Oncogenic PIK3CA induces centrosome amplification and tolerance to genome doubling

Abstract

Mutations in PIK3CA are very frequent in cancer and lead to sustained PI3K pathway activation. The impact of acute expression of mutant PIK3CA during early stages of malignancy is unknown. Using a mouse model to activate the Pik3ca ^H1047R hotspot mutation in the heterozygous state from its endogenous locus, we here report that mutant Pik3ca induces centrosome amplification in cultured cells (through a pathway involving AKT, ROCK and CDK2/Cyclin E-nucleophosmin) and in mouse tissues, and increased in vitro cellular tolerance to spontaneous genome doubling. We also present evidence that the majority of PIK3CA ^H1047R mutations in the TCGA breast cancer cohort precede genome doubling. These previously unappreciated roles of PIK3CA mutation show that PI3K signalling can contribute to the generation of irreversible genomic changes in cancer. While this can limit the impact of PI3K-targeted therapies, these findings also open the opportunity for therapeutic approaches aimed at limiting tumour heterogeneity and evolution.

Fig. 1

Gene targeting to create a hypomorph Pik3ca ^H1047R+neo allele. a Targeted Pik3ca allele showing the frt-flanked neo selection cassette, before and after Flp-mediated recombination. Exon sequences are represented by filled black rectangles, intron sequences by a black line. The frt sites are represented as yellow triangles with the pointed end indicating orientation. The positions of the primers used for PCR screening are designated by arrows. b p110α expression levels and phosphorylation of Akt in Pik3ca ^WT and Pik3ca ^H1047R+neo ES cells. c p110α expression and Akt phosphorylation in Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 72 h after addition of 4-OHT or vehicle

Fig. 2

p110α^H1047R expression leads to centrosome amplification in cells and tissues. a Frequency of cells with centrosome amplification (n > 2) in WT and Pik3ca ^H1047R primary E13.5 MEFs (72 h after addition of 4-OHT or vehicle; 200 cells were scored per genotype and per time point; values = mean ± SD) and mouse keratinocytes (isolated from 8-week-old Pik3ca ^WT;Flpe-ER ^T2 or Pik3ca ^H1047R+neo;Flpe-ER ^T2 mice, cultured for 7 days of which the last 48 h were in the presence of 4-OHT or vehicle; 400 cells were scored per genotype and per condition). Statistically significant differences are indicated by *(P < 0.05), as determined by non-parametric Mann–Whitney t test (one-tailed). b Whole-mount of E8.5 embryos stained for pericentrin. Dashed lines contour single-cell nuclei. White arrows point towards individual centrosomes in the WT cells. Mutant embryos show enlarged and amplified number of centrosomes per cell. c Cryosections of skin and colon of 8-week-old Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 mice treated for 5 consecutive days with tamoxifen (80 mg kg⁻¹ by gavage), stained for γ-tubulin (red) and actin (green). White arrows point towards centrosomes. Dashed lines contour single-cell nuclei. White boxes surround areas that are magnified underneath

Fig. 3

p110α^H1047R expression in MEFs leads to centrosome overduplication. a Representative immunofluorescence images showing extra centrosomes in p110α^H1047R MEF cells composed of two centrioles. b Representative immunofluorescence images showing extra centrosomes contributing to the mitotic spindle in p110α^H1047R MEF cells. c Centrosome number during the first cell cycle upon induction of p110α^H1047R expression (top panel; 200 cells per genotype and time point were scored for the centrosome analysis; values = mean ± SD) and parallel analysis of DNA synthesis (assessed by BrdU incorporation; bottom panel: 10,000 cells were acquired from two independent WT and two independent p110α^H1047R MEF lines. Statistically significant differences are indicated by *(P < 0.05), as determined by non-parametric Mann–Whitney t test (one-tailed). MEFs were plated and cultured overnight in serum-containing medium. The next morning, cells were serum-starved in the presence of 4-OHT for 48 h, followed by re-addition of 10% fetal bovine serum and sampling of cells at the indicated time points. d Percentage of binucleated MEFs in cultures treated 2 days with 4-OHT. Binucleation was assessed by IF using DAPI to stain DNA. A total of 200 cells were scored per genotype in 3 Pik3ca ^WT;Flpe-ER ^T2 and 3 Pik3ca ^H1047R+neo;Flpe-ER ^T2 independent MEF lines (values = mean ± SD)

