Prognostic testing in uveal melanoma by transcriptomic profiling of fine needle biopsy specimens

Abstract

Many uveal melanoma patients die of metastasis despite ocular treatment. Transcriptomic profiling of enucleated tumors can identify patients at high metastatic risk. Because most uveal melanomas do not require enucleation, a biopsy would be required for this analysis. Here, we establish the feasibility of transcriptomic analysis of uveal melanomas from fine needle aspirates. Transcriptomic profiles were analyzed from postenucleation "mock" needle biopsies and matching tumors from eight enucleated eyes and from fine needle aspirates in 17 uveal melanomas before radiotherapy. Predictive accuracy was assessed using a weighted voting classifier optimized for probe set selection using a minimal redundancy/maximum relevance algorithm. Transcriptomic profiles from mock biopsies were highly similar to those from their matching tumor samples (P < 0.0001). Transcriptomic profiles from fine needle aspirates clustered into two classes with discriminating probe sets that overlapped significantly with those for our published classification (P < 0.00001). No loss of predictive accuracy was identified among eight needle aspirates obtained from a distant location. Thus, it is feasible to obtain RNA of adequate quality and quantity to perform transcriptomic analysis on uveal melanoma samples obtained by fine needle biopsy. This method can be applied to specimens obtained from distant geographic locations and can stratify uveal melanoma patients based on metastatic risk.

Figure 1

Overview of study design.

Figure 2

Heat maps showing unsupervised hierarchical clustering of uveal malignant melanomas (MM), matching mock biopsy specimens (MB), and needle biopsy specimens (NB) using 806 probe sets filtered for a median significance P value <0.05 and gene expression variance >1.

Figure 3

A: Venn diagram showing concordant probe sets between the NB, MM-MB, and origMM datasets. B: Comparison of GenChip expression units for the 45-probe set list in the indicated datasets. C: Hierarchical clustering and (D) principal component analysis of the indicated datasets using the 45-probe-set list (blue spheres, class 1 tumors; red spheres, class 2 tumors). The two classes indicated in the Tschentscher dataset refer to monosomy versus disomy for chro-mosome 3.

Figure 4

Predictive model for classifying tumor samples for the indicated datasets. The predictive model was evaluated for class assignment by transcriptome signature in all datasets except the Tschentscher dataset, which was evaluated for monosomy 3. Probe sets were entered randomly (−mRMR) or by minimum redundancy and maximum relevance (+mRMR) into a weighted voting algorithm. Classification errors calculated by leave-one-out cross-validation are plotted on the upper graph. The mean and minimum confidence scores are plotted on the lower graph.