Poly(ADP-ribose) polymerase 1 accelerates single-strand break repair in concert with poly(ADP-ribose) glycohydrolase

Abstract

Single-strand breaks are the commonest lesions arising in cells, and defects in their repair are implicated in neurodegenerative disease. One of the earliest events during single-strand break repair (SSBR) is the rapid synthesis of poly(ADP-ribose) (PAR) by poly(ADP-ribose) polymerase (PARP), followed by its rapid degradation by poly(ADP-ribose) glycohydrolase (PARG). While the synthesis of poly(ADP-ribose) is important for rapid rates of chromosomal SSBR, the relative importance of poly(ADP-ribose) polymerase 1 (PARP-1) and PARP-2 and of the subsequent degradation of PAR by PARG is unclear. Here we have quantified SSBR rates in human A549 cells depleted of PARP-1, PARP-2, and PARG, both separately and in combination. We report that whereas PARP-1 is critical for rapid global rates of SSBR in human A549 cells, depletion of PARP-2 has only a minor impact, even in the presence of depleted levels of PARP-1. Moreover, we identify PARG as a novel and critical component of SSBR that accelerates this process in concert with PARP-1.

FIG. 1.

Reduced rates of SSBR in PARP-1^−/− chicken DT40 cells. (A) Total DNA strand breakage was quantified in wild-type (WT) and PARP-1^−/− DT40 cells by alkaline comet assays with untreated cells (Unt.), with cells immediately after treatment with 25 μM H₂O₂ for 20 min on ice (0), and with H₂O₂-treated cells after the indicated repair period in H₂O₂-free medium. Data points are means (± 1 SE) of at least three independent experiments, with the average tail moment from 100 cells quantified in each experiment. (B) Total DNA strand breakage was quantified in wild-type (WT), PARP-1^−/−, KU70^−/−, and XRCC3^−/− DT40 cells as described above. (C) The data from panel B was replotted as the fraction (%) of DNA strand breaks remaining at the indicated time points. **, PARP-1 and WT repair kinetics were significantly different (analysis of variance, P = 3 × 10⁻⁴). Ku70^−/− and XRCC3^−/− repair kinetics were not significantly different from those of the WT (P = 0.47 and P = 0.15, respectively). (D) A representative scatter plot of the raw data from one of the experiments used in panels B and C to show the level of variation in DNA strand breakage within single populations of cells. Each dot represents the tail moment of an individual cell, and 100 cells were scored per sample.

FIG. 2.

Depletion of PARP-1 but not PARP-2 reduces rates of chromosomal SSBR and sensitizes human A549 cells to oxidative DNA damage. (A) Levels of PARP-1 and PARP-2 protein in total cells extracts from A549 cells transfected with pcD2E and either empty pSuper (Control), pSuper-PARP-1 (PARP-1), pSuper-PARP-2 (PARP-2), or both pSuper-PARP-1 and pSuper-PARP-2 (PARP-1/PARP-2), as measured by immunoblotting with appropriate antibodies. (B) Levels of PAR before and after (1-min repair) treatment with 10 mM H₂O₂ on ice with A549 cells depleted of the indicated proteins, as measured by indirect immunofluorescence microscopy. Cells were counterstained with DAPI to identify nuclear DNA. (C) Clonogenic survival of A549 cells depleted of the indicated proteins following exposure to the indicated concentrations of H₂O₂ in PBS for 10 min at RT. Cells were fixed after 14 days and stained with methylene blue, and the fraction (%) of surviving cells was calculated. Data are the means (± 1 SE) of three independent experiments. **, the survival curve for control cells was significantly different (by analysis of variance [ANOVA]) from those of PARP-1-depleted (P = 0.009) and PARP-1/PARP-2-depleted (P = 0.01) cells but not those of PARP-2-depleted cells (P = 0.57). The survival curves for PARP-1- and PARP-1/PARP-2-depleted cells were not significantly different (P = 0.76). (D) Total DNA strand breakage was quantified by comet assays with A549 cells depleted of the indicated proteins before (Unt.) and immediately after (0) treatment with 100 μM H₂O₂ for 20 min on ice and after the indicated repair periods in H₂O₂-free medium. Data points are the means (± 1 SE) of at least three independent experiments, with the average tail moment from 100 cells calculated in each experiment. (E) The data from panel D were replotted as the fraction (%) of DNA strand breaks remaining at the indicated DNA repair time points. **, the repair kinetics for control cells were statistically significantly (ANOVA) different from those of PARP-1-depleted (P = 7.4 × 10⁻⁷) and PARP-1/PARP-2-depleted (P = 0.68 × 10⁻⁸) cells but not those of PARP-2-depleted cells (P = 0.87). The repair kinetics for PARP-1- and PARP-1/PARP-2-depleted cells were not significantly different (P = 0.1).

