Mutant p53 prolongs NF-κB activation and promotes chronic inflammation and inflammation-associated colorectal cancer

Abstract

The tumor suppressor p53 is frequently mutated in human cancer. Common mutant p53 (mutp53) isoforms can actively promote cancer through gain-of-function (GOF) mechanisms. We report that mutp53 prolongs TNF-α-induced NF-κB activation in cultured cells and intestinal organoid cultures. Remarkably, when exposed to dextran sulfate sodium, mice harboring a germline p53 mutation develop severe chronic inflammation and persistent tissue damage, and are highly prone to inflammation-associated colon cancer. This mutp53 GOF is manifested by rapid onset of flat dysplastic lesions that progress to invasive carcinoma with mutp53 accumulation and augmented NF-κB activation, faithfully recapitulating features frequently observed in human colitis-associated colorectal cancer (CAC). These findings might explain the early appearance of p53 mutations in human CAC.

Figure 1. Mutp53 prolongs TNFα–induced NF-κB activation

A. PANC-1 cells were transfected with siRNA oligonucleotides specific for p53 (sip53) or lacZ as control (siCon). 48 hr later TNF-α was added at the indicated final concentration for an additional 24 hr. RNA was extracted and subjected to qRT-PCR analysis with primers specific for IL-8 mRNA. Values were normalized for GAPDH mRNA in the same sample. B. SW480, HT29, HCT116 (+/+), and HCT116 derivatives without p53 (−/−) or with a knock-in 53 R248W (mut) were transfected as in (A) and exposed to 0.5 ng/ml TNF-α for 24 hr. IL-8 mRNA was quantified as in (A). C. PANC-1 cells were transfected as in (A) and exposed to 0.5 ng/ml TNF-α for the indicated periods. RNA was extracted and subjected to qRT-PCR analysis with primers specific for IL-8 mRNA. Values were normalized as in (A). D. The same RNA samples as in (B) were subjected to qRT-PCR analysis with primers derived from the first intron of the IL-8 gene. Values were normalized as in (A). E. PANC-1 cells were transfected with siRNA oligonucleotides specific for p53 (p) or scrambled oligonucleotides as control (C), treated with 0.5 ng/ml TNF-α for the indicated time periods and harvested. Chromatin-bound proteins (see Experimental Procedures) were subjected to Western blot analysis with the indicated antibodies. GAPDH and H2B served to assess the absence of cytoplasmic contamination and the presence of chromatin, respectively. F. PANC1 cells were treated with TNF-α (0.5 ng/ml) for 0, 0.5 or 8 hr and subjected to chromatin immunoprecipitation (ChIP) with p65 and p53 antibodies, followed by qPCR analysis with primers flanking the NF-κB site of the IL-8 promoter or the upstream p53-responsive element (RE) of the p21 gene (negative control). Values are presented as percentage of input. In the entire figure, error bars represent +/− standard deviations (SD). See also Figure S1.

Figure 2. Mice expressing mutp53 are excessively susceptible to DSS

A. Organoids comprised of intestinal epithelial cells of p53 +/+, −/− and m/m mice were cultured as in Experimental Procedures- left: representative photomicrograph of both low magnification (bar = 500 µm) and higher magnification (bar = 200 µm), then treated with TNF-α (0.5ng/ml) for 24 hr. p53, TNF-α and KC mRNA levels were quantified as in Fig. 1A. Bars represent ± SD. B. p53+/− and +/m mice were treated with 2% DSS at the indicated time windows or left untreated (Con). Body weight was monitored throughout the indicated period. Values represent average relative weight normalized to the weight at the start of the treatment; bars indicate standard errors. **=p-value< 0.01. C. p53+/− and +/m mice were treated as in (B). Mice were sacrificed at day 50 and colon lengths were measured. Distribution of individual measurements along with mean and standard deviation are shown. **=p-value< 0.01. D. Colons of p53+/− and +/m mice, either untreated (Con) or treated with DSS, were collected at day 60 and subjected to histopathological analysis (bars = 100 µm). See also figure S2.

Figure 3. Mice expressing mutp53 are prone to chronic inflammation

A. Representative colonoscopy images of p53+/− and +/m mice subjected to chronic DSS treatment (DSS) or left untreated (Con) at day 50. B,C. p53+/− and +/m mice, treated as in (A), were subjected to colonoscopy at the indicated time points and scored blindly. An average inflammatory score was calculated (n = 5 mice/group). *=p-value< 0.05; **=p-value< 0.01 D. Histopathological analysis of mouse colon sections at day 107. Low (bars = 200 µm) and high (bars = 50 µm) magnifications are shown for each specimen; dashed rectangle indicates the enlarged area. Asterisks indicate lymphocytic aggregations; arrows depict neutrophils. Note the existence of an area with microerosion in the +/m DSS case. E. Colons were obtained from DSS-treated mice at the indicated time points, and levels of secreted TNF-α were assessed as described in Experimental Procedures. Distributions of individual mice together with mean plus standard deviation for each group are shown. NT = non-treated. **=p-value< 0.01. F. Epithelial cell enriched (ECE) fractions were obtained from DSS-treated mice at day 60. RNA was extracted and subjected to qRT-PCR with primers specific to the indicated genes. Values were normalized to GAPDH mRNA in the same sample. **=p-value< 0.01. *=p-value< 0.05. In the entire figure, error bars represent +/− SD. See also figure S3.

