Head and neck cancer subtypes with biological and clinical relevance: Meta-analysis of gene-expression data

Abstract

Head and neck squamous cell carcinoma (HNSCC) is a disease with heterogeneous clinical behavior and response to therapies. Despite the introduction of multimodality treatment, 40-50% of patients with advanced disease recur. Therefore, there is an urgent need to improve the classification beyond the current parameters in clinical use to better stratify patients and the therapeutic approaches. Following a meta-analysis approach we built a large training set to whom we applied a Disease-Specific Genomic Analysis (DSGA) to identify the disease component embedded into the tumor data. Eleven independent microarray datasets were used as validation sets. Six different HNSCC subtypes that summarize the aberrant alterations occurring during tumor progression were identified. Based on their main biological characteristics and de-regulated signaling pathways, the subtypes were designed as immunoreactive, inflