p53 cooperates with DNA methylation and a suicidal interferon response to maintain epigenetic silencing of repeats and noncoding RNAs

Abstract

Large parts of mammalian genomes are transcriptionally inactive and enriched with various classes of interspersed and tandem repeats. Here we show that the tumor suppressor protein p53 cooperates with DNA methylation to maintain silencing of a large portion of the mouse genome. Massive transcription of major classes of short, interspersed nuclear elements (SINEs) B1 and B2, both strands of near-centromeric satellite DNAs consisting of tandem repeats, and multiple species of noncoding RNAs was observed in p53-deficient but not in p53 wild-type mouse fibroblasts treated with the DNA demethylating agent 5-aza-2'-deoxycytidine. The abundance of these transcripts exceeded the level of β-actin mRNA by more than 150-fold. Accumulation of these transcripts, which are capable of forming double-stranded RNA (dsRNA), was accompanied by a strong, endogenous, apoptosis-inducing type I IFN response. This phenomenon, which we named "TRAIN" (for "transcription of repeats activates interferon"), was observed in spontaneous tumors in two models of cancer-prone mice, presumably reflecting naturally occurring DNA hypomethylation and p53 inactivation in cancer. These observations suggest that p53 and IFN cooperate to prevent accumulation of cells with activated repeats and provide a plausible explanation for the deregulation of IFN function frequently seen in tumors. Overall, this work reveals roles for p53 and IFN that are key for genetic stability and therefore relevant to both tumorigenesis and the evolution of species.

Fig. 1.

Primary cells deficient in functional p53 are hypersensitive to 5-aza-dC treatment. (A) p53-WT and p53-null MEFs were treated with 0, 5, or 10 µM 5-aza-dC for 120 h. Viable cells were visualized by methylene blue staining. (B) Western blot detection of p53 and β-actin (loading control) proteins in p53-WT MEFs (lanes 1 and 2), p53-null MEFs (lanes 3 and 4), and p53-WT MEFs expressing shRNA against p53 (shp53, lanes 5 and 6) or the p53-inactivating genetic suppressor element-56 (GSE56, lanes 7 and 8) left untreated (−) or treated (+) with 500 nM doxorubicin (Dox) for 16 h. (C) Cytotoxicity of 5-aza-dC in cells described in B. Cells were treated with the indicated concentrations of 5-aza-dC for 5 d. Viability was determined by methylene blue staining and extraction, followed by spectrophotometric quantification. Percent viability is shown relative to control cells treated with 0.1% DMSO. In all relevant figures, error bars show SDs for assays performed in triplicate. (D) Cytotoxicity of 5-aza-dC (5 d in vitro treatment) in primary cells from different tissues of adult p53-WT and p53-null mice was determined as in C. (E) Caspase-3,7 activity (cleavage of the fluorescent substrate AC-Devd-AMC) in p53-WT and p53-null MEFs treated with the indicated concentrations of 5-aza-dC for 48 h or 1 µM doxorubicin (Dox) for 16 h. (F) Western blot analysis of DNMTI and β-actin (loading control) protein levels in p53-WT and p53-null MEFs treated with the indicated concentrations of 5-aza-dC for 48 h. (G) The overall extent of genomic DNA methylation in p53-WT and p53-null MEFs left untreated (U) or treated (T) with 10 µM 5-aza-dC for 48 h was determined by digestion of DNA with the methylation-sensitive restriction enzyme McrBC, which cuts only its sites that are methylated.

Fig. 2.

Illumina microarray-based analysis of gene expression in p53-WT and p53-null MEFs left untreated or treated with 10 µM 5-aza-dC for 48 h. (A) (Center) Venn diagram showing no overlap between the 55 and 124 genes up-regulated (≥fivefold) by 5-aza-dC in p53-WT (Left) and p53-null (Right) cells. Bar graphs show mRNA expression levels (signal intensity on Illumina microarray) of genes identified as 5-aza-dC–induced in p53-WT MEFs (Left) or in p53-null MEFs (Right) in all four samples (p53-WT and p53-null MEFs left untreated or treated with 5-aza-dC). (B) Fold-induction (log scale; 5-aza-dC–treated relative to untreated) of a subset of genes identified as 5-aza-dC–induced in either p53-WT MEFs or p53-null MEFs. Note the scale of induction of IFN-β1 in p53-null MEFs. (C) Validation of Illumina microarray gene expression analysis was performed by RT-PCR using independently isolated RNA from p53-WT and p53-null MEFs left untreated or treated with 10 µM 5-aza-dC for 48 h and specific primers for mouse IFN-β1, H2-Q6, IRF7, and β-actin (control).

