Gene variability between perineural-positive and perineural-negative squamous cell skin cancers

Abstract

Aim: To identify differentially expressed genes (DEGs) between perineural invasion-positive (PP) and-negative (PN) cutaneous squamous cell cancers (CSCC). Materials/Methods: Forty CSCC samples with and without perineural invasion were processed for RNA isolation and hybridization to Affymetrix-U219 DNA microarrays. Raw gene expression data were normalized by Robust Multi-array Averaging (RMA) and log2 transformed. Gene expression-based classification models were created and accuracies evaluated using leave-oneout cross-validation. Results: At a stringent limma p-value (p<0.001), 24 genes were differentially expressed between PP and PN samples. The cross-validated performance of the eight classification models exhibited a mean accuracy of 85-95%. Diagonal linear discriminant was most accurate at 95%, followed by Bayesian compound covariate at 94%. The poorest accuracy (85%) was observed for 1-Nearest neighbor and Support vector machines. Conclusion: Gene expression may distinguish between PP and PN CSCC. Understanding these gene patterns may potentiate more timely diagnosis of perineural invasion and guide comprehensive therapies.