To investigate the role of TDG during 5-FU treatment of cells in culture, we established SV40 immortalized mouse embryonic fibroblasts (MEFs) with homozygous or heterozygous Tdg disruptions (Tdg^+/+, Tdg^+/−, Tdg^−/−) from embryos (embryonic day [ED] 9.5) of heterozygous matings. The Tdg knockout allele, generated by classical gene targeting, had a replacement of exons 6 and 7, encoding parts of the catalytic core of TDG, with a neomycin resistance cassette (Figure S1). We then used litter-matched MEF lines for phenotypic examination. Western blotting with a polyclonal anti-mouse TDG antibody confirmed that neither full-length nor truncated versions of TDG were present in whole-cell extracts of the homozygous knockout MEFs, whereas heterozygous cells produced about half endogenous levels of the protein (Figure 1A; unpublished data). Continuous exposure of these MEFs to 5-FU for 48 h reduced living cell counts in a dose-dependent manner. However, compared to wild-type MEFs, TDG-deficient cells displayed a remarkable resistance (Figure 1B), and heterozygous cells showed an intermediate 5-FU sensitivity (Figure S2). These findings implicated a rate-limiting contribution of TDG to 5-FU–mediated cytotoxicity. A differential response of TDG-proficient and -deficient MEFs to 5-FU treatment was also observed in a real-time assessment of growth behavior. Whereas the cell numbers in cultures of TDG-proficient MEFs started to decline after 36 h of 5-FU exposure, TDG-deficient cells responded with a dose-dependent growth retardation only (Figure 2A).

Since immortalization by the SV40 large-T antigen (LTA) occurs through inactivation of antiproliferative proteins such as p53 or pRb and, thus, can affect the cellular DNA damage response [29,30], we also included spontaneously immortalized MEF cell lines in our analysis. To this end, we set up isogenic Tdg-proficient and -deficient MEF lines by stable transfection of a single clone with either a complementing Tdg transgene under the control of an SV40 promoter or the corresponding expression vector only (Figure 1A). Survival tests then showed that Tdg expression sensitized the Tdg-deficient cells to 5-FU to a level observed with the Tdg-proficient MEFs (Figure 1B). This confirmed that the 5-FU resistance of Tdg knockout cells is a direct consequence of the loss of TDG rather than of unspecific effects by SV40 LTA immortalization or other differences in clonal backgrounds.

To validate the resistance phenotype in cells that are naturally immortal, we examined the 5-FU response of Tdg^+/− and Tdg^−/− mouse embryonic stem (ES) cells generated in our laboratory (Figure 1A) (Y. Saito, unpublished data). Also there, the loss of TDG was associated with a remarkable increase in resistance towards 5-FU (Figure 1B). Hence, the mechanism by which TDG mediates cytotoxicity of 5-FU is active in very divergent cell types, including immortalized differentiated cells as well as undifferentiated stem cells.

To examine the drug specificity of this phenotype, we assessed the sensitivities of TDG-proficient and -deficient MEFs towards the monofunctional DNA alkylating agent methyl methansulfonate (MMS) (Figure 1C). At MMS concentrations yielding ≥10% cell survival, the TDG status did not significantly affect cellular sensitivity. At higher concentrations (≤5% survival), however, TDG-deficient cells were slightly more sensitive. Thus, TDG may contribute to the repair of MMS-induced DNA lesions, but it does not mediate cytotoxicity as it does in the case of 5-FU.

Finally, to address the impact of TDG on long-term survival of 5-FU–treated human cancer cells, we performed clonogenic survival assays. We established HeLa cell clones either stably transfected with a construct overexpressing human TDG from a cytomegalovirus (CMV) promoter or with the corresponding vector only. In addition, we applied a small interfering RNA (siRNA) approach to knockdown TDG in both HeLa cell clones. Continuous exposure of these HeLa cells to 5-FU for 72 h reduced colony forming units in a dose-dependent manner. The cellular sensitivity, however, significantly correlated with TDG protein levels (Figure 2B), being highest for TDG-overexpressing cells and lowest for the vector control cells with additional TDG knockdown. Thus, reduced TDG expression confers a long-term survival benefit to HeLa cells, establishing that the TDG expression status in a human cancer cell line determines its response to treatment with 5-FU.

