The telomeric protein TRF2 binds the ATM kinase and can inhibit the ATM-dependent DNA damage response

Abstract

The telomeric protein TRF2 is required to prevent mammalian telomeres from activating DNA damage checkpoints. Here we show that overexpression of TRF2 affects the response of the ATM kinase to DNA damage. Overexpression of TRF2 abrogated the cell cycle arrest after ionizing radiation and diminished several other readouts of the DNA damage response, including phosphorylation of Nbs1, induction of p53, and upregulation of p53 targets. TRF2 inhibited autophosphorylation of ATM on S1981, an early step in the activation of this kinase. A region of ATM containing S1981 was found to directly interact with TRF2 in vitro, and ATM immunoprecipitates contained TRF2. We propose that TRF2 has the ability to inhibit ATM activation at telomeres. Because TRF2 is abundant at chromosome ends but not elsewhere in the nucleus, this mechanism of checkpoint control could specifically block a DNA damage response at telomeres without affecting the surveillance of chromosome internal damage.

Figure 1. TRF2 Inhibits the IR-Induced Cell Cycle Arrest

(A) Retrovirally infected IMR90 cells were treated with 4 Gy IR (left and right) or treated with 4 Gy IR and exposed to caffeine (10 mM) directly after irradiation (middle). After 16 h, during which the cells were incubated in 1 μg/ml colcemide, the DNA was stained with DAPI and mitotic cells were identified by immunofluorescence with an antibody to phosphorylated histone H3. (B) Quantification of bypass of IR-induced cell cycle arrest. The mean percentage of phosphorylated histone H3-positive cells and SDs from three experiments are given. The low maximal incidence of phosphorylated H3-positive nuclei (approximately 18%) is due to loss of mitotic cells during processing; loss of mitotic cells occurred at the same level in control and experimental samples.

Figure 2. Effect of TRF2 on Downstream Readouts of the IR-Induced ATM Response

(A) Retrovirally infected IMR90 cells were exposed to 5 Gy IR and harvested after 0, 12, 24, and 36 h. Levels of p53, Bax, p21, Hdm2, p16, pRB, and γ-tubulin (loading control) were detected by immunoblotting of equal cell number equivalents. (B) Amount of p53 protein at the indicated timepoints (hours) was determined by densitometry of p53 immunoblots such as shown in (A). Amounts were normalized to the vector control at 0 h. Mean values from three experiments and standard deviations are shown. (C) Retrovirally infected IMR90 cells were exposed to 20 Gy IR and harvested after 45 min. Nbs1 was immunoprecipitated and subsequently detected by immunoblotting using a general Nbs1 antibody and a phosphospecific Nbs1 S343 antibody. IPs were treated with λ-phosphatase where indicated.

Figure 3. Effect of TRF2 on IR-Induced ATM Phosphorylation

(A) Overexpression of TRF2 inhibits IR-induced phosphorylation of transfected ATM in 293T cells. 293T cells co-transfected with ATM and either TRF2, TRF1, or vector were treated with the indicated doses of IR. After a 30-min recovery, cells were harvested and immunoblot analysis was performed on whole-cell lysates. (B) Overexpression of TRF2 inhibits IR-induced phosphorylation of endogenous ATM in primary fibroblasts. IMR90 primary fibroblasts infected with a retroviral construct expressing TRF2 or an empty virus were treated with the indicated doses of IR. After a 1 h recovery, cells were harvested and ATM was immunoprecipitated from whole-cell lysates. Immunoblot analysis was performed on immunoprecipitated ATM.

Figure 4. TRF2 Interacts with the ATM Kinase In Vivo and In Vitro and TRF2 Does Not Localize to IRIF

(A) Co-IP of TRF2 with ATM. Protein extracts from IMR90 cells and A-T cells (AG02496) infected with an empty virus or a TRF2-overexpressing virus were incubated with anti-ATM or anti-Cyclin D1 antibodies as indicated, and TRF2 was detected in the IP pellets by immunoblotting. The right panel represents IPs with anti-ATM antibodies from IMR90 cells infected with a retrovirus overexpressing Nova1 or the empty vector and detection of Nova1 by immunoblotting. For each extract 1% of the IP input (input) was processed for immunoblotting in parallel. (B) Bacterially expressed ATM–GST fusion proteins were purified on glutathione agarose beads and visualized by Western blotting with anti-GST antibody (Upstate Biotechnology [Lake Placid, New York, United States] #06–332) (top). Unfused GST was run on a separate gel because of its low molecular weight. Equal amounts of fusion proteins and GST alone were incubated with purified baculoviral TRF2 (middle) or TRF1 (bottom), bound to glutathione beads, spun down, washed, and bound proteins were processed for immunoblotting with an anti-TRF1 or anti-TRF2 serum. (C) TRF2 does not localize to IRIFS. IMR90 primary fibroblasts infected with a retroviral construct expressing TRF2 or an empty virus were treated with 5 Gy IR. After a 90 min recovery, cells were fixed and processed for immunofluorescence with or without Triton X-100 extraction before fixation. Arrowheads denote foci of TRF2 signal previously demonstrated to represent telomeres. When overexpressed, some TRF2 is localized to nucleolus.