis. Models such as microhomology-mediated break-induced replication (MM-BIR) have been invoked to explain these rearrangements. We examined BIR and template switching between highly diverged sequences in Saccharomyces cerevisiae, induced during repair of a site-specific double-strand break (DSB). Our data show that such template switches are robust mechanisms that give rise to complex rearrangements. Template switches between highly divergent sequences appear to be mechanistically distinct from the initial strand invasions that establish BIR. In particular, such jumps are less constrained by sequence divergence and exhibit a different pattern of microhomology junctions. BIR traversing repeated DNA sequences frequently results in complex translocations analogous to those seen in mammalian cells. These results suggest that template switching among repeated genes is a potent driver of genome instability and evolution.

Keywords: break-induced replication; chromosome rearrangements; chromothripsis; template switching.

Figure 1.

Mechanisms of chromosome rearrangements via BIR and template switching. (A) Genetic assay to measure the frequencies of template switching following a DSB. The assay system is based on the 804-bp URA3 gene from S. cerevisiae, which was split into three overlapping segments, each sharing 300-bp homology, that we call “UR,” “RA,” and “A3” (see also Supplemental Fig. 1). A DSB is induced by the galactose-inducible HO endonuclease adjacent to the UR locus, located at the CAN1 locus in a nonessential terminal region of chromosome 5 (Chr 5); this break can be repaired by a BIR mechanism using, as the template, the RA sequence located in the middle of the opposite chromosome arm. Chr 5 is shown in reversed orientation from the conventional representation. Template switching from RA to A3, located 50 kb more distally on the same chromosome arm, will result in the creation of a functional URA3 gene as part of a nonreciprocal translocation that can be screened by selection on media lacking uracil. (B). Examining the mechanism of BIR and template switching. HO endonuclease creates a DSB next to the UR sequence. Following strand invasion into the RA template (dark-blue line followed by cyan line), clipping of the nonhomologous 3′ tail (red line) is a prerequisite for DNA synthesis. Template switching after the initial strand invasion can proceed by two alternative pathways. (Left) DNA synthesis proceeds past the RA template, and the subsequent template switch intermediate (cyan followed by green) carries a nonhomologous 3′ tail (green line). Subsequent DNA synthesis using the A3 sequence requires clipping of the nonhomologous 3′ tail (green line). (Right) Alternatively, a template switch into the A3 sequence (cyan followed by light-blue line) occurs during synthesis within the RA template. Subsequent DNA synthesis using the A3 sequence does not require tail clipping. With regards to tail clipping, the alternative shown on the left is similar to the first strand invasion event. In contrast, the alternative shown on the right is mechanistically different from the first strand invasion event, as it does not require tail clipping. The two alternatives are distinguished by examining the microhomology usage of the 3′ ends (see the text for details). Gray lines represent adjacent, nonhomologous, flanking sequences.

Figure 2.

Constructs to examine homologous BIR, homeologous BIR, and template switch mechanisms. (A) BIR-only construct (yRA107). An HO-induced DSB next to the UR sequence is repaired by BIR using the RA3 sequence located on the opposite arm of Chr 5 and ∼80 kb distal to the telomere. UR and RA3 shares 300-bp homology. Repair by BIR results in reconstitution of functional URA3 gene and loss of a chromosome fragment centromere-distal to the HO DSB. (B) Template switch construct (yRA53). DSB is repaired by BIR using the RA sequence located 80 kb distal to the telomere. Some of the BIR forks will switch templates to A3 located 50 kb away from RA and 30 kb distal to the telomere. UR shares 300-bp homology with RA, and RA shares 300-bp homology with A3. The template switch is assayed as a reconstitution of the functional URA3 gene. (C) Same as B except that the orientation of RA is flipped so that the invading BIR fork is directed toward the centromere (yRA55). (D) Interchromosomal template switch construct (yRA126) in which A3 is located on Chr IX 30 kb distal to the telomere. (E) BIR-only construct (yRA52). An HO-induced DSB next to the UR sequence is repaired by BIR using the RA3 sequence located on the opposite arm of Chr 5 and ∼30 kb distal to the telomere. UR and RA3 share 300-bp homology. (F) Homeologous BIR construct (yRA57). An HO-induced DSB next to the S. cerevisiae UR sequence is repaired by BIR using the RA3 sequence from Kluyveromyces lactis located on the opposite arm of Chr 5 and ∼30 kb distal to the telomere, reconstituting a chimeric URA3. Sc-UR and Kl-RA3 are 68.3% identical and share a maximum of 11-bp microhomology. (G) BIR-only construct (yRA213). DSB at URA is repaired by BIR using the A3 sequence located 30 kb distal to the telomere. URA shares 300-bp homology with A3. (H) Homeologous BIR-only construct (yRA192); similar to G except Kl-A3 is substituted for Sc-A3. Sc-URA and Kl-A3 are 76% identical and share a maximum of 17-bp microhomology. (I) Homeologous template switch construct (yRA58). HO-induced DSB next to UR is repaired by homologous BIR between Sc-UR and Sc-RA and homeologous template switching between Sc-RA and Kl-A3 reconstituting a chimeric URA3. The dark-blue and cyan rectangles represent the Sc-URA3 and Kl-URA3 sequences, respectively.