Fig. 4

p110α^H1047R expression leads to centrosome overduplication through RhoA and ROCK pathway activation. a Assessment of RhoA activity in Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 3 days after treatment with 4-OHT. The experiment was performed three times using three independent Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs. A representative experiment is shown. b Cyclin E protein levels in Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 3 days after treatment with 4-OHT. Cell extracts from three independent MEF lines per genotype are shown. c Activation of signalling pathways involved in centrosome duplication by p110α^H1047R expression, and effect of p110α inhibition (by 24 h of treatment with 3 µM A66). Cell extracts from two independent MEF lines per genotype are shown. d Effect of inhibition of CDK2 (by 2 h of treatment with 1 µM NU6140) or Akt (by 2 h of treatment with MK2206) on signalling pathways involved in centrosome duplication. e Impact of inhibition of p110α (by 3 µM A66), Akt (by 1 µM Akti X) or ROCK (by 10 µM Y27632 or 0.5 µM H1152) on p110α^H1047R-induced centrosome amplification in primary MEFs. A total of 100 cells were scored per condition using two independent p110α^H1047R MEF lines; values = mean ± SD. f Impact of inhibition of Akt (by 1 µM Akti X) or ROCK (by 10 µM Y27632) for 15 days on centrosome numbers in p110α^H1047R Nutu cells. Centrosomes were revealed by γ-tubulin staining. In total, 200 cells were scored per cell line and per condition

Fig. 5

Efficient clustering of extra centrosomes and lack of chromosomes segregation errors early upon p110α^H1047R expression. a Quantification of the number of cells with centrosome amplification that either make it through mitosis or experience mitotic slippage or cytokinesis failure. In total, 152 WT cells (50, 48 and 54 cells from 3 independent WT MEFs) and 161 Pik3ca ^H1047R cells (50, 61 and 50 cells from 3 independent Pik3ca ^H1047R MEFs) with centrosome amplification entering mitosis were analysed; values = mean ± SD). b Frequency of segregation errors occurring in anaphase of Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 3 days after treatment with 4-OHT. A total of 103 WT cells from 3 independent WT MEFs (33, 32 and 38); and 101 Pik3ca ^H1047R cells (38, 39 and 24 from 3 independent Pik3ca ^H1047R MEFs) in anaphase were analyzed for the presence of chromosome segregation errors. Individual values are plotted. c Representative immunofluorescence images of mitotic spindle conformations observed in Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 3 days after treatment with 4-OHT and quantification of the incidence of pseudo-bipolar and multipolar spindles in metaphases with > 2 centrosomes. 74 WT cells (29, 30 and 15 cells from three independent WT MEFs) and 83 Pik3ca ^H1047R cells (30, 27 and 26 cells from 3 independent Pik3ca ^H1047R MEFs) with centrosome amplification in prometaphase/metaphase were analyzed (values = mean ± SD). Statistically significant differences are indicated by *(P < 0.05), as determined by non-parametric Mann–Whitney t test (one-tailed)