Fig. 3.

Treatment of p53-null MEFs with 5-aza-dC induces a lethal IFN response. (A) Western blot detection of p53 and β-actin (loading control) proteins in MEFs from ifnar^−/− mice expressing endogenous WT p53 (lanes 1 and 2) or shRNA against p53 (shp53, lanes 3 and 4) or the p53-inactivating genetic suppressor element-56 (GSE56, lanes 7 and 8) left untreated (−) or treated (+) with 500 nM doxorubicin (Dox) for 16 h. (B) Cytotoxicity of 5-aza-dC in cells differing in p53 and IFNAR status. Cells were treated with the indicated concentrations of 5-aza-dC for 5 d. Viability was determined by methylene blue staining and extraction, followed by spectrophotometric quantification. Percent viability is shown relative to control cells treated with 0.1% DMSO. (C) Cytotoxicity of 5-aza-dC in MEFs from ifnar^+/+ or ifnar^−/− mice expressing endogenous WT p53 (transduced with a nonspecific control shRNA construct) or shRNA against p53 (shp53). Cells were left untreated or treated with 10 µM 5-aza-dC for 120 h before detection of viable cells by methylene blue staining. (D) Caspase-3,7 activity (cleavage of the fluorescent substrate AC-Devd-AMC) in MEFs from p53-WT, p53-null, and ifnar^−/− mice and MEFs from ifnar^−/− mice expressing shRNA against p53 (shp53). Cells were treated with the indicated concentrations of 5-aza-dC for 48 h before the caspase assay. (E) Western blot analysis of expression of the IFN-inducible protein p49 (and β-actin as a loading control) in SCCVII cells: intact (lane 1); mock transfected (lane 2); transfected with the GFP-expression construct plv-CMV-GFP (250 ng per well of a six-well plate; used here and below for monitoring transfection efficiency) (lane 3); transfected with plv-CMV-GFP as above together with 500 ng of RNA (rRNA-depleted fraction) from 5-aza-dC–treated p53-WT (lane 4) and p53-null MEFs (lane 5) and untreated p53-WT (lane 6) and p53-null MEFs (lane 7). Transfection of plv-CMV-GFP and double-stranded poly(I:C) RNA (1μg, an efficient IFN-inducing agent) was used as a positive control (lane 8).

Fig. 4.

Massive transcriptional up-regulation of repetitive elements in p53-null MEFs treated with 5-aza-dC. The abundance of GSAT (A), B2 (B), B1 (C), and ncRNA (D) transcripts in RNA samples isolated from untreated p53-WT MEFs, 5-aza-dC–treated p53-WT MEFs, untreated p53-null MEFs, and 5-aza-dC–treated MEFs relative to the abundance of β-actin mRNA is shown in bar graphs (calculations are based on the results of total RNA sequencing) and Northern blots. For Northern blots the positions of 18S and 28S rRNAs are indicated by arrowheads, and ethidium bromide staining of the gel before transfer is shown in A as a common control for RNA loading and quality. (E) The overall abundance of RNA transcripts representing GSAT DNA (sat DNA), SINEs B1 and B2, ncRNAs, and IAPs in the p53-null (KO) or p53-WT MEFs, untreated or treated with 5-aza-dC, is shown in β-actin units (y axis). Pie diagrams show the proportion of each of the above-listed classes of RNAs in the pool of new transcripts induced by 5-aza-dC treatment in p53-null MEFs (Upper) and in the pool of transcripts present in untreated p53-null cells versus untreated p53-WTcells (Lower). (F) Hypothetical scheme of formation of dsRNA by annealing of RNA-polymerase III-driven transcripts of B1 or B2 SINEs with B1 and B2 sequences present in antisense orientation in polymerase II-driven mRNAs. Introns within mRNA are spliced out before nuclear export, so it is unlikely that a dsRNA will be formed by the annealing of a polymerase III-transcribed SINE sequence to SINE sequences within mRNA introns for further detection by pattern recognition receptors outside the nucleus, such as PKR.

Fig. 6.

