RAD-51-dependent and -independent roles of a Caenorhabditis elegans BRCA2-related protein during DNA double-strand break repair

Abstract

The BRCA2 tumor suppressor is implicated in DNA double-strand break (DSB) repair by homologous recombination (HR), where it regulates the RAD51 recombinase. We describe a BRCA2-related protein of Caenorhabditis elegans (CeBRC-2) that interacts directly with RAD-51 via a single BRC motif and that binds preferentially to single-stranded DNA through an oligonucleotide-oligosaccharide binding fold. Cebrc-2 mutants fail to repair meiotic or radiation-induced DSBs by HR due to inefficient RAD-51 nuclear localization and a failure to target RAD-51 to sites of DSBs. Genetic and cytological comparisons of Cebrc-2 and rad-51 mutants revealed fundamental phenotypic differences that suggest a role for Cebrc-2 in promoting the use of an alternative repair pathway in the absence of rad-51 and independent of nonhomologous end joining (NHEJ). Unlike rad-51 mutants, Cebrc-2 mutants also accumulate RPA-1 at DSBs, and abnormal chromosome aggregates that arise during the meiotic prophase can be rescued by blocking the NHEJ pathway. CeBRC-2 also forms foci in response to DNA damage and can do so independently of rad-51. Thus, CeBRC-2 not only regulates RAD-51 during HR but can also function independently of rad-51 in DSB repair processes.

FIG. 1.

CeBRC-2 possesses a subset of conserved domains present in human BRCA2. A scaled representation of human BRCA2 compared with CeBRC-2 is shown at the top. The various conserved domains, including the BRC repeat region (red), the helical region (yellow), OB folds (green), the tower-like structure (blue), and putative NLSs (black-orange), are indicated. The single BRC motif (residues 9 to 114) in CeBRC-2 is situated at the N terminus of CeBRC-2. Two putative NLSs are located on either side of a single OB fold situated at the C terminus of the protein (residues 263 to 370). aa, amino acids. (A) Protein sequence alignment of the eight BRC motifs of BRCA2 (abbreviated brc1 to brc8) with the single BRC motif of CeBRC-2 (CeBRC-2_brc). Asterisks indicate the critical residues required for the BRC4-Rad51 interaction, as defined structurally (34). (B) Alignment of the OB fold domain of CeBRC-2 (CeBRC-2_OB fold) with the OB fold of RPA1 from six different species (At, A. thaliana; rice; Mus, mouse; Hs, human; Nc, Neurospora crassa; and Ce, C. elegans).

FIG. 2.

CeBRC-2 and RAD-51 interact directly in vitro and in vivo. (A) The yeast two-hybrid system was used to test for protein interactions among RAD-51, RAD-51D, CeBRC-2 (residues 1 to 114), CeBRC-2 (1 to 250), CeBRC-2 (full length [FL]), CeBRC-2 (114 to 394), RPA-1, RPA-2, and MRT-2 fused to either the DNA binding domain (DB) or the activation domain (AD) of GAL4 by scoring for lacZ expression. Controls: 1, DB-DP and AD-E2F1; 2, Gal4p and AD; 3, DB-Fos and AD-Jun; 4, DB-pRB and AD-E2F1; and 5, DB and AD without any fusion (5). Lane M, markers. (B) CeBRC-2, CeBRC-2(His₆), and RAD-51 were expressed in E. coli (10% of the whole-cell extracts used in the pull-down assays is shown in lanes 1 to 4), and pull-down assays were performed with whole-cell extracts and Talon beads, which specifically bind to proteins containing polyhistidine tracks. RAD-51 was pulled down on Talon beads with full-length C-terminal histidine-tagged Ce-BRC-2 (lane 8) but not when expressed alone (lane 7) or with untagged CeBRC-2 (lane 9). Pull-down assay samples were resolved by SDS-12% PAGE and stained with Coomassie brilliant blue. (C) Flag-tagged CeBRC-2 was coimmunoprecipitated with anti-Myc MAb 9E10 when coexpressed in 293T cells with CMV_Myc-RAD-51 (lane 5) but not with CMV_Myc (lane 3). WB, Western blot; IP, immunoprecipitation. Approximately 30% of Myc-RAD-51 in the extracts was pulled down with Flag-tagged CeBRC-2. (D) Ce-BRC-2 and RAD-51 were coimmunoprecipitated with anti-Myc MAb 9E10 (lane 3) and anti-HA MAb 12CA5 (lane 4) from extracts derived from the C. elegans dwIs7 (P_brc-2brc-2::HA_8×His_Tev_Myc) transgenic line, which expresses CeBRC-2 fused at the C terminus to HA_8×His_Tev_Myc epitopes, but not from extracts derived from an untagged strain (lanes 1 and 2). Wt, wild type. We estimated that 30 to 35% of the RAD-51 pool in the extracts was pulled down with CeBRC-2. (E) Purified full-length recombinant CeBRC-2(His₆). An SDS-12% PAGE analysis of purified CeBRC-2(His₆) stained with Coomassie brilliant blue is shown. (F) DNA binding activity of CeBRC-2. DNA binding reactions with mixtures containing ssDNA or dsDNA and the indicated concentrations of CeBRC-2 were carried out as described in Materials and Methods. Protein-DNA complexes (indicated by an arrow) were analyzed by 4% PAGE. Asterisks indicate 5′-³²P-end labels.

FIG. 3.

Cebrc-2 deletion mutant. (A) Schematics of the gene structure of Cebrc-2 (T07E3.5) and the predicted protein product for wild-type (Wt) N2 (394-residue protein) and the brc-2 (tm1086) deletion mutant (138-residue predicted protein). brc-2 (tm1086) carries a 672-bp deletion in the Cebrc-2 gene that removes exons 5 to 8. aa, amino acids. (B) Nested PCR with Cebrc-2-specific primers of wild-type N2 (lanes 1 and 4) and brc-2 (tm1086) heterozygotes (lanes 2 and 3) showing the 672-bp deletion. In lanes 2 and 3, the faint band above the tm1086 deletion product corresponds to the internal PCR product amplified from the wild-type chromosome. (C) Although a 138-residue protein could be expressed from the brc-2 (tm1086) allele, Western blotting with an N-terminus-specific CeBRC-2 antibody failed to detect any protein in a brc-2 (tm1086)^−/− mutant protein compared with full-length CeBRC-2 protein in wild-type N2. The asterisk indicates a nonspecific protein that cross-reacted with the CeBRC-2 antibody.

FIG. 4.

Embryonic lethality and meiotic DSBR defects in Cebrc-2 mutants. (A) Table of the number of viable progeny and the number of DAPI-stained structures observed at diakinesis in animals of the indicated genotype (n, number counted). The corresponding defect(s) in meiosis is indicated. N2 (wild type [Wt]) (1) and the lig-4 mutant (7) have a very low frequency of embryonic lethality and display six bivalent chromosomes at diakinesis. Cebrc-2 (2), rad-51 (3), Cebrc-2 rad-51 (4), and rad-51 lig-4 (9) mutants fail to produce any viable progeny and display between one and five DAPI-stained structures at diakinesis. Cebrc-2 lig-4 (8) and Cebrc-2 rad-51 lig-4 (10) mutants fail to produce any viable progeny and display nine or more DAPI-stained structures at diakinesis. (B) Germ lines from adult hermaphrodites of the indicated genotype were isolated, fixed in paraformaldehyde, and stained with DAPI. A representative projection of a three-dimensional data stack through a single oocyte nucleus at the diakinesis stage of the meiotic prophase is shown. N2 (wild type) (panel 1) and the lig-4 mutant (7) display six DAPI-stained bivalent chromosomes at diakinesis. Aggregation of chromosomes and chromatin decompaction are detected at diakinesis in Cebrc-2 (panel 2), rad-51 (3), Cebrc-2 rad-51 double (4), and lig-4 (RNAi) rad-51 double (9) mutants. Twelve DAPI-stained univalents are seen in spo-11 (panel 5) and spo-11 Cebrc-2 double (6) mutants. Twelve or more DAPI-stained structures are seen in lig-4 (RNAi) Cebrc-2 double (panel 8) and Cebrc-2 lig-4 (RNAi) rad-51 triple (10) mutants. Scale bar, 5 μm.

FIG. 5.

Loss of Cebrc-2 disrupts RAD-51 localization and results in RPA-1 accumulation at DSBs. (A) Low-magnification images of a wild-type germ line stained with DAPI depicting the six zones in which RAD-51, RPA-1, and apoptosis are quantitated. (B) Representative images of RAD-51 staining in midpachytene nuclei (panels 1 to 5) and quantitation of RAD-51 foci in the six zones of the germ line (6 to 10) for the indicated genotypes. Wt, wild type. (C) Representative images of RPA-1 staining in late-pachytene nuclei (panels 1 to 5) and quantitation of RPA-1 foci in the six zones of the germ line (6 to 10) for the indicated genotypes. (D) Increased apoptotic corpses in rad-51, Cebrc-2, and Cebrc-2 rad-51 double mutants. Corpses were counted in each of the six zones and are shown for the indicated genotypes as previously described (5).

FIG. 6.

Radiation-induced defects in Cebrc-2 mutants. RAD-51 and RPA-1 staining reveal radiation-induced DSBR defects in Cebrc-2 mutants and following microinjection of dominant-negative BRC peptides into N2 (wild type [Wt]). Immunostaining was performed for RAD-51 (A) and RPA-1 (B) on germ lines of the indicated genotypes at 4 h after treatment with 75 Gy of gamma irradiation. The average number of RAD-51 and RPA-1 foci per nucleus is graphically represented (n, number of nuclei counted) The average number of foci per nucleus in the absence of gamma irradiation is shown by the white bars. (C) Schematic of wild-type (BRC_Wt) and mutant (BRC_Mut) BRC peptides. The mutant BRC peptide has a deletion of seven residues within the RAD-51 interaction domain. The BRC_Wt peptide efficiently pulls down RAD-51 from whole worm extracts, but the BRC_Mut peptide is defective for RAD-51 binding. Peptide pull-down assay samples and 1/10 the input (^1/10I) were subjected to Western blotting with a RAD-51 antibody. (D) Representative images of RAD-51 staining in germ lines injected with BRC_Wt and BRC_Mut peptides. Each peptide (1 mg/ml) was microinjected into the germ line of 25 N2 (wild-type) animals. At 2 h after injection, animals were exposed to 75 Gy of gamma irradiation. At 4 h after irradiation, germ line nuclei were fixed and immunostained with RAD-51 antibody.

FIG. 7.

CeBRC-2 forms foci after DNA damage independent of rad-51. Representative images show CeBRC-2 staining in mitotic germ line nuclei of the indicated genotypes before and 4 h after treatment with 75 Gy of gamma irradiation (IR). Wt, wild type.

FIG. 8.

Possible roles of CeBRC-2 in DSBR. (A) In wild-type (N2) animals, CeBRC-2 functions in DSBs through HR by transporting RAD-51 into the nucleus and targeting RAD-51 to processed DBSs. (B) In rad-51 mutants (defective for HR), CeBRC-2 may displace or prevent the accumulation of RPA-1 at resected DSBs. CeBRC-2 can also promote an alternative DSBR (aDSBR) pathway distinct from NHEJ. (C) In Cebrc-2 mutants (defective for HR and aDSBR), RPA-1 persists or accumulates at DSBs, and repair ensues by NHEJ.