Role for the mammalian Swi5-Sfr1 complex in DNA strand break repair through homologous recombination

Abstract

In fission yeast, the Swi5-Sfr1 complex plays an important role in homologous recombination (HR), a pathway crucial for the maintenance of genomic integrity. Here we identify and characterize mammalian Swi5 and Sfr1 homologues. Mouse Swi5 and Sfr1 are nuclear proteins that form a complex in vivo and in vitro. Swi5 interacts in vitro with Rad51, the DNA strand-exchange protein which functions during HR. By generating Swi5(-/-) and Sfr1(-/-) embryonic stem cell lines, we found that both proteins are mutually interdependent for their stability. Importantly, the Swi5-Sfr1 complex plays a role in HR when Rad51 function is perturbed in vivo by expression of a BRC peptide from BRCA2. Swi5(-/-) and Sfr1(-/-) cells are selectively sensitive to agents that cause DNA strand breaks, in particular ionizing radiation, camptothecin, and the Parp inhibitor olaparib. Consistent with a role in HR, sister chromatid exchange induced by Parp inhibition is attenuated in Swi5(-/-) and Sfr1(-/-) cells, and chromosome aberrations are increased. Thus, Swi5-Sfr1 is a newly identified complex required for genomic integrity in mammalian cells with a specific role in the repair of DNA strand breaks.

Figure 1. Mouse Swi5 and Sfr1 interact in vivo and in vitro.

(A) Schematic diagrams depict Swi5, Sfr1 and the respective truncation mutants. (B) Interaction between Swi5 and Sfr1 was analyzed by yeast two-hybrid analysis. Reciprocal combinations of Gal4AD and Gal4DBD-fusion proteins were examined. Control plate, SD media without leucine and tryptophan; Experimental, SD media without leucine, tryptophan, histidine, and adenine. (C) Interaction between Swi5 and Sfr1 was analyzed by GST pull-down assays using recombinant proteins expressed in E. coli. CBB-stained SDS polyacrylamide gels of His₆-Sfr1 expression (left) and pull-down by GST or GST-Swi5 fusion protein (right). (D) Yeast two-hybrid assay using the truncated Swi5 protein described in A. Gal4AD-Swi5N exhibited interaction with Gal4DBD-Sfr1. (E) Yeast two-hybrid assay using the truncated Sfr1 proteins described in A. Gal4DBD-Sfr1C interacted with Gal4AD-Swi5. (F) GST pull-down assay using Swi5N. Pull-down of GST-Swi5N precipitated His₆-Sfr1. (G) GST pull-down assay using Sfr1C. Pull-down of GST-Swi5 precipitated His₆-Sfr1C. (H) Swi5 and Sfr1 interaction in mouse ES cells was shown by co-immunoprecipitation using anti-Swi5 and anti-Sfr1 antibodies. Interaction with Rad51 was not observed in this assay.

Figure 2. Swi5 and Sfr1 are mutually interdependent for their stability.

(A) Schematic of genomic disruption of Swi5. Exons 3 and 4 are replaced by neo. (B) Schematic of genomic disruption of Sfr1. Exons 2 and 3 are replaced by neo. (C) Swi5 and Sfr1 expression was examined by Western blotting of mouse ES cell lines deficient for Swi5 and Sfr1. The arrowheads indicate Swi5 and Sfr1 protein bands. There is a faint cross-reacting protein at the same position as Swi5. (D) Swi5 ^−/− and Sfr1 ^−/− cells proliferate with similar kinetics to wild-type cells. 2×10⁴ cells were seeded per well of a 6-well plate. Cell proliferation was measured by counting live cells at 24-hour intervals. Means with standard deviations (SD) are shown in the plot. (E) Swi5 ^−/− and Sfr1 ^−/− cells exhibit similar cell cycle profiles compared to wild-type cells. Propidium iodide stained cells were analyzed by flow cytometry. The cell cycle was calculated by FlowJo with a Watson pragmatic model. The means with SD are shown in the graph. (F) Localization of Swi5 and Sfr1 protein in mouse ES cells. Immunofluorescence of Swi5 and Sfr1 is shown in green in the respective left panels, with the DAPI-stained nucleus (blue) additionally shown in the merged images in the respective right panels. In the absence of Sfr1, Swi5 is not detectable; in the absence of Swi5, Sfr1 protein levels are reduced, but are still detectable. (G) Swi5 and Sfr1 do not show specific localization to heterochromatin detected by trimethyl-lysine 9 of histone H3 and intense DAPI staining in MEF cells.