Detection of transcripts of repetitive elements in mouse tumor cell lines and spontaneous tumors. (A) Detection of mouse GSAT sequences in total RNA from mouse tumor cell lines CT-26 (colon tumor), LLC-1 (Lewis lung carcinoma), and SCC-VII (squamous cell carcinoma) left untreated or treated with 10 µM 5-aza-dC for 48 h. Dot blotting was performed with 500 ng total RNA per dot and single-strand hybridization probes GSAT-F and GSAT-R. (B) Detection of IFN-β1, IRF-7, CXCL10, and β-actin (loading control) mRNA by RT-PCR in the cells described in A. (C) Cytotoxicity of 5-aza-dC in LLC-1, CT26, and SCC-VII cells. Cells were treated with the indicated concentrations of 5-aza-dC for 5 d. Viability was determined by methylene blue staining and extraction, followed by spectrophotometric quantification. Percent viability is shown relative to control cells treated with 0.1% DMSO. (D) (Upper Two Panels) GSAT sequences were detected in total RNA from thymic lymphomas of p53-null mice (five tumors, L1–L5, from five different mice assayed in duplicate) and in two normal thymuses (T4 and T5) isolated from p53-null mice using dot blotting as described in A. (Lower Two Panels) RT-PCR analysis of IFN-β1 and β-actin (loading control) mRNA expression. (E) Northern hybridization was used to detect SINE B1 sequences in total RNA from MMTV-her2/neu mammary tumors (eight tumors from eight different mice). 18S and 28S rRNA levels detected by ethidium bromide staining confirmed equivalent RNA quality and loading for all tumors.

Fig. 5.

Structural features of major repetitive sequences that are transcriptionally repressed by p53. (A and B) Comparison of putative p53-binding sites from B1, B2, and GSAT repeats with “activating” and “repressing” p53-binding consensus sequences (32). (C and D) p53 binding to its consensus sequence within a ³²P-labeled oligonucleotide was detected by EMSA (C, lane 1), and the specificity of the observed p53-probe complex was confirmed by supershift with the anti-p53 antibody Ab421 (lane 2). Unlabeled competitor oligonucleotides were added at 10:1, 20:1, and 40:1 molar excess over the labeled probe in lanes 3–5 (oligonucleotide containing the p53-binding consensus sequence, positive control), lanes 6–8 (an 84-bp oligonucleotide containing the first two B1-derived putative p53-binding sequences), and lanes 9–11 (λpL promoter-derived oligonucleotides of similar length, negative control). Bands corresponding to p53-binding complexes were quantified by densitometry and normalized to the free radio-labeled probe. (E) Relative frequency of deviations from consensus at specific nucleotides positions within putative p53-binding sites of B1 elements activated by 5-aza-dC in p53-null MEFs. Mutation rates (calculated as P values) were determined for the indicated sets of nucleotides of the three putative p53-binding sites found in B1 consensus sequence. The directed minimal difference was calculated between P values in the 5-aza-dC–treated p53-KO sample versus the first three samples. Analysis of each key position (highlighted in red) of the p53-binding sites within the SINE B1 revealed that the positive minimal differences (black bars) are indicative of lower mutation rates found in the treated p53-KO samples as compared with any other sample set comprising other nucleotides from p53 recognition element (blue bars; shown for only one of four sets analyzed). (F) Comparison of the mutation rate in the key nucleotide positions with mutation rates in other nucleotides within putative p53-binding sites in all four series was performed by the voting method. For each series, the sum of squares of positive differences is χ² distributed; the sum of squares of the negative differences also is χ² distributed. The first χ² value indicates the overall voting of series’ positions for lower rate of mutation in 5-aza-dC–treated p53-KO. Conversely, the second χ² value is voting for higher overall rate of mutations in the series. The ratio of these two values normalized by the corresponding degrees of freedom (numbers of positive and negative differences) is F-distributed. Results are shown as minus log P values of the F-test in key-position series (red) and four control series (blue). The F-test P values of a lower mutation rate in the 5aza+p53ko sample across five series of positions are listed. *Only one P value (0.004 of the key positions) is statistically significant.

Fig. P1.

A model of three levels of negative control of genomic repeat expression. Expression of interspersed repeats (SINEs) and pericentromeric tandem repeats (gamma-satellite DNA, GSAT) in the genome of normal mouse cells is blocked by p53 and DNA methylation, either of which is sufficient for transcriptional silencing. Combined p53 inactivation and DNA demethylation through experimental means or natural circumstances (as in tumor cells) lead to unsilencing and massive transcription of these repeat elements, followed by triggering of a suicidal type I IFN response. The predicted ability of repeat transcripts to form dsRNA likely mediates the observed IFN induction in cells with unsilenced repeats. Dashed lines indicate hypothetical statements.