DNA methyltransferase 1 knockdown activates a replication stress checkpoint

Abstract

DNA methyltransferase 1 (DNMT1) is an important component of the epigenetic machinery and is responsible for copying DNA methylation patterns during cell division. Coordination of DNA methylation and DNA replication is critical for maintaining epigenetic programming. Knockdown of DNMT1 leads to inhibition of DNA replication, but the mechanism has been unclear. Here we show that depletion of DNMT1 with either antisense or small interfering RNA (siRNA) specific to DNMT1 activates a cascade of genotoxic stress checkpoint proteins, resulting in phosphorylation of checkpoint kinases 1 and 2 (Chk1 and -2), gammaH2AX focus formation, and cell division control protein 25a (CDC25a) degradation, in an ataxia telangiectasia mutated-Rad3-related (ATR)-dependent manner. siRNA knockdown of ATR blocks the response to DNMT1 depletion; DNA synthesis continues in the absence of DNMT1, resulting in global hypomethylation. Similarly, the response to DNMT1 knockdown is significantly attenuated in human mutant ATR fibroblast cells from a Seckel syndrome patient. This response is sensitive to DNMT1 depletion, independent of the catalytic domain of DNMT1, as indicated by abolition of the response with ectopic expression of either DNMT1 or DNMT1 with the catalytic domain deleted. There is no response to short-term treatment with 5-aza-deoxycytidine (5-aza-CdR), which causes demethylation by trapping DNMT1 in 5-aza-CdR-containing DNA but does not cause disappearance of DNMT1 from the nucleus. Our data are consistent with the hypothesis that removal of DNMT1 from replication forks is the trigger for this response.

FIG. 1.

DNMT1 knockdown activates a cellular response utilizing components of the replication stress checkpoint. (a) Representative Western blot analysis of protein levels of DNMT1, CDC25a, β-actin, pChk2, and Chk2 in nuclear extracts prepared from T24 cells treated with 50 nM DNMT1 AS or its mismatch control (Con AS) for 24 h. (b and d) Relative optical density of DNMT1 and CDC25a immunoreactivity. Values are means ± standard error (*, P < 0.05, Student's t test; n = 3). (c) Normalized relative optical density of pChk2 immunoreactivity. Values are means ± standard error (*, P < 0.05, Student's t test; n = 3). (e) Representative Western blot analysis of protein levels of DNMT1 and replication stress checkpoint response proteins CDC25a, β-actin, pChk2, and Chk2 in nuclear extracts prepared from T24 cells treated with either 120 nM siDNMT1 or siCon for 24 h. (f and h) Relative optical density of DNMT1 and CDC25a immunoreactivity Values are means ± standard error (*, P < 0.05, Student's t test; n = 3). (g) Normalized relative optical density of pChk2 immunoreactivity. Values are means ± standard error (*, P < 0.05, Student's t test; n = 3). Protein levels were compared to those of the β-actin loading control, except pChk2, which was compared to Chk2 protein levels. (i) Western blot analysis of protein levels of pChk1 and Chk1 in nuclear extracts from T24 cells treated with 50 nM DNMT1 antisense (DNMT1 AS) or its mismatch control (Con AS) for 24 h. (j) Western blot analysis of protein levels of CDC25b and β-actin in nuclear extracts from T24 cells treated with 120 nM siDNMT1 or siCon for 24 h.

FIG. 2.

Knockdown of DNMT1 protein levels in A549 cells induces pChk2. Shown is Western blot analysis of protein levels of DNMT1, β-actin, Chk1, and Chk2 in nuclear extracts prepared from A549 cells, which were treated with 120 nM DNMT1 AS or Con AS to determine if DNMT1 depletion-dependent replication stress checkpoint induction is cell line specific.

FIG. 3.

DNMT1 depletion induces γH2AX focus formation. (a) T24 cells treated with 50 nM DNMT1 AS or Con AS for 24 h were coimmunostained with the anti-γH2AX antibody, which recognizes phospho-Ser139-H2AX, and DAPI to visualize DNA. (b) T24 cells treated with 120 nM siDNMT1 or siCon for 24 h were coimmunostained with the anti-γH2AX antibody to recognize phospho-H2AX and DAPI to recognize DNA. (c) Quantification of γH2AX immunoreactivity of T24 cells treated with 50 nM DNMT1 AS or Con AS for 24 h and stained with the anti-γH2AX antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, paired t test; n = 3). (d) Quantification of γH2AX immunoreactivity of T24 cells treated with 120 nM siDNMT1 or siCon for 24 h and stained with the anti-γH2AX antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, paired t test; n = 3). (e) Western blot analysis of protein levels of γH2AX and pan-H3 in histone extracts prepared from T24 cells which were treated with 50 nM DNMT1 AS or Con AS for 24 h. (f) Western blot analysis of protein levels of γH2A.X and pan-H3 in histone extracts prepared from T24 cells which were treated with 120 nM siDNMT1 or siCon for 24 h.

FIG.4.