Figure 3.

Template switching followed the initial DNA synthesis of BIR without a significant delay. Kinetics of the initial DNA synthesis (BIR) and template switching were examined by primer extension assay with quantitative PCR. (A) Experimental scheme for quantitative PCR. The primer pairs employed are represented by arrows. (B) Kinetics of BIR and template switching are shown in the same graph. (C) Kinetics of template switching (zoomed in) are shown as a separate graph. The frequency of template switching was estimated to be ∼2%∼6% of the all-BIR invasion attempts, consistent with the results from the genetic assay. Error bars represent the range of two independent experiments.

Figure 4.

Sequence usage distinguishes canonical strand invasion from template switch. (A) Microhomology usage during strand invasion in a homeologous BIR strain. An HO DSB near the Sc-UR is repaired first by strand invasion into the homeologous Kl-RA3 sequence (yRA57). Arrows show the frequencies of microhomology usage during the invasion event. (B) Microhomology usage during strand invasion in homeologous BIR in a template switch strain (yRA54). An HO DSB near the Sc-UR is repaired first by strand invasion into the homeologous Kl-RA sequence. Arrows show the frequencies of microhomology usage during the invasion event. (C) Sequence usage during the template switch from Sc-UR to Kl-RA3 (yRA204). An HO DSB near the Sc-UR is repaired first by strand invasion into the homologous Sc-UR* sequence in which the promoter and 12 bp 5′ of the ORF are deleted (represented by the blue block with a jagged edge). The subsequent template switch between the Sc-UR* and the homeologous Kl-RA3 sequence reconstitutes a functional chimeric URA3. Arrows show the frequencies of microhomology usage during the template switch event.

Figure 5.

The 3′ end preference during homeologous BIR between highly divergent sequences is reduced in the absence of Msh6. (A) Relative efficiencies of homologous BIR in wild type (WT) and msh6Δ. (B) Relative efficiencies of homeologous BIR in wild type and msh6Δ. (C) Microhomology usage in the absence of MSH6 during strand invasion in the homeologous BIR strain. Note the reduced 3′ end preference compared with the wild type (Fig. 4A). (D) Microhomology usage during strand invasion in a homeologous BIR strain with low sequence divergence (76%). Arrows show the frequencies of microhomology usage during the invasion event. Letters in dark blue and cyan represent the S. cerevisiae and K. lactis sequences, respectively.

Figure 6.

BIR and template switch have different requirements for Rad51, Pol32, and Rdh54. (A) BIR frequencies in wild type (WT), rdh54Δ, rad51Δ, and pol32Δ. (B) Template switch frequencies in wild type, rdh54Δ, rad51Δ, and pol32Δ during BIR. (C) Template switch frequencies in wild type, rdh54Δ, rad51Δ, and pol32Δ during SSA.

Figure 7.

Ty and δ element-mediated template switching. (A) yRA107 construct. DSB next to the UR sequence is repaired by BIR using the RA3 sequence, resulting in loss of the centromere-distal broken fragment and reconstitution of the URA3 gene. Note that DNA synthesis of the invading BIR fork is directed toward the telomere. (B) yRA108 construct. The DSB next to the UR sequence is repaired by BIR using the RA3 sequence, resulting in loss of the centromere-distal broken fragment and reconstitution of the URA3 gene. In contrast to A, the invading BIR fork is directed toward the centromere, potentially leading to dicentric chromosomes and subsequent chromosome instability. (C) BIR frequencies of the yRA107 and yRA108 constructs. (D) PFGE analyses of yRA107 and yRA108. (Top panel) (M) Chromosome size marker; (a1 and a2) uncut yRA107 and yRA108 controls; (b1 and b2) yRA107 BIR survivors; (c1 to c10) yRA108 BIR survivors. (Bottom panel) Southern blot analyses of the PFGE with URA3 ORF as the probe. Multiple bands seen in c1, c4, and c6 are putative unstable dicentric intermediates. (E,F) aCGH analyses of c3 and c5 from D. Green troughs represent deletion of the centromere-distal chromosome fragment. Red peaks represent duplications/triplications. Schematic interpretations of the respective aCGH analyses. Ty and δ elements that mediated the template switch events are shown as large and small red triangles, respectively. Hashed patterns represent new DNA synthesis (please see the text for details). The event shown in E results in the loss of the left arm of Chr 5 distal to the CAN1 locus and a concomitant duplication of a portion of the left of Chr 3. The event shown in F results in the loss of left arm of Chr 5 distal to the CAN1 locus and a concomitant triplication of a portion of right arm of Chr 5.