Biochemical studies revealed that the human TDG acts on a rather broad range of substrates, including G•U and G•5-FU mispairs, but also 5-FU base-paired with adenine. 5-FU, in fact, turned out to be the only base that is efficiently processed by TDG in the normal base-pairing configuration or even in single-stranded DNA [22,23]. We thus reasoned that the excision of 5-FU and/or uracil from genomic DNA by TDG might be a source of 5-FU–mediated cytotoxicity in TDG-proficient cells. To test this, we first validated the 5-FU– and uracil-processing abilities of purified mouse TDG in base-release assays. This showed that, like its human counterpart, the mouse protein excises thymine, uracil, and 5-FU opposite guanine, but also 5-FU paired with adenine, all with comparable efficiencies (Figure 3A). A•U containing homoduplex DNA, however, was hardly processed, suggesting that TDG does not contribute significantly to the repair of A•U base pairs.

To assess the contribution of the endogenous mouse TDG to overall uracil and 5-FU processing, we then analyzed the activities present in nuclear extracts of Tdg wild-type, heterozygous, and null mutant MEFs. G•T processing served as a control and was detectable in extracts from wild-type, but not from homozygous Tdg knockout cells (Figure 3A). Compared to homozygous wild-type cells, heterozygous Tdg knockout cells showed reduced thymine excision activity, consistent with the reduced levels of TDG in these cells (Figures 3B and 1A). Thus, TDG constitutes the major and rate-limiting mismatch-specific thymine excision activity in these cells, suggesting that MBD4, another G•T processing DNA glycosylase [31,32], is not or only poorly active. A lack of MBD4 activity was observed also with protein extracts from mouse ES cells (Y. Saito, unpublished data) and in previous studies with different cell systems [24,33]. Considerably higher amounts of nicked DNA products were detected for all uracil- and 5-FU–containing substrates. Removal of uracil and 5-FU from G•U, G•5-FU, and A•U was equally efficient irrespective of the TDG status. Excision of 5-FU from an A•5-FU substrate, however, was significantly reduced in extracts from Tdg^−/− MEFs (Figure 3A and 3B). The remaining activity on A•5-FU, but also the efficient processing of A•U, G•U, and G•FU in extracts from Tdg knockout MEFs most likely reflects the action of other UDGs with overlapping substrate spectra. As the highly efficient UNG2 was inhibited by addition of saturating amounts of UGI peptide in these assays (unpublished data) and MBD4 activity was not detected, Smug1 most likely represents the redundant uracil- and 5-FU–processing activity observed here. The data therefore suggest that, under conditions of low UNG2 activity in cells, such as outside of S-phase when UNG2 is down-regulated [33–35], TDG constitutes a major and rate-limiting A•5-FU–processing activity.

This is consistent with measurements of 5-FU incorporation into genomic DNA following 5-FU treatment. The genomic levels of uracil and 5-FU upon treatment with 10 μM 5-FU for 48 h were four and 11 times higher in TDG knockout MEFs (3.4 × 10⁵ U residues; 1.7 × 10⁶ 5-FU residues) than in wild-type cells (8.2 × 10⁴ U residues; 1.5 × 10⁵ 5-FU residues), respectively, and this compares to the levels measured in 5-FU–treated Smug1 knockdown cells (D. Barnes, personal correspondence; [9]). Not only do these data confirm that 5-FdUMP gets incorporated into genomic DNA, they also establish that both TDG and Smug1 constitute the major activities processing these lesions, whereas UNG2 does not appear to contribute significantly as also implicated by uracil/5-FU incorporation measurements and sensitivity tests with Ung^−/− knockout cells [9,15].