Replication stress induction due to DNMT1 depletion is dependent on ATR. (a) Representative confocal microscopic images of T24 cells treated with 100 nM ATR siRNA (siATR) or siCon for 24 h immunostained with the anti-ATR antibody. (b) Quantification of ATR immunoreactivity of T24 cells treated with 100 nM siATR or siCon for 24 h stained with the anti-ATR antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, Student's t test; n = 3). (c) Representative confocal microscopic images of T24 cells treated with 100 nM siATR or siCon for 24 h followed by treatment with 120 nM siDNMT1 or siCon for 24 h immunostained with the anti-γH2AX antibody to recognize phospho-Ser139-H2AX. (d) Quantification of γH2AX immunoreactivity of T24 cells treated with 100 nM siATR or siCon for 24 h followed by treatment with 120 nM siDNMT1 or siCon for 24 h and stained with the anti-γH2AX antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, paired t test; n = 3). (e) Quantification of incorporated [³H]thymidine in T24 cells treated with 100 nM control siRNA, 100 nM ATR siRNA, 120 nM DNMT1 siRNA, or 100 nM ATR and 120 nM DNMT1 siRNA (*, P < 0.05, paired t test; n = 3). (f) Western blot analysis of protein levels of γH2A.X and pan-H3 in histone extracts prepared from normal human fibroblast cells and Seckel syndrome fibroblasts which were treated with 100 nM siDNMT1 or siCon for 48 h. (g) Representative images of cytosine and methylcytosine of the following treatment groups as determined by nearest-neighbor analysis: control (siCon siCon), siATR, siDNMT1, siDNMT1 and siATR, or 1 μM 5-aza-CdR. (h) Quantification of percentage of unmethylated cytosine content of treatment groups (*, P < 0.05, paired t test; n = 3).

FIG.4.

Replication stress induction due to DNMT1 depletion is dependent on ATR. (a) Representative confocal microscopic images of T24 cells treated with 100 nM ATR siRNA (siATR) or siCon for 24 h immunostained with the anti-ATR antibody. (b) Quantification of ATR immunoreactivity of T24 cells treated with 100 nM siATR or siCon for 24 h stained with the anti-ATR antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, Student's t test; n = 3). (c) Representative confocal microscopic images of T24 cells treated with 100 nM siATR or siCon for 24 h followed by treatment with 120 nM siDNMT1 or siCon for 24 h immunostained with the anti-γH2AX antibody to recognize phospho-Ser139-H2AX. (d) Quantification of γH2AX immunoreactivity of T24 cells treated with 100 nM siATR or siCon for 24 h followed by treatment with 120 nM siDNMT1 or siCon for 24 h and stained with the anti-γH2AX antibody. Values (signal intensity) are means ± standard error (*, P < 0.05, paired t test; n = 3). (e) Quantification of incorporated [³H]thymidine in T24 cells treated with 100 nM control siRNA, 100 nM ATR siRNA, 120 nM DNMT1 siRNA, or 100 nM ATR and 120 nM DNMT1 siRNA (*, P < 0.05, paired t test; n = 3). (f) Western blot analysis of protein levels of γH2A.X and pan-H3 in histone extracts prepared from normal human fibroblast cells and Seckel syndrome fibroblasts which were treated with 100 nM siDNMT1 or siCon for 48 h. (g) Representative images of cytosine and methylcytosine of the following treatment groups as determined by nearest-neighbor analysis: control (siCon siCon), siATR, siDNMT1, siDNMT1 and siATR, or 1 μM 5-aza-CdR. (h) Quantification of percentage of unmethylated cytosine content of treatment groups (*, P < 0.05, paired t test; n = 3).

FIG.5.

Depletion of DNMT1 does not induce genomic hypomethylation, while genomic hypomethylating agents do not induce replication stress. (a) Representative stained T24 cells treated with 120 nM siDNMT1, siCon, or 1 μM 5-aza-CdR immunostained with the anti-5-methylcytosine antibody. (b) Quantification (intensity) of 5-methylcytosine immunoreactivity of T24 cells treated with 120 nM siDNMT1, siCon, or 1 μM 5-azaCdR. Values are means ± standard error (*, P < 0.05, paired t test; n = 3). (c) 5-Aza-CdR treatment depletes free DNMT1 but not chromatin-bound DNMT1 but does not induce replication stress. Results are shown for Western blot analysis of protein levels of nuclear DNMT1, chromatin-bound DNMT1, pChk2, and Chk2 in whole-cell extracts prepared from T24 cells treated with 1 μM 5-aza-CdR or vehicle control (DMSO). (d) Representative T24 cells treated with 1 μM 5-aza-CdR for 24 h or 120 nM siDNMT1 were stained with the anti-DNMT1 antibody and visualized by phase-contrast microscopy. (e) Quantification of DNMT1 immunoreactivity of T24 cells treated with 1 μM 5-aza-CdR for 24 h, 120 nM siDNMT1, or control (*, P < 0.05, paired t test; n = 3). (f) DNMT1 constructs and siRNAs specific for the different UTR regions of DNMT1 used in this study. Human DNMT1 AS and siDNMT1 target the human 5′ UTR but do not have overlapping target sequences. Mouse DNMT1 siRNA (simDNMT1) targets the 3′ UTR present in the endogenous mouse DNMT1. pEF6-DNMT1 WT has an Xpress epitope present in the 5′ UTR and has no 3′ UTR. pEF6-DNMT1 ΔCAT has an Xpress epitope present in the 5′ UTR, a deletion in the catalytic domain, as well as no 3′ UTR. Shown are the results of Western blot analysis of levels of Xpress-tagged proteins in nuclear extracts prepared from NIH 3T3 cells stably transfected with either pEF6-DNMT1 WT or pEF6-DNMT1 ΔCAT. (g) Western blot analysis of protein levels of endogenous mouse DNMT1 (mDNMT1), Xpress, and PCNA in nuclear extracts prepared from NIH 3T3 cells stably transfected with pEF6 empty vector, pEF6-DNMT1 WT, or pEF6-DNMT1 ΔCAT, which were treated with 100 nM simDNMT1 or siCon for 48 h. The anti-mouse DNMT1 antibody recognizes the endogenous DNMT1, but it does not recognize the shorter ectopic DNMT1 polypeptides, under the conditions used in our Western blot analysis. (h) Western blot analysis of protein levels of γH2A.X and pan-H3 in histone extracts prepared from NIH 3T3 cells stably transfected with pEF6 empty vector, pEF6-DNMT1 WT, or pEF6-DNMT1 ΔCAT, which were treated with 100 nM simDNMT1 or siCon for 48 h.

