RNA Oncoimmune Phenotyping of HPV-Positive p16-Positive Oropharyngeal Squamous Cell Carcinomas by Nodal Status

Abstract

Clinical trials that deintensify treatment for patients with suspected human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) use p16 expression to identify HPV-mediated tumors and guide treatment. While p16 staining has a strong correlation with good outcomes, approximately 12% of p16-positive patients have recurrent disease. Biomarkers that reveal tumor-specific characteristics, such as nodal involvement, may change therapy decisions. To assess whether if a tumor-specific genetic signature exists for node-negative vs node-positive HPV 16-positive/p16-positive OPSCCs. This was a retrospective cohort study with randomized case selection for p16 OPSCCs undertaken at a university-based, tertiary care cancer center. Samples were collected from patients with p16-positive OPSCC. A total of 21 HPV 16/p16-positive tumors were used in this study. Gene expression profiles of node-negative vs node-positive tumor samples were evaluated using a differential expression analysis approach and the sensitivity and specificity of a molecular signature was determined. Among the 21 patients in the study (3 women, 18 men; mean [SD] age, 54.6 [9.6] years), 6 had node-negative disease and 15 had node-positive disease. Using differential expression analysis, we found 146 genes that were significantly different in patients with node-negative disease vs those with node-positive disease, of which 15 genes were used to create a genetic signature that could distinguish node-negative-like from node-positive-like disease. The resultant molecular signature has a sensitivity of 88.2% (95% CI, 63.6%-98.5%) and specificity of 85.7% (95% CI, 42.1%-99.6%). The positive likelihood ratio of this signature was 6.1 (95% CI, 1.0-38.2) and the negative likelihood ratio was 0.1 (95% CI, 0.04-0.5). Given this population's prevalence of node-positive disease of 70.8%, the positive- and negative-predicative values for this gene signature were 93.7% (95% CI, 70.8%-98.9%) and 75.0% (95% CI, 44.1%-92.0%), respectively. In addition, we developed a gene signature using agnostic, machine learning software that identified a 40-gene profile that predicts node-negative disease from node-positive disease (area under the curve, 0.93; 95% CI, 0.63-1.00). Many HPV-16 and p16-positive tumors are treated as "lower-risk," but they do not have similar genetic compositions at the biological level. The identification of subgroups with unique expression patterns, such as those with nodal metastases, may guide physicians toward alternative or more aggressive therapies. In our study, unguided clustering suggested that that the larger biological characteristics of a tumor could be a better prognostic biomarker.