5-FU treatment has been associated with the generation of DNA strand breaks [2,10,11]. In the light of our biochemical evidence, implicating TDG in processing genomic A•5-FU base pairs, this might be accounted for by an accumulation of apyrimidinic/apurinic sites (AP-sites) in DNA. Through further processing by the BER system, spontaneous breakage, or stalling of DNA polymerases, these could give rise to increased levels of single-stranded DNA breaks (SSBs) in cells. To test this hypothesis, we applied alkaline Comet analyses to assess 5-FU–induced SSB formation in TDG-proficient and -deficient MEFs, as well as in complemented knockout cells stably expressing an ectopic wild-type or catalytic mutant Tdg (Figure 4A). To avoid Tdg overexpression artifacts in the latter [33], we made use of constructs that drive Tdg expression from its endogenous promoter (D. Schuermann, unpublished results). Automated analyses of Comet tail moments then showed similar background levels of DNA strand breaks in all untreated cell populations. Following treatment with 5 μM 5-FU for 24 h and a recovery of another 24 h, however, the tail moments increased significantly above background in TDG-proficient populations, whereas no significant increase was detected for TDG-deficient cells (Figure 4B). Remarkably, cells complemented with the catalytic-inactive mutant form of TDG did not show significantly elevated tail moments after 5-FU treatment. These data indicate that base excision by TDG accounts for the increase in steady-state levels of DNA strand breaks observed upon treatment of cells with 5-FU.

DNA processing after base excision generates SSBs, feeding into a SSB repair pathway whereby XRCC1 plays a central role [36]. To address a possible engagement of SSB repair following 5-FU treatment, we quantified nuclear XRCC1 foci by immunofluorescence detection of the endogenous protein with specific mono- and polyclonal antibodies [37]. This showed indeed that the median number of XRCC1 foci per cell increased after 24 h of low-dose 5-FU treatment and a recovery of 24 h in the absence of the drug (Figure 4C). We therefore conclude that uracil/5-FU excision from genomic DNA activates SSB repair processes at the site of the lesion. Remarkably, 5-FU treatment induced significantly more XRCC1 foci in Tdg knockout cells, indicating higher SSB repair activity in these cells, most probably downstream of uracil/5-FU excision by the remaining UDG activities. Thus, in wild-type cells TDG may compete with these glycosylases for the 5-FU substrates, generate AP-sites, but then prevent efficient downstream processing of the repair intermediates by the SSB repair pathway.

5-FU treatment was shown to delay or even arrest S-phase progression in HeLa and DT40 cells [38,39]. To address the role of TDG in this context, we determined the cell-cycle profiles of TDG-proficient and -deficient MEFs following 5-FU treatment. Relative to the mock control, treatment for 24 h with 5 μM 5-FU and subsequent cultivation in drug-free medium for additional 24 h resulted in a significant enrichment of Tdg wild-type cells in the S (2-fold) and G2/M phases (1.3-fold) of the cell cycle (Figure 5A). This enrichment occurred at the expense of the G1 cell population, which was reduced by a factor of three. By contrast, the 5-FU–induced changes in cell-cycle distribution of TDG-deficient MEFs were less pronounced and not statistically significant (Figure 5A). Since a treatment with hydroxyurea (HU) impeded S-phase progression equally in both cell lines (unpublished data), a defective intra–S-phase DNA-damage checkpoint in the TDG knockout MEFs can be excluded. To corroborate the TDG dependence of the 5-FU–mediated S-phase delay, we compared the response of Tdg knockout cells complemented by stable expression of endogenous levels of wild-type Tdg with that of a vector control. Also in this setting, the S-phase delay induced by 5-FU treatment was significantly more pronounced in the Tdg-expressing cell line (1.7-fold vs. 1.2-fold) (Figure 5B). Thus, TDG contributes to cell-cycle responses following 5-FU treatment.

