Genetic and epigenetic changes in chromosomally stable and unstable progeny of irradiated cells

Abstract

Radiation induced genomic instability is a well-studied phenomenon, the underlying mechanisms of which are poorly understood. Persistent oxidative stress, mitochondrial dysfunction, elevated cytokine levels and epigenetic changes are among the mechanisms invoked in the perpetuation of the phenotype. To determine whether epigenetic aberrations affect genomic instability we measured DNA methylation, mRNA and microRNA (miR) levels in well characterized chromosomally stable and unstable clonally expanded single cell survivors of irradiation. While no changes in DNA methylation were observed for the gene promoters evaluated, increased LINE-1 methylation was observed for two unstable clones (LS12 and CS9) and decreased Alu element methylation was observed for the other two unstable clones (115 and Fe5.0-8). These relationships also manifested for mRNA and miR expression. mRNA identified for the LS12 and CS9 clones were most similar to each other (261 mRNA), while the 115 and Fe5.0-8 clones were more similar to each other, and surprisingly also similar to the two stable clones, 114 and 118 (286 mRNA among these four clones). Pathway analysis showed enrichment for pathways involved in mitochondrial function and cellular redox, themes routinely invoked in genomic instability. The commonalities between the two subgroups of clones were also observed for miR. The number of miR for which anti-correlated mRNA were identified suggests that these miR exert functional effects in each clone. The results demonstrate significant genetic and epigenetic changes in unstable cells, but similar changes are almost as equally common in chromosomally stable cells. Possible conclusions might be that the chromosomally stable clones have some other form of instability, or that some of the observed changes represent a sort of radiation signature and that other changes are related to genomic instability. Irrespective, these findings again suggest that a spectrum of changes both drive genomic instability and permit unstable cells to persist and proliferate.

Figure 1. Human NFκB methylation status.

Representative gels for A) methylation sensitive PCR of bisulfite modified DNA for the NFκB promoter; B) PCR of unmodified genomic DNA; and C) methylation sensitive PCR of bisulfite modified DNA for TSLC1 and CDH1 promoter methylation. D) Bisulfite sequencing for NFκB promoter. ‘L’ lanes indicate molecular weight ladders, ‘u’ lanes indicate PCR using primers specific to unmethylated promoter sequences; ‘m’ lanes indicate PCR using primers specific to methylated promoter sequences; ‘u+’ and ‘m+’ indicate respective positive control PCRs; the H2O lane indicates a PCR control containing no DNA template; open circles indicate unmethylated CpG; dashes indicate that no data was obtained).

Figure 2. NFκB gene expression.

A) Melt curve for NFκB qRT-PCR with the two PCR products indicated by red arrows. B) Sequence mismatch between human and CHO PCR products. Red arrows indicate species specific primer sites. C) CHO and D) human NFkB gene expression relative to the parental GM10115 cell line. Columns represent mean + SE for three experiments; * P<0.05, 2-tailed t-test.

Figure 3. DNA methylation for stable and unstable clones normalized to the parental GM10115 cell line.

A) LINE-1, B) Alu element, and C) global DNA methylation relative to the parental GM10115 cell line. D) 11 bands were analyzed for global DNA methylation and sequencing was able to provide identity for 2 of the amplicons. E) Representative gel for methylation sensitive HpaII digest PCR. F) Representative control (MspI) gel supports the hypothesis for possible deletion events in the LS12 and 115 cell lines. Arrows indicate missing band. In all cases the data represent mean +SE for four replicate experiments, * P<0.05, 2-tailed t-test.

Figure 4. Representative heat map emphasizing the relationship among the various clones for significant changes in mRNA levels.

For the purpose of this qualitative illustration, we present the heat map for the statistical threshold of P<0.10 where significant increases are red, significant decreases are green and no change is black. The actual numerical data used in the study were normalized using the Robust multiarray analysis, and differentially regulated genes were identified with multiple testing and false discovery rate statistics at P<0.05. Three replicate arrays were performed and the significance threshold was set at P<0.05.

Figure 5. Overlap in gene expression profiles.

The differentially regulated genes represented in each Venn diagram were identified with multiple testing and false discovery rate statistics at P<0.05. Three replicate arrays were performed and the significance threshold was set at P<0.05.

Figure 6. Overlap in miR expression profiles.

Preliminary statistical analyses were performed on raw data normalized by the LOWESS method on the background-subtracted data. ANOVA were then performed to identify differences in miR expression. Two replicate arrays were performed, so the significance threshold was set at P<0.10.