Transcribed-Ultra Conserved Region expression is associated with outcome in high-risk neuroblastoma

Abstract

Background: Neuroblastoma is the most common, pediatric, extra-cranial, malignant solid tumor. Despite multimodal therapeutic protocols, outcome for children with a high-risk clinical phenotype remains poor, with long-term survival still less than 40%. Hereby, we evaluated the potential of non-coding RNA expression to predict outcome in high-risk, stage 4 neuroblastoma.

Methods: We analyzed expression of 481 Ultra Conserved Regions (UCRs) by reverse transcription-quantitative real-time PCR and of 723 microRNAs by microarrays in 34 high-risk, stage 4 neuroblastoma patients.

Results: First, the comparison of 8 short- versus 12 long-term survivors showed that 54 UCRs were significantly (P < 0.0491) over-expressed in the former group. For 48 Ultra Conserved Region (UCRs) the expression levels above the cut-off values defined by ROC curves were strongly associated with good-outcome (OS: 0.0001 <P < 0.0185, EFS: 0.0001 <P < 0.0491). Then we tested the Transcribed-UCR (T-UCR) threshold risk-prediction model on an independent cohort of 14 patients. The expression profile of 28 T-UCRs was significantly associated to prognosis and at least 15 up-regulated T-UCRs are needed to discriminate (P < 0.0001) short- from long-survivors at the highest sensitivity and specificity (94.12%). We also identified a signature of 13 microRNAs differently expressed between long- and short-surviving patients. The comparative analysis of the two classes of non-coding RNAs disclosed that 9 T-UCRs display their expression level that are inversely correlated with expression of 5 complementary microRNAs of the signature, indicating a negative regulation of T-UCRs by direct interaction with microRNAs. Moreover, 4 microRNAs down-regulated in tumors of long-survivors target 3 genes implicated in neuronal differentiation, that are known to be over-expressed in low-risk tumors.

Conclusions: Our pilot study suggests that a deregulation of the microRNA/T-UCR network may play an important role in the pathogenesis of neuroblastoma. After further validation on a larger independent set of samples, such findings may be applied as the first T-UCR prognostic signature for high-risk neuroblastoma patients.

Figure 1

(A) ROC curve. Sensitivity and specificity in predicting survival based on different numbers of T-UCRs whose expression levels are above the thresholds defined by each respective ROC curve. The point marked with the red dot represents the highest average of sensitivity and specificity at the cut-off value of 15 (AUC = 0.988, Z statistic = 25.078, P = 0.0001). Kaplan-Meier analysis for (B) overall and (C) event-free survival of all 34 NBs. Comparison of survival probabilities of patients with ≥15 or <15 up-regulated T-UCRs. In each graph are reported the number of patients in predicted subgroups and the number of patients with event (between brackets).

Figure 2

Hierarchically clustered heat map of differentially expressed microRNAs (n = 13) between the two tumors conditions. Non-detected signals are indicated in white. On top bar, short-survivors tumors (yellow) and long-survivor tumors (blue) are shown.