FIG. 3.

H₂O₂-induced formation and removal of γ-H2AX from normal and PARP-1-depleted A549 cells. γ-H2AX foci were quantified in normal and PARP-1-depleted A549 cells before (Unt.) treatment with 100 μM H₂O₂ for 20 min on ice and after the indicated repair periods in H₂O₂-free medium. Data points are the means (± 1 SE) of three independent experiments. Note that the kinetics at which γ-H2AX foci declined in normal and PARP-1-depleted cells were not significantly different (analysis of variance, P = 0.057).

FIG. 4.

Impact of PARP-1 and/or PARG depletion on levels of H₂O₂-induced PAR synthesis. (A) The left panel shows levels of PARP-1 and PARG proteins in total cell extracts from A549 cells transfected with pcD2E and either empty pSuper (Control), pSuper-PARP-1 (PARP-1), pSuper-PARG (PARG), or both pSuper-PARP-1 and pSuper-PARG (PARP-1/PARG), as measured by immunoblotting with anti-PARP-1 MAb, anti-PARG polyclonal antibody, and anti-PNK polyclonal antibody as a loading control. The right panel shows the immunoblot of a different set of cell extracts from normal (−) and PARG-depleted A549 cells with anti-PARG antibody, showing the specificity of the antibody in the region of the blot containing full-length (110-kDa) PARG. The positions of molecular weight (MW) standards are shown. (B) Levels of PAR (rows P) in normal (Control) or PARG-1-depleted (PARG RNAi) A549 cells before treatment with 10 mM H₂O₂ on ice (−H₂O₂), 1 min after H₂O₂ treatment (+H₂O₂), and after the indicated repair periods in drug-free medium, as measured by indirect immunofluorescence microscopy. Cells were counterstained with DAPI (rows D) to identify nuclear DNA. (C) Levels of PAR (rows P) in PARG-1-depleted (PARG RNAi) or PARG-1/PARP-1-depleted (PARG/PARP-1 RNAi) A549 cells treated as described in the legend to panel B. Cells were counterstained with DAPI (rows D) to identify nuclear DNA.

FIG. 5.

PARG accelerates SSBR in concert with PARP-1 in human A549 cells. (A) Clonogenic survival of A549 cells depleted or not of PARG following exposure to the indicated concentrations of H₂O₂ for 10 min at RT. Cells were fixed after 14 days and stained with methylene blue, and the fraction (%) of surviving cells was calculated. Data are the means (± 1 SE) of three independent experiments. **, the difference between the control and the PARG-depleted survival curves is statistically significantly (analysis of variance [ANOVA], P = 4.7 × 10⁻⁵). (B) Total DNA strand breakage was quantified by alkaline comet assays with control A549 cells (Control), PARP-1-depleted A549 cells (PARP-1 RNAi), PARG-depleted A549 cells (PARG RNAi), or PARP-1/PARG-depleted A549 cells (PARP-1/PARG RNAi) before (Unt.) and immediately after (0) treatment with 100 μM H₂O₂ for 20 min on ice and after the indicated repair periods in H₂O₂-free medium. Data points are the means (± 1 SE) of at least three independent experiments, with the average tail moment from 100 cells calculated in each experiment. (C) The data from panel B were replotted as the fraction (%) of DNA strand breaks remaining at the indicated DNA repair time points. **, statistically significant (ANOVA) differences were observed between the repair kinetics of control cells and those treated with either PARP-1 (P = 0.004), PARG (P = 0.001), or PARP-1/PARG (P = 0.001) RNAi. Repair kinetics of cells treated with PARP-1/PARG RNAi are not significantly different from those treated with PARP-1 or PARG RNAi alone.

FIG. 6.

Accumulation of RFP-XRCC1 in normal and PARP-1- or PARG-depleted HeLa cells. (A) RFP-XRCC1 foci were detected with HeLa cells transiently transfected with an mRFP-XRCC1 expression construct and either an empty pSuper vector, a pSuper-PARP1 RNAi construct, or a pSuper-PARG RNAi construct by direct fluorescence microscopy. Cells were either mock treated (Unt.) or treated with 100 μM H₂O₂ for 20 min on ice followed by incubation in drug-free medium for the indicated repair periods. Nuclei were counterstained with DAPI. Bars represent 10 μm. Representative images are shown. (B) Quantification of the results from the experiment shown in panel A. Transfected (RFP-positive) cells were chosen at random, and the number of XRCC1 foci present was scored. Data are from a single experiment representative of multiple repeats.