Identifying radiation exposure biomarkers from mouse blood transcriptome

Abstract

Ionising radiation is a pleiotropic stress agent that may induce a variety of adverse effects. Molecular biomarker approaches possess promise to assess radiation exposure, however, the pleiotropic nature of ionising radiation induced transcriptional responses and the historically poor inter-laboratory performance of omics-derived biomarkers serve as barriers to identification of unequivocal biomarker sets. Here, we present a whole-genome survey of the murine transcriptomic response to physiologically relevant radiation doses, 2 Gy and 8 Gy. We used this dataset with the Random Forest algorithm to correctly classify independently generated data and to identify putative metabolite biomarkers for radiation exposure.

Figure 1

Assessment of the murine transcriptional response to γ-rays in the context of radiation responsive genes identified in an ex vivo human study (Paul and Amundson, 2008). (A) Heatmap of the murine homologs for the genes in the radiation response classifier constructed by Paul and Amundson. The left-side bar indicates the direction of transcriptional perturbation by ionising radiation in the human dataset (green: down-regulated, red: up-regulated). The majority of the murine homologs are perturbed in the same direction as the human genes by ionising radiation exposure. (B) qRT-PCR measurements of select radiation-responsive genes (Bax, Cdkn1a, Isg20l1) normalised to GADPH from three of the samples (0, 2 and 8Gy) (see online version for colours)

Figure 2

Analysis of the classifier. (A) Multi-dimensional-scaling plot of the control (0 Gy) and γ-irradiated (2 and 8 Gy) samples using the 50 most important genes as determined by Random Forests illustrates a strong separation of the control and two treatment groups. (B) Heatmap of radiation-responsive transcriptional perturbations, relative to the median of the control group, for the 50 most important genes as determined by Random Forests. (C) Heatmap of radiation-responsive transcriptional perturbations, relative to the median of the control group, for the 50 most important up-regulated genes as determined by Random Forests (see online version for colours)

Figure 3

Heatmap of the aggregate Z-scores for putative reporter metabolites associated with transcriptional perturbations in the murine metabolic network following γ-ray exposure (2 Gy and 8 Gy). P-values were calculated for each gene in the treatment groups vs. the control group using Student’s t-test and the Benjamini–Hochberg correction for multiple hypotheses testing. The p-values were converted to Z-scores using the inverse normal cumulative distribution, and aggregate Z-scores for the metabolites were calculated from the Z-scores of all genes whose gene products employed the metabolite as a substrate. Promiscuous metabolites, such as the hydrogen ion, phosphate ion and water, were excluded from analysis (see online version for colours)