5-FU–induced cell-cycle arrest in early S-phase was shown previously to depend on Chk1, an effector protein kinase [38,39] that gets activated in response to DNA damage or replication stress through ATR-dependent serine (S317 and S345) phosphorylation (Chk1-p) [40]. We examined the role of TDG in checkpoint activation following treatment of cells with 10 μM 5-FU for 24 h and a recovery in drug-free medium for another 24 h. Immunoblotting of whole-cell extracts with a S345 phospho-specific Chk1 antibody confirmed significant activation of the kinase in Tdg wild-type cells (Figure 6A). In extracts of 5-FU–treated Tdg knockout cells, however, 5-FU–induced Chk1 phosphorylation was hardly detectable. This was not due to an absence of Chk1 or an inability to phosphorylate the kinase in these cells; immunodetection of total Chk1 protein confirmed similar levels in wild-type and knockout extracts (Figure 6A), and the replication inhibitor HU induced Chk1 phosphorylation in both cell types (Figure 6C). Note that the reduced TDG protein levels detected in the extracts of 5-FU treated wild-type MEFs (Figure 6A) reflect the accumulation of the cells in S-phase, where TDG is not expressed [33]. Finally, stable transfection of a TDG-expressing plasmid restored 5-FU–inducible Chk1 phosphorylation in the Tdg knockout cells (Figure 6B).

To address the dynamics of Chk1 activation, we monitored S345 phosphorylation during a 24-h treatment with 10 μM 5-FU and an additional recovery time of 24 h in the absence of 5-FU. Weak Chk1 phosphorylation became detectable after 16 h of treatment both in Tdg wild-type and knockout MEFs. This initial signal persisted throughout a treatment period of 24 h (Figure 6C), but declined gradually during the subsequent recovery period. Strikingly, however, in TDG-proficient cells, Chk1 phosphorylation reappeared at 40 h into the time course, which is 16 h after removal of the drug (Figure 6C). Thus, 5-FU elicits an early checkpoint response that is independent of TDG and a late response that depends on TDG.

Another readout of ATM- or ATR-dependent DNA-damage responses is the formation of nuclear foci containing a phosphorylated variant of histone H2AX [41]. γH2AX is considered a marker of DNA damage, including DNA double-strand breaks that may occur during DNA replication when moving forks encounter damage in the parental strands. We thus measured changes in the steady-state levels of γH2AX foci in TDG-proficient and -deficient MEF populations upon treatment with 5 μM 5-FU for 24 h and additional recovery for 24 h in drug-free medium. Although both mock-treated cell lines showed similar levels of γH2AX foci, the wild-type MEFs accumulated significantly higher numbers of γH2AX foci than the TDG-deficient cells during 5-FU treatment (Figure 6D). This corroborates that 5-FU treatment induces DNA strand breaks and, consequently, DNA-damage signaling in a TDG-dependent manner.

Chemicals and reagents were purchased from Sigma, Complete protease inhibitor from Roche, RNase from Qiagen and UGI from New England Biolabs. LIF was from Chemicon-Millipore, sodium pyruvate from Invitrogen, and all other supplements or cell culture media from Sigma. The polyclonal rabbit anti-mTDG antiserum was newly generated by immunization with recombinant full-length mouse TDGa (Primm Labs). Rabbit anti-Chk1 (#2345) and rabbit anti-Chk1-Ser345p (#2341) antibodies were from Cell Signaling, the mouse anti–β-actin (ab8226) antibody was from Abcam, the rabbit anti-XRCC1 (X0629) was from Sigma, and the mouse anti-γH2AX (#05–636) was from Chemicon-Millipore. The monoclonal rat anti-hsTDG antibody was described in [44]. The secondary horseradish peroxidase–conjugated antibodies against mouse (NXA931) or rabbit (NA934V) were purchased from GE Healthcare Life Sciences, the secondary Cy2-conjugated donkey anti-mouse IgG (715-225-151) and anti-rabbit IgG (711-225-152) antibodies, and donkey serum (017-000-001) were from Jackson ImmunoResearch Laboratories, and the horseradish peroxidase–conjugated antibody against rat (A5795) was from Sigma. ON-TARGETplus SMARTpool siRNA against human Tdg (L-003780–01), ON-TARGETplus Non-targeting Pool control siRNA (D-001810–10) and DharmaFECT siRNA transfection reagent (T-2001) were from Thermo Scientific Dharmacon.

