Therapy-Related Transcriptional Subtypes in Matched Primary and Recurrent Head and Neck Cancer.

Purpose: The genetic relatedness between primary and recurrent head and neck squamous cell carcinomas (HNSCC) reflects the extent of heterogeneity and therapy-driven selection of tumor subpopulations. Yet, current treatment of recurrent HNSCC ignores the molecular characteristics of therapy-resistant tumor populations.
Experimental Design: From 150 tumors, 74 primary HNSCCs were RNA sequenced and 38 matched primary/recurrent tumor pairs were both whole-exome and RNA sequenced. Transcriptome analysis determined the predominant classical (CL), basal (BA), and inflamed-mesenchymal (IMS) transcriptional subtypes according to an established classification. Genomic alterations and clonal compositions of tumors were evaluated from whole-exome data.
Results: Although CL and IMS subtypes were more common in primary HNSCC with low recurrence rates, the BA subtype was more prevalent and stable in recurrent tumors. The BA subtype was associated with a transcriptional signature of partial epithelial-to-mesenchymal transition (p-EMT) and early recurrence. In 44% of matched cases, the dominant subtype changed from primary to recurrent tumors, preferably from IMS to BA or CL. Expression analysis of prognostic gene sets identified upregulation of hypoxia, p-emt, and radiotherapy resistance signatures and downregulation of tumor inflammation in recurrences compared with index tumors. A relevant subset of primary/recurrent tumor pairs presented no evidence for a common clonal origin.
Conclusions: Our study showed a high degree of genetic and transcriptional heterogeneity between primary/recurrent tumors, suggesting therapy-related selection of a transcriptional subtype with characteristics unfavorable for therapy. We conclude that therapy decisions should be based on genetic and transcriptional characteristics of recurrences rather than primary tumors to enable optimally tailored treatment strategies.
(©2021 American Association for Cancer Research.)