FIG.5.

Depletion of DNMT1 does not induce genomic hypomethylation, while genomic hypomethylating agents do not induce replication stress. (a) Representative stained T24 cells treated with 120 nM siDNMT1, siCon, or 1 μM 5-aza-CdR immunostained with the anti-5-methylcytosine antibody. (b) Quantification (intensity) of 5-methylcytosine immunoreactivity of T24 cells treated with 120 nM siDNMT1, siCon, or 1 μM 5-azaCdR. Values are means ± standard error (*, P < 0.05, paired t test; n = 3). (c) 5-Aza-CdR treatment depletes free DNMT1 but not chromatin-bound DNMT1 but does not induce replication stress. Results are shown for Western blot analysis of protein levels of nuclear DNMT1, chromatin-bound DNMT1, pChk2, and Chk2 in whole-cell extracts prepared from T24 cells treated with 1 μM 5-aza-CdR or vehicle control (DMSO). (d) Representative T24 cells treated with 1 μM 5-aza-CdR for 24 h or 120 nM siDNMT1 were stained with the anti-DNMT1 antibody and visualized by phase-contrast microscopy. (e) Quantification of DNMT1 immunoreactivity of T24 cells treated with 1 μM 5-aza-CdR for 24 h, 120 nM siDNMT1, or control (*, P < 0.05, paired t test; n = 3). (f) DNMT1 constructs and siRNAs specific for the different UTR regions of DNMT1 used in this study. Human DNMT1 AS and siDNMT1 target the human 5′ UTR but do not have overlapping target sequences. Mouse DNMT1 siRNA (simDNMT1) targets the 3′ UTR present in the endogenous mouse DNMT1. pEF6-DNMT1 WT has an Xpress epitope present in the 5′ UTR and has no 3′ UTR. pEF6-DNMT1 ΔCAT has an Xpress epitope present in the 5′ UTR, a deletion in the catalytic domain, as well as no 3′ UTR. Shown are the results of Western blot analysis of levels of Xpress-tagged proteins in nuclear extracts prepared from NIH 3T3 cells stably transfected with either pEF6-DNMT1 WT or pEF6-DNMT1 ΔCAT. (g) Western blot analysis of protein levels of endogenous mouse DNMT1 (mDNMT1), Xpress, and PCNA in nuclear extracts prepared from NIH 3T3 cells stably transfected with pEF6 empty vector, pEF6-DNMT1 WT, or pEF6-DNMT1 ΔCAT, which were treated with 100 nM simDNMT1 or siCon for 48 h. The anti-mouse DNMT1 antibody recognizes the endogenous DNMT1, but it does not recognize the shorter ectopic DNMT1 polypeptides, under the conditions used in our Western blot analysis. (h) Western blot analysis of protein levels of γH2A.X and pan-H3 in histone extracts prepared from NIH 3T3 cells stably transfected with pEF6 empty vector, pEF6-DNMT1 WT, or pEF6-DNMT1 ΔCAT, which were treated with 100 nM simDNMT1 or siCon for 48 h.

FIG. 6.

Model of replication arrest following DNMT1 depletion. DNMT1 is normally present in the replication fork. Depletion of DNMT1 similar to depletion of other fork resident proteins, leads to activation of ATR and the downstream pathway; phosphorylation of γH2AX and Chk1/Chk2, leading to CDC25a phosphorylation and degradation. CDC25a phosphatase activity is required for activation of CDC45 (7); thus, degradation of CDC25a leads to decreased CDC45 loading onto the replication origin (data not shown). This leads to an overall decreased capacity for the replication complex to load onto origins, leading to an arrest in DNA replication as well as a block in progression of S phase.