Translating expression profiling into a clinically feasible test to predict neuroblastoma outcome.

PURPOSE

To assess the feasibility of predicting neuroblastoma outcome using highly parallel quantitative real-time PCR data.

EXPERIMENTAL DESIGN

We generated expression profiles of 63 neuroblastoma patients, 47 of which were analyzed by both Affymetrix U95A microarrays and highly parallel real-time PCR on microfluidic cards (MFC; Applied Biosystems). Top-ranked genes discriminating patients with event-free survival or relapse according to high-level analysis of Affymetrix chip data, as well as known neuroblastoma marker genes (MYCN and NTRK1/TrkA), were quantified simultaneously by real-time PCR. Analysis of PCR data was accomplished using high-level bioinformatics methods including prediction analysis of microarray, significance analysis of microarray, and Computerized Affected Sibling Pair Analyzer and Reporter.

RESULTS

Internal validation of the MFC method proved it highly reproducible. Correlation of MFC and chip expression data varied markedly for some genes. Outcome prediction using prediction analysis of microarray on real-time PCR data resulted in 80% accuracy, which is comparable to results obtained using the Affymetrix platform. Real-time PCR data were useful for risk assessment of relapsing neuroblastoma (P = 0.0006, log-rank test) when Computerized Affected Sibling Pair Analyzer and Reporter analysis was applied.

CONCLUSIONS

These data suggest that multiplex real-time PCR might be a promising approach to reduce the complexity of information obtained from whole-genome array experiments. It could provide a more convenient and less expensive tool for routine application in a clinical setting.