EEPD1 Rescues Stressed Replication Forks and Maintains Genome Stability by Promoting End Resection and Homologous Recombination Repair

Abstract

Replication fork stalling and collapse is a major source of genome instability leading to neoplastic transformation or cell death. Such stressed replication forks can be conservatively repaired and restarted using homologous recombination (HR) or non-conservatively repaired using micro-homology mediated end joining (MMEJ). HR repair of stressed forks is initiated by 5' end resection near the fork junction, which permits 3' single strand invasion of a homologous template for fork restart. This 5' end resection also prevents classical non-homologous end-joining (cNHEJ), a competing pathway for DNA double-strand break (DSB) repair. Unopposed NHEJ can cause genome instability during replication stress by abnormally fusing free double strand ends that occur as unstable replication fork repair intermediates. We show here that the previously uncharacterized Exonuclease/Endonuclease/Phosphatase Domain-1 (EEPD1) protein is required for initiating repair and restart of stalled forks. EEPD1 is recruited to stalled forks, enhances 5' DNA end resection, and promotes restart of stalled forks. Interestingly, EEPD1 directs DSB repair away from cNHEJ, and also away from MMEJ, which requires limited end resection for initiation. EEPD1 is also required for proper ATR and CHK1 phosphorylation, and formation of gamma-H2AX, RAD51 and phospho-RPA32 foci. Consistent with a direct role in stalled replication fork cleavage, EEPD1 is a 5' overhang nuclease in an obligate complex with the end resection nuclease Exo1 and BLM. EEPD1 depletion causes nuclear and cytogenetic defects, which are made worse by replication stress. Depleting 53BP1, which slows cNHEJ, fully rescues the nuclear and cytogenetic abnormalities seen with EEPD1 depletion. These data demonstrate that genome stability during replication stress is maintained by EEPD1, which initiates HR and inhibits cNHEJ and MMEJ.

Fig 1. EEPD1 deficiency reduces clonogenicity and growth rate, extends S phase, and sensitizes cells to replication stress.

(A) A549 cells were transfected with control siRNA or siRNA targeting EEPD1 and plating efficiencies were determined (mean ±SEM). (B) Relative growth rates of control and EEPD1 deficient cells (mean ±SEM). (C,D) Immunofluorescence microscopy of control and EEPD1 deficient A549 cells stained with DAPI, cyclin A (S phase marker), and phospho-H3 (M phase marker) at indicated times after siRNA transfection. Representative data are shown in panel C. Quantitation of 4–12 determinations (124–468 nuclei/determination) scored per time point is shown in panel D; values are mean percentages (±SEM) of cyclin A- or phospho-H3-positive nuclei. (E) Clonogenic survival of A549 cells transfected with si-EEPD1 or control siRNA, and then treated with various replication stress agents. EEPD1 repression was confirmed by Western blot, above (n = 6–9 in triplicate, means ±SEM). *, **, *** indicate P≤0.05, 0.01, 0.001 (t tests), respectively, in this and all subsequent figures unless otherwise specified.

Fig 2. EEPD1 promotes replication fork restart after stress.

(A) Replication recovery assayed as percentage of cells with ≥3 BrdU foci 2 h after release from 18 h treatment with 10 mM HU. Representative data (left) and quantitation (right) for cells transfected with control siRNA or si-EEPD1 targeted to 3’ UTR, with or without expression of siRNA-resistant FLAG-tagged EEPD1 (n = 11–23 determinations per condition, >100 cells scored/condition, means ±SEM). EEPD1 expression is shown by Western blot below for each condition. (B,C) Restart of stalled forks by DNA fiber analysis with HEK-293 cells transfected with empty vector (CMV), CMV-EEPD1 overexpression vector, control siRNA, or EEPD1 siRNA analyzed 15–30 min after release from HU replication stress. Representative images of fibers with IdU stained red and CldU stained green (B) and fiber quantitation (C) shown as percentage (means ±SD) of restarted forks (red + green fibers), stopped forks (red fibers), and new forks (green fibers) for >3 distinct determinations per condition (121–211 fibers/condition). (D) Fiber lengths and symmetry were measured in control and EEPD1 deficient cells to determine replication speed (left), and the percentage of bidirectional fibers (right), defined as red fibers with flanking green segments.

Fig 3. EEPD1 promotes HR DSB repair and suppresses cNHEJ.

(A,B) cNHEJ repair of I-SceI-induced DSBs was measured in EJ5 cells with or without EEPD1 depletion by EEPD1 or control lentiviral shRNA, and assayed as percentages of GFP⁺ cells by flow cytometry (n = 12 in triplicate, means ±SD). HR repair of I-SceI-induced DSBs was measured in HT256 cells with or without EEPD1 depletion assayed as frequencies of G418-resistant colonies per viable cell (n = 15 in triplicate, mean ±SD). (C) HT256 gene conversion tract spectra with or without EEPD1 depletion were determined by mapping 12 silent restriction site markers in the neo gene. Bars indicate converted markers for each tract type; the number of products of each tract type is listed with percentages. (D) Tract lengths of each product are plotted; bars indicate mean ± 95% confidence intervals. (E) Clonogenic survival of A549 cells treated with olaparib for 18 h at indicated doses with or with EEPD1 repression (n = 3 in triplicate, mean ± SEM).