For bacterial expression of an N-terminally 6xHis-tagged mouse TDG, the murine TdgA cDNA (GenBank accession number: NM_172552) was cloned into pET28c (Novagen-Merck). Mammalian expression constructs were obtained by PCR cloning of the mouse TdgA sequence into pSG5-HH25 [44] or pTCO4 (D. Schuermann, unpublished data) for expression controlled by the SV40 or the authentic Tdg promoter, respectively. Constructs expressing human Tdg from a CMV promoter were obtained by PCR cloning of the Tdg cDNA (GenBank: NM_003211) into pCEP4 (Invitrogen). In vitro mutagenesis of mouse Tdg was performed using the QuikChange site-directed mutagenesis kit (Stratagene). PCR primer sequences and vector maps are available on request.

For spontaneous immortalization, primary cells from Tdg^−/− embryos (ED 9.5) were expanded in growth medium (DMEM, 10% FCS, 2 mM L-glutamine). Cultures were kept at <90% confluency at all times. Spontaneously immortalized cell lines were obtained through prolonged cultivation in medium containing 20% FCS and stored in growth medium containing 10% DMSO at 5 × 10⁶ cells/ml in liquid nitrogen. Alternatively, primary cells were immortalized by transfection with a plasmid expressing SV40 large T-antigen. Immortal MEFs were cultivated in growth medium containing penicillin/streptomycin (pen/strep) at 37 °C with 5% CO₂. For complementation, Tdg^−/− cell lines were transfected at 70% confluency with 1 μg of plasmid DNA and the Transfectin reagent (BioRad). Puromycin-resistant cells were selected and further maintained in medium supplemented with 1.5 μg/ml puromycin. For protein extraction, Comet assays or FACS analysis, 1 × 10⁶ (mock) or 2 × 10⁶ (5-FU) cells were seeded into 10-cm culture dishes and incubated for 24 h. Cells were treated with indicated 5-FU concentrations for 24 h and washed with PBS. After additional incubation for 24 h in drug-free medium, cells were harvested by trypsinization. Mouse ES cells with a homozygous disruption of the Tdg gene were selected with increasing concentrations of neomycin from ES cells heterozygous for Tdg. ES cells were passaged in ES medium (DMEM, 15% heat-inactivated FCS, 2 mM L-glutamine, 0.1 mM β-mercaptoethanol, 1 mM sodium pyruvate, 1× nonessential amino acids, 1× pen/strep, 1,000 U/ml LIF) in the presence of γ-ray–inactivated feeder cells, which were removed prior to sensitivity assays. HeLa cells were maintained in growth medium containing penicillin/streptomycin (pen/strep) at 37 °C with 5% CO₂.

