Gene Expression Analysis of (Paired) Primary and Relapsed Wilms Tumor Samples to Unravel the Underlying Factors Driving Tumor Recurrence

Abstract

Purpose: We aimed to unravel underlying factors driving Wilms tumor (WT) recurrence and to build a prediction model for recurrence based on gene expression data of (paired) primary and relapsed WT samples.

Experimental design: Gene expression levels from seven paired primary and relapsed WT samples from patients treated in the Princess Máxima Center were compared among each other, as well as to matched primary WT samples of patients without recurrence (controls). The differential gene expression analysis results were run through ToppGene for functional enrichment. We built a 10-fold ridge regression model to predict relapse based on gene expression levels of the seven primary cases and all other available primary WT controls (n = 42).

Results: The comparison of primary WT and paired relapses showed downregulation of genes involved in immune regulation among relapses and upregulation of cancer stem cell (CSC) regulation genes. Comparing these primary WT samples to matched controls, we observed that downregulated genes in primary samples of relapsed patients were related to stromal cells and muscle development, and upregulated genes were associated with CSCs. The prediction model revealed a sensitivity of 57.14% (95% CI: 14.29%-85.71%) and a specificity of 92.86% (95% CI: 83.33%-100%) when predicting WT relapse.

Conclusion: The CSC pool could play a role in relapse through immune regulation and tumor propagation. Differentiation of CSCs into mesenchymal cells might attenuate the risk of relapse. Our prediction model might aid in selecting patients with an increased risk of relapse at primary diagnosis when externally validated.

FIGURE 1

Copy number variations and mutated genes in paired primary and relapsed WT samples.

FIGURE 2

Differential gene expression comparing primary and paired relapsed WT samples. (A) Principal component analysis based on the top 500 genes (VST normalized). (B) Volcano plot showing all significantly differentially expressed genes. The most differentially expressed genes (based on adjusted p‐value) are annotated by gene symbol.

FIGURE 3

TERT expression (transcripts per million (TPM)) in primary and paired relapsed WT samples, compared using the Wilcoxon signed‐rank test. Patient 7 has a known TERT mutation (c.‐146C>T).

FIGURE 4

Differential gene expression comparing primary WT samples of patients with subsequent relapse (cases) and without (controls). (A) Principal component analysis based on the top 500 genes (VST normalized). (B) Volcano plot showing all significantly differentially expressed genes. The most differentially expressed genes (based on adjusted p‐value) are annotated by gene symbol.

FIGURE 5

Distribution of immune cell type proportions across control samples and paired primary and relapse samples.

FIGURE 6

(A) Results of ridge regression WT relapse prediction model. (B) ROC‐curve with a maximized sensitivity and specificity at a threshold of 0.136.