Applicability of Gene Expression in Saliva as an Alternative to Blood for Biodosimetry and Prediction of Radiation-induced Health Effects

Abstract

As the great majority of gene expression (GE) biodosimetry studies have been performed using blood as the preferred source of tissue, searching for simple and less-invasive sampling methods is important when considering biodosimetry approaches. Knowing that whole saliva contains an ultrafiltrate of blood and white blood cells, it is expected that the findings in blood can also be found in saliva. This human in vivo study aims to examine radiation-induced GE changes in saliva for biodosimetry purposes and to predict radiation-induced disease, which is yet poorly characterized. Furthermore, we examined whether transcriptional biomarkers in blood can also be found equivalently in saliva. Saliva and blood samples were collected in parallel from radiotherapy (RT) treated patients who suffered from head and neck cancer (n = 8) undergoing fractioned partial-body irradiations (1.8 Gy/fraction and 50-70 Gy total dose). Samples were taken 12-24 h before first irradiation and ideally 24 and 48 h, as well as 5 weeks after radiotherapy onset. Due to the low quality and quantity of isolated RNA samples from one patient, they had to be excluded from further analysis, leaving a total of 24 saliva and 24 blood samples from 7 patients eligible for analysis. Using qRT-PCR, 18S rRNA and 16S rRNA (the ratio being a surrogate for the relative human RNA/bacterial burden), four housekeeping genes and nine mRNAs previously identified as radiation responsive in blood-based studies were detected. Significant GE associations with absorbed dose were found for five genes and after the 2nd radiotherapy fraction, shown by, e.g., the increase of CDKN1A (2.0 fold, P = 0.017) and FDXR (1.9 fold increased, P = 0.002). After the 25th radiotherapy fraction, however, all four genes (FDXR, DDB2, POU2AF1, WNT3) predicting ARS (acute radiation syndrome) severity, as well as further genes (including CCNG1 [median-fold change (FC) = 0.3, P = 0.013], and GADD45A (median-FC = 0.3, P = 0.031)) appeared significantly downregulated (FC = 0.3, P = 0.01-0.03). A significant association of CCNG1, POU2AF1, HPRT1, and WNT3 (P = 0.006-0.04) with acute or late radiotoxicity could be shown before the onset of these clinical outcomes. In an established set of four genes predicting acute health effects in blood, the response in saliva samples was similar to the expected up- (FDXR, DDB2) or downregulation (POU2AF1, WNT3) in blood for up to 71% of the measurements. Comparing GE responses (PHPT1, CCNG1, CDKN1A, GADD45A, SESN1) in saliva and blood samples, there was a significant linear association between saliva and blood response of CDKN1A (R2 = 0.60, P = 0.0004). However, the GE pattern of other genes differed between saliva and blood. In summary, the current human in vivo study, (I) reveals significant radiation-induced GE associations of five transcriptional biomarkers in salivary samples, (II) suggests genes predicting diverse clinical outcomes such as acute and late radiotoxicity as well as ARS severity, and (III) supports the view that blood-based GE response can be reflected in saliva samples, indicating that saliva is a "mirror of the body" for certain but not all genes and, thus, studies for each gene of interest in blood are required for saliva.

FIG. 1.

The box plot in panel A displays the ratio of bacterial 16S rRNA and human 18S rRNA for all whole saliva samples (n = 24). Solid lines represent the median and circles the outliers. The inserted table shows the calculated ratio between raw Ct values of human 18S rRNA and bacterial 16S rRNA as an indicator of bacterial contamination in relation to human RNA. Descriptive statistics: mean, median, standard deviation (stdev), minimum (min) and maximum (max). The box plots in panel B represent the concentration (μg/μl) of 24 RNA isolates (left side). The right side shows the quality of isolated RNA using RNA integrity numbers (RIN) for saliva samples (total n = 24). Dashed lines represent the mean, solid lines the median, and circles the outliers.

FIG. 2.

Aggregated data of DGE in saliva for all 9 genes (PHPT1, CCNG1, CDKN1A, GADD45, SESN1, FDXR, DDB2, POU2AF1, and WNT3) is shown over time of the radiotherapy scheme (number of radiotherapy fractions). GE is given as fold change (FC) relative to unexposed (normalized against a combination of ACTB/ATP6/B2M). Symbols reflect the median (N = 7), and error bars the standard error of the mean (SEM). The superimposed grey area refers to a FC < |2|. Significant changes in GE relative to unexposed are indicated with asterisks (**P < 0.02). Individual plots per donor and gene are shown in Supplementary Fig. S1 (https://doi.org/10.1667/RADE-26-00176.1.S1).

FIG. 3.

This figure focuses on the comparison of radiation-induced DGE of CDKN1A, PHPT1, CCNG1, GADD45, and SESN1 in saliva versus blood (task III-1). Panel A: the DGE of CDKN1A is shown by way of example for each patient in separate panels over time of the radiotherapy scheme (number of radiotherapy fractions). GE is given as fold change (FC) relative to unexposed (normalized against a combination of ACTB/ATP6/B2M in saliva samples and HPRT1 in blood samples). The black circles represent GE results from saliva samples, and gray squares represent GE results from blood samples. In the right panel, data of all patients for CDKN1A is aggregated. Symbols reflect the median (N = 7), and error bars the standard error of the mean (SEM). The superimposed gray areas refer to a FC < |2|. Significant changes in GE relative to unexposed are indicated with asterisks (**P < 0.02). Panel B: FC values obtained with RNA from saliva samples and those obtained with RNA from blood samples for each measurement were correlated with linear regression analysis (calculated R² and P values are provided). Outliers from 95% confidence interval were excluded. Panel C: Equivalently shows aggregated data for PHPT1, CCNG1, CDKN1A, GADD45, and SESN1. Individual plots per donor and gene are shown in Supplementary Fig. S1 (https://doi.org/10.1667/RADE-26-00176.1.S1).