Cells were washed with ice-cold PBS and lysed for 30 min on ice in lysis buffer (50 mM Na-phosphate [pH 8.0], 125 mM NaCl, 1% NP-40, 0.5 mM EDTA, 1 mM PMSF, 1 mM DTT, 1× Complete protease inhibitors, 2× phosphatase inhibitor cocktail 1 and 2). Extracts were clarified by centrifugation (15 min, 20,000g, 4 °C). Protein concentrations were determined using the Bradford reagent (BioRad). A total of 50 μg of soluble protein was separated in 10% SDS-polyacrylamide gels and transferred to a nitrocellulose membrane (Millipore). Membranes were washed once with TBS-T (100 mM Tris/HCl [pH 8.0], 150 mM NaCl, 0.1% Tween20) and incubated with blocking buffer (TBS-T, 5% dry milk) for 1 h at room temperature (RT). Blocked membranes were washed once with TBS-T for 5 min before incubation with the primary antibody for 1 h at 33 °C (anti-mTDG) or RT (anti–β-actin) in blocking buffer or overnight at 4 °C in TBS-T containing 5% BSA (anti-Chk1 and anti-Chk1-Ser345p). Dilutions were: 1:10,000 for the rabbit anti-mTDG antibody and the mouse anti-β-actin, 1:1,000 for the rabbit anti-Chk1 and the rabbit anti-Chk1-Ser345p. The washing steps after hybridization were: once at 33 °C and twice at RT for 15 min (anti-mTDG), three times at RT for 10 min (anti-β-actin), and three times for 5 min at RT (anti-Chk1 and anti-Chk1-Ser345p). Both secondary horseradish peroxidase–conjugated antibodies were diluted 1:5,000 in blocking buffer and hybridized to the membranes for 1 h at RT. After three washing steps of 10 min at RT, detection of the signals was carried out using the Immobilon Western Chemiluminescent HRP Substrate (Millipore).

Cell viability of MEFs and ES cells was measured by the Cell Counting Kit-8 (Dojindo). Triplicate cultures of each cell line were plated in 96-well plates at 1 × 10³ cells per well and pre-incubated in the respective growth medium. 5-FU or MMS was added to final concentrations as indicated. Cells were exposed for 48 h to 5-FU (MMS: 1 h, and an additional 47 h in normal growth medium), and then washed with PBS before incubation in medium containing the WST-8 substrate at 37 °C. After incubation for 2 h (MEF) or 4 h (ES), the cell density was measured indirectly by quantification of the solubilized formazan product at 450 nm with a SpectraMax340 microplate spectrophotometer (Molecular Devices). For real-time analysis of cell growth during 5-FU treatment, MEF cells were seeded in 12-well plates at approximately 5% confluence. Following a preincubation of 24 h, the growth medium was exchanged with medium containing 5-FU concentrations as indicated. Cell proliferation was recorded with an automated IncuCyte microscope (Essen Instruments) by monitoring nine regions per well every hour. The assessment of cell proliferation was based on confluence as calculated by the integrated IncuCyte software. For measurement of clonogenic cell survival, HeLa cells were plated at 3 × 10⁵/well in six-well plates. After 24 h, cells were transfected with 100 nM siRNA (Tdg-directed or control) using DharmaFECT 1 according to the manufacturer's instructions. Twenty-four hours after transfection, cells were trypsinized, counted, and then plated in duplicate in 10-cm dishes at cell densities between 200 and 800 cells/dish in growth medium containing 5-FU concentrations as indicated. Remaining cells were further cultivated in normal growth medium for Western blot analysis of TDG protein after 72 h. Seventy-two hours after plating, the medium of 5-FU and mock-treated cells was exchanged with 5-FU–free growth medium, and plates were incubated for additional 14 d. Colonies were visualized by staining with a 10% Giemsa solution after washing with PBS and fixation with 50% methanol.