Fig. 6

p110α^H1047R expression provides cellular tolerance to genome doubling. a Frequency of aneuploid cells (i.e. with a number of chromosomes that differs from 40), assessed by metaphase chromosome spreads, in primary MEFs 5 days after treatment with 4-OHT. Statistically significant differences are indicated by *(P < 0.05), as determined by non-parametric Mann–Whitney t test (two-tailed). Five independent Pik3ca ^WT;Flpe-ER ^T2 and 5 independent Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs were analyzed, and ~50 metaphase spreads counted per MEF line. b Frequency of tetraploid cells in Pik3ca ^WT;Flpe-ER ^T2 and Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs, 3 and 5 days after treatment with 4-OHT. Cells were considered to be tetraploid (or tetraploid-derived) if the number of chromosomes per cell was ≥ 70. Three independent Pik3ca ^WT;Flpe-ER ^T2 and 3 independent Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs were analyzed, and ~50 metaphase spreads counted per MEF line and per time point (values = mean ± SD). Statistically significant differences are indicated by *(P < 0.05), as determined by the non-parametric Mann–Whitney t test. c Analysis of chromosome numbers in mouse keratinocytes 2 days after addition of 4-OHT. One Pik3ca ^WT;Flpe-ER ^T2 and one Pik3ca ^H1047R+neo;Flpe-ER ^T2 keratinocyte culture were analyzed. d Frequency of binucleated MEFs dividing within a period of 30 h after DCB-induced tetraploidization, assessed 3 days after treatment with 4-OHT. Three independent Pik3ca ^WT;Flpe-ER ^T2 and three independent Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEFs were analyzed, and 60–80 binucleated cells were tracked per MEF line (values = mean ± SD). Statistically significant differences are indicated by *(P < 0.05), as determined by the non-parametric Mann–Whitney t test (one-tailed)

Fig. 7

The cancer cell fraction and timing of PIK3CA ^H1047R mutations in human breast cancer. a The cancer cell fraction of PIK3CA ^H1047R mutations in the TCGA breast cancer cohort. Each symbol represents a non-silent somatic mutation in an individual tumour. On the basis of the probability distributions of the cancer cell fraction, mutations were determined to be either clonal (red circles, upper bound of confidence interval ≥ 1) or subclonal (blue circles, upper band of confidence interval < 1). Error bars represent the 95% confidence interval. PIK3CA ^H1047R mutations are significantly more often clonal than subclonal (P < 0.001). b Timing of PIK3CA ^H1047R mutations in the TCGA genome-doubled breast cancer cohort. The proportion of PIK3CA ^H1047R mutations that likely occurred prior to genome doubling is depicted with a dotted line representing expected distribution based on background randomizations. The graph shows that the majority of PIK3CA ^H1047R mutations likely precede genome doubling, more than expected by chance (P < 0.0001). The proportion of pre-genome doubling is the proportion of PIK3CA ^H1047R mutations that occur pre-genome doubling. The distribution relates to the expected number of mutations occurring pre-genome doubling. This is based on taking the same number of mutations, and randomly sampling this 10,000 times. This gives an estimate of the likelihood that a random sample of mutations would show the same number of pre-doubled mutations

Fig. 8

Impact of pharmacological blockade of PI3K pathway components on tetraploidization in primary and tumour-derived MEFs. a Impact of inhibition of p110α (by 3 µM A66) or ROCK (by 10 µM Y27632) on p110α^H1047R-induced chromosomal abnormalities in primary MEFs. One Pik3ca ^H1047R+neo;Flpe-ER ^T2 MEF line was analyzed and at least 50 metaphase spreads were counted per condition. Inhibitors were added together with the 4-OHT to induce p110α^H1047R expression. b Impact of 14 day inhibition of p110α (by 3 µM A66), Akt (by 1 µM MK-2206) or ROCK (by 10 µM Y27632) on chromosome numbers of two independent stably transformed p110α^H1047R MEF clones with a different degree of tetraploidy. c Impact of inhibition of Akt (by 1 µM Akti X) or ROCK (by 10 µM Y27632) for 21 days on chromosome numbers of p110α^H1047R Nutu clone 1 (shRNA p53-immortalized p110α^H1047R MEF clone passed through nude mice as tumour). Chromosome counting was performed on DAPI-stained metaphase spreads. Fifty spreads were counted per line and condition, unless otherwise stated

Fig. 9

Summary of key observations on the impact of PIK3CA mutation on centrosome amplification and possible tolerance to genome doubling