Figure 4. Gain-of-function effect of mutp53

A. Mice of the indicated genotypes were treated and analyzed as in Fig. 2B. Only DSS-treated mice are shown. Error bars represent +/− standard error (SE). B. p53−/− and m/m mice were treated with DSS as in Fig. 2B. and monitored periodically by colonoscopy. Inflammatory scores were determined as in Fig. 3B. **=p-value< 0.01. Error bars represent +/− SD. C. Kaplan-Mayer plot showing survival of DSS treated p53−/− and m/m mice.**=p-value< 0.01 by Mantel-Cox test.

Figure 5. Mutp53 mice are prone to DSS-induced colon carcinoma

A. p53+/− and +/m mice were treated with DSS as in Fig. 2B. Mice were sacrificed at the indicated time points and colon sections were subjected to histopathological analysis. Each bar depicts the percentage of mice within a given group scoring positive for the indicated lesions. Numbers of animals/group are noted at the bottom (n=). NL= no lesion; Dys. = dysplasia (low or high grade); ICa = invasive carcinoma. B. Representative histopathological images of colon sections obtained from non-treated mice (NT) of the indicated genotypes or mice subjected to chronic DSS treatment and sacrificed at the indicated time points. Note the presence of low grade flat dysplasia in p53+/m cases at 90 days and the development of well-differentiated carcinoma and mucinous adenocarcinoma at days 100 and 107, respectively. Cancerous glands (white arrowheads) invade the muscularis mucosae, identified by smooth muscle actin (SMA) staining (insets). Star denotes pool of extracellular mucin. Bar sizes: upper panel = 50µm, middle panel = 200 µm, lower panel = 600 µm. C. Low magnification images of colon sections from DSS-treated mice of the indicated genotypes, obtained at day 120. Note the progressive multifocal invasive carcinoma with prominent mucin lakes in the p53+/m mouse. Bars = 500 µm. See also Figure S4.

Figure 6. Analysis of p53, p65, iNOS and γH2AX in DSS-exposed mice

A. Colons of p53+/− and +/m mice were harvested either without treatment (Con), immediately after acute DSS treatment (Ac), or at day 60 of the chronic DSS protocol (Ch), and subjected to ChIP analysis with antibodies against mouse p65 (left) or mouse p53 (right). Extracted DNA was subjected to qPCR with primers flanking the NF-κB site of the MIP2 gene promoter. Primers corresponding to a region located far from any coding gene (GALc) served as negative control. ChIP values are presented as percentage of input. B. Colon sections were prepared at day 7 from mice of the indicated genotypes subjected to acute DSS treatment, as well as from non-treated mice (NT), and stained for p53 (bars = 100 µm). Insets display a higher magnification (bars in upper insets are 50 µm and bars in lower insets are 25 µm). C. Colon sections prepared as in (B) were stained with antibodies against iNOS; sections from two +/m mice are included to show the mouse-to-mouse variability in this genotype. Bars are 50 µm. D. Staining for p53, p65 and γH2AX in invading gland within the colon of a p53+/m mouse, collected at day 105 of the chronic DSS protocol. Bars are 50 µm. In the entire figure, error bars represent +/− SD. See also figure S5.

Figure 7. Mutp53-p65 correlation in human CAC and IBD

A. Concurrent strong immunostaining of p53 and nuclear p65 in consecutive serial sections of a representative human CAC case carrying a p53R273H mutation (case 36102, Figure S6A). B. Staining abundance and intensity (%LI) were calculated for all 18 specimens as described in Figure S6A. The scatter plot depicts the p65 and p53 %LI values for each individual tumor. Pearson correlation coefficient for all groups together = 0.85. C. Immunostaining for p53, p65 and p21 in the epithelium, within an area of severe acute inflammation, in a human case of severe active colitis. Upper panel displays a low magnification field; two glands (a and b) are indicated by dashed rectangles. Higher magnifications of gland a (middle panel) and gland b (lower panel) are shown below. Arrows indicate cells with intense nuclear staining. Scale bars = 50µm. See also Figure S6.

Figure 8. Analysis of mice subjected to DSS+AOM

A. Scheme of treatment schedule with DSS+AOM. p53+/− and +/m mice were subjected to treatment with DSS+AOM. B. Weight index was monitored and calculated as in Fig. 2B. **=p-value< 0.01. Error bars represent +/− SE. C. p53+/− and +/m mice treated with DSS+AOM were periodically monitored by colonoscopy. Each bar depicts the percentage of mice within a given group bearing adenomatous polyps (AP) or no lesion (NL); number of animals/group indicated at the bottom. D. Representative colonoscopy images of polyps in p53+/− and +/m mice at day 105 of exposure to the DSS+AOM protocol. See also Figure S7.