Figure 3. Swi5 and Sfr1 have a role in HR in mammalian cells.

(A) Swi5 interacts with Rad51 in GST pull-down assay using recombinant proteins expressed in E. coli. The upper panels show CBB-stained SDS polyacrylamide gels. Note that Rad51 runs at similar molecular weight as GST-Swi5 (37 kDa). The pull-down was analyzed by Western blotting using anti-Rad51 antibody (EMD chemicals #PC130), as shown in the lower panels. (B) Schematic of the DR-GFP assay . The DR-GFP construct consists of direct repeats of two mutated GFP genes, SceGFP, which is disrupted by an 18 bp recognition site for I-SceI, and the truncated iGFP, genomically integrated into the Hprt locus. When a single DSB generated by I-SceI is repaired via gene coversion with iGFP, expression of GFP is restored and can be measured by FACS analysis. (C) Unperturbed Swi5 ^−/− and Sfr1 ^−/− cells exhibit similar HR frequencies compared to wild-type cells after I-SceI expression. (D–F) DR-GFP assays with co-transfection of empty, BRC3 or BRC3Δ expression vectors, respectively. Swi5 ^−/− and Sfr1 ^−/− cells show decreased HR with BRC3 expression. The respective cDNA expression constructs complemented the phenotypes of Swi5 ^−/− and Sfr1 ^−/− cells. Each value represents data from ≥3 independent experiments. Statistically significant differences are presented with p-values calculated using an unpaired t-test. Means with SD are shown in graphs in C–F.

Figure 4. Swi5 ^−/− and Sfr1 ^−/− cells are defective in the repair of DNA strand breaks.

(A–C) Clonogenic survival assays after treatment with X-rays, camptothecin and etoposide, respectively. (D) Normal induction of Chk2 and Chk1 phosphorylation by X-irradiation in Swi5 ^−/− and Sfr1 ^−/− cells. Cells irradiated with 8 Gy were collected at the indicated time points. Protein extracts were examined by Western blotting to analyze phosphorylation of Chk2 (Millipore #05-649) by mobility shift and Chk1 by a phospho-specific antibody against Serine 345 (Cell Signaling #2341). (E) Normal inhibition of mitotic entry in Swi5 ^−/− and Sfr1 ^−/− cells after X-irradiation. Cells irradiated at 8 Gy followed by two hours post incubation were fixed in 70% ethanol. Mitotic cells were stained using anti-phospho-histone H3 antibody (Millipore #06-570) and counted by flow cytometry. Means with SD are shown in graphs in A–C and E.

Figure 5. Swi5 ^−/− and Sfr1 ^−/− cells are sensitive to Parp inhibiton.

(A) Hypersensitivity of Swi5 ^−/− and Sfr1 ^−/− cells to olaparib. Cells were grown with continuous exposure at the indicated concentration of olaparib. Surviving colonies were stained with Giemsa. (B) Chromosome aberrations are induced in Swi5 ^−/− and Sfr1 ^−/− cells to a greater extent than in wild-type cells after olaparib exposure. Metaphase spreads were prepared from cells with or without 48 hour exposure to 0.6 µM of olaparib. Chromosomes stained without banding using Giemsa were examined. Counts of chromosome aberrations are presented in Table S1. Means are shown with the standard error of the mean (SEM). The p-values were calculated using the Mann-Whitney test summing radial chromosomes and chromatid breaks/gaps. (C) Induction of SCEs by olaparib is lower in Swi5 ^−/− and Sfr1 ^−/− cells than in wild-type cells. The y-axis is the number of SCEs per metaphase for each nucleus counted. Cells were incubated in BrdU-containing medium for two cell cycles with or without exposure to 0.1 µM of olaparib for 6 hours before preparation of metaphase spreads. Indicated numbers of nuclei were counted. Means with SEM are shown in the plots. The p-values were calculated using unpaired t-test.