For expression of mTDGa, 2 l of Superbroth containing 50 μg/ml kanamycin were inoculated with an overnight culture of Escherichia coli BL21(DE3) transformed with pET-28c-mTdgA. The culture was grown to an A₆₀₀ (absorbance at 600 nm) of 0.6 and cooled to 15 °C. TDG expression was induced by the addition of 200 μM IPTG and incubation was allowed to proceed at 15 °C for 23 h. Cells were collected by centrifugation (Sorvall SLC-6000, 5,000 rpm, 4 °C, 30 min), and the pellets were resuspended in 3 ml/g sonication buffer (50 mM Na-phosphate [pH 8.0], 750 mM NaCl, 20% glycerol, 1 mM imidazole, 10 mM β-mercaptoethanol, 1 mM phenylmethylsulfonyl fluoride). After shock freezing in liquid nitrogen, cells were stored at −80 °C. Crude extracts were prepared by sonication (12 times for 30 s on ice with intermittent chilling), and clarified by centrifugation (Sorvall SS34, 18,000 rpm, 4° C). All steps were performed at 4 °C. The supernatant was applied to a disposable column packed with 1.5 ml of pre-equilibrated Ni-NTA agarose (Qiagen) at a flow rate of 15 ml/h. After washing with 120 ml of buffer, bound proteins were eluted with 10 ml of sonication buffer containing 500 mM imidazole and dialyzed against buffer H50 (50 mM Na-phosphate [pH 8.0], 50 mM NaCl, 20% glycerol, 10 mM β-mercaptoethanol, 1 mM phenylmethylsulfonyl fluoride). After loading the dialyzed fraction onto a 5-ml HiTrap Heparin HP column (GE Healthcare) at a flow rate of 1 ml/min and washing with 10 ml of H50, bound protein was eluted with a liner gradient of 50–800 mM NaCl in 50 ml. Purest fractions were pooled, dialyzed against buffer Q20 (50 mM Na-phosphate [pH 8.5], 20 mM NaCl, 10% glycerol, 10 mM β-mercaptoethanol, 1 mM phenylmethylsulfonyl fluoride), and loaded on a 1-ml HiTrap Q HP at a flow rate of 1 ml/min. After washing with 10 ml of Q20 buffer, bound proteins were eluted with a linear gradient of 20–500 mM NaCl in 15 ml. The fractions containing TDG with >98% homogeneity were pooled, dialyzed against storage buffer (50 mM Na-phosphate [pH 8.0], 50 mM NaCl, 10% glycerol, 10 mM β-mercaptoethanol, 1 mM phenylmethylsulfonyl fluoride), frozen in liquid nitrogen and stored at −80 °C.

Nuclear protein extracts were prepared according to [33]. For base release assays, 20 μg of nuclear proteins were incubated with 1 pmol of a fluorescein-labeled homoduplex or mismatched DNA substrate (2) in reaction buffer (50 mM Tris-HCl [pH 8.0], 1 mM EDTA, 1 mM DTT, 1 mg/ml BSA, 2 U UGI) for 20 h at 37 °C. Generated AP-sites were cleaved by the addition of NaOH to a final concentration of 100 mM and heating to 95 °C for 10 min. Subsequently, DNA was ethanol precipitated overnight at −20 °C in 0.3 M Na-acetate (pH 5.2) and in the presence of 0.4 mg/ml carrier tRNA. The DNA was collected by centrifugation (20 min, 20,000g, 4 °C) and washed in 80% ethanol. Air-dried pellets were resuspended in loading buffer (1× TBE, 90% formamide), heated at 95 °C for 5 min, and then immediately chilled on ice. Reaction products were separated on 15% denaturing polyacrylamide gels in 1× TBE. The fluorescein-labeled DNA was visualized with a Typhoon 9400 (GE Healthcare) and quantified using the ImageQuant TL software (GE Healthcare). Levels of genomic uracil and 5-FU were determined as described in [9] after treatment of cells with 10 μM 5-FU for 24 h.