Fig 4. HR requires EEPD1 to a greater extent than MMEJ.

(A) Schema of the MMEJ/HR-MluI reporter system and Western blot confirming EEPD1 knockdown. (B) Flow cytometry of cells with and without I-SceI transduction. (C) Representative results of PCR amplified EGFP⁺ products digested with BssHII (MMEJ) or MluI (HR). The percentage of the total product digested by each enzyme indicates the relative utilization of each repair pathway. (D) Graphical representation of the densitometric analysis of the cleaved PCR products over total products, showing relative fractions of HR and MMEJ in cells with or without EEPD1 depletion (n = 3).

Fig 5. EEPD1 promotes end resection and downstream replication stress signaling.

(A,B) End resection after IR measured by the fraction of cells with ss BrdU present in non-denatured DNA. Representative images (A) and quantitation (B) are shown as mean ±SD, n = 11–19 per condition, 139–180 cells/condition. (C) End resection adjacent to a single I-SceI DSB in HT1904 cells was measured in control cells and in cells depleted for EEPD1, CtIP and/or Exo1, alone or together (n = 3, means ± SD). For depletion of each protein, see S6 Fig. (D,E) Phospho-S4/S8 RPA32, gamma-H2Ax, and RAD51 nuclear foci formation in A549 cells after replication stress with and without EEPD1 depletion. DAPI nuclear counterstain is blue. (F,G) Phosphorylation of ATR (T1989), Chk1 (S345), and RPA32 (S4/S8) analyzed by Western blot in HU or mock-treated A549 cells with and without EEPD1 depletion. Representative blot (F) and quantification (n = 3–4 blots, means ±SD) (G) presented as relative protein levels normalized to β-actin loading controls. (H) Representative results (left) of alkaline single cell electrophoresis assays in untreated or HU-treated A549 cells with or with EEPD1 depletion, and quantitation (right) showing means ±SEM (n = 5).

Fig 6. EEPD1 is recruited to replication forks in response to HU replication stress.

(A,B) HEK-293 cells over-expressing wild-type V5-tagged EEPD1 treated with 10 mM HU for 18 h, chromatin was isolated 0–2 h after HU release and probed for EEPD1, and histone H3 as loading control (n = 4). Immunoblots (A) and densitometric measures of EEPD1 (B) are shown as average relative protein levels (means ±SD, n = 4) normalized to H3 as a chromatin loading control. (C) iPOND analysis of HEK-293 cells over-expressing V5-tagged EEPD1. Cells were incubated for 10 min in medium with 10 uM EdU to label nascent DNA, and then treated with 3 mM HU for indicated times to stall replication forks. (D) Control iPOND assay using a thymidine chase confirms the specificity of EEPD1 recruitment to nascent DNA. (E) Chromatin immunoprecipation of EEPD1 recruited to single DSB within neo locus in HT1904 cells. Schema showing PCR primer pairs relative to DSB site (above) and PCR results (below). (F,G) Co-immunoprecipitation of EEPD1 with Exo1, CtiP, BLM, and RPA32, but not Dna2. (H) Degradation of Exo1 and BLM when EEPD1 is depleted. Representative blot above, quantitation (mean ±SEM) of three replicate blots, below.

Fig 7. EEPD1 maintains genome stability and is overexpressed in colorectal cancers.

(A) A549 cells were transfected with control siRNA or si-EEPD1 were stained with DAPI and analyzed for nuclear aberrations. Arrows indicate micronuclei and nuclear bridges. (B) Confirmation of 53BP1 and/or EEPD1 depletion by Western blot analysis of A549 cells transfected with cognate siRNAs; loading control is eEF2. (C,D) Representative images of unstressed A549 cells from panel B, with arrows indicating micronuclei (C), and quantitation of nuclear bridges and micronuclei plotted as mean percentages of nuclear aberrations (n = 10, 142–190 nuclei/determination) ± SD. (E) Representative photomicrographs of chromosome aberrations. (F) Quantification of chromosome aberrations in A549 cells treated with HU, IR or untreated, and with depletion of EEPD1 and/or 53BP1 (n = 3 metaphase spreads per condition, 102–374 metaphases scored per spread). (G) EEPD1 expression was determined in colorectal carcinomas and adjacent normal mucosa samples. Box and whisker plots are shown with median (heavy line) and upper/lower quartiles indicated (bars). EEPD1 expression is 2.3-fold higher in tumor samples (P = 9×10⁻³⁰).