Comet assays were performed according to [50] with minor modifications described by [51]. After treatment, cells were trypsinized, collected by centrifugation (5 min, 450g, RT), and then washed with PBS. Ten thousand cells were resuspended in 100 μl of low-melting-point agarose (PBS, 0.5% LMPA; Lonza) at 37 °C, and casted onto microscope slides precoated with 1.5% normal melting agarose (BioRad). After gelling, cells were lysed by immersion of the slides in freshly prepared ice-cold lysis buffer (2.5 M NaCl, 100 mM EDTA, 10 mM Tris/HCl [pH 10], 1% TritonX-100, 10% DMSO) for 90 min at 4 °C. Slides were then washed with ddH₂O and covered with fresh electrophoresis buffer in an electrophoresis tank (1 mM EDTA, 300 mM NaOH [pH >13]). After DNA denaturation for 30 min at 4 °C, electrophoresis was performed at 25 V and 300 mA for 20 min. All the above steps were done under dimmed light. Neutralization was carried out by three washings of 10 min with 0.4 M Tris/HCl (pH 7.5) at RT. After two fixation steps of 5 min in 100% EtOH at RT, slides were air-dried and stained with 50 μl PI solution (Vectashield, 2.5 μg/ml propidium iodide). Comet tail moments of 100 to 150 cells per slide were analyzed by automated analysis [52] using a Leitz MIAS image analyzer (Leitz Messtechnik) together with a Leica DM RBE microscope (Leica Microsystems).

A total of 5 × 10⁵ to 5 × 10⁶ cells were fixed overnight in 5 ml of 70% ethanol at 4 °C, collected by centrifugation (5 min, 800g, 4 °C) and resuspended in 0.3 ml of RNase solution (100 mM Tris/HCl [pH 7.5], 100 mM NaCl, RNase 0.5 mg/ml). RNA digestion was performed at 37 °C for 45 min; 0.3 ml of PE solution (0.4% HCl, pepsin 1 mg/ml) was added to the samples during the last 15 min of incubation. The DNA was stained by the addition of 0.6 ml PI solution (PBS, 50 μg/ml propidium iodide) on ice for 30 min. Samples were analyzed by flow cytometry with a FACS Canto ll cytometer (Beckton Dickinson). Cell-cycle distribution was analyzed using the FlowJo software (TreeStar).

MEFs were cultivated on coverslips for 24 h. Cells were then treated with 5 μM 5-FU for 24 h followed by cultivation in drug-free medium for another 24 h. Coverslips were then washed twice in PBS and the cells fixed for 15 min with PF-buffer (PBS, 2% paraformaldehyde) at RT, washed 4× 10 min in PBS at RT, and permeabilized in ice-cold P-buffer (PBS, 0.2% TritonX100) for 5 min. Coverslips were incubated for another 5 min in ice-cold P-buffer containing 0.2% NaBH₄. After blocking twice in H-buffer for 10 min (PBS, 1% BSA) and once in D-buffer for 10 min (PBS, 1:20 donkey serum), samples were hybridized with the anti-XRCC1 (1:100 dilution in H-buffer) or the anti-γH2AX (1:500 dilution in H-buffer) antibody for 1 h at RT. Following four washes of 10 min in H-buffer, the samples were hybridized with the respective Cy2-conjugated secondary antibody at a dilution of 1:500 (XRCC1) or 1:200 (γH2AX) in H-buffer for 1 h at RT. After four washes of 10 min in PBS, the coverslips were dried and embedded in Mowiol (Calbiochem, Germany). XRCC1 or γH2AX signals were visualized on an Axiovert 200M microscope (Zeiss) using a FITC filter (excitation 492 nm, emission 520 nm).

Statistical analyses were done using the Prism 5 software (GraphPad Software). Comet tail moment data were analyzed according to P. Duez et al., 2003 [53] by two-way ANOVA of medians and 75% percentiles obtained from three independent experiments, followed by the Bonferroni post test. XRCC1 and γH2AX foci distributions were tested for normality by the Shapiro-Wilk test and further evaluated by one-way ANOVA using the nonparametric Kruskal-Wallis test followed by the Dunn multiple comparison analysis comparing treated with untreated samples. Analysis of cell-cycle data was done by the Fisher exact test from contingency tables comparing the distributions of G1-, S-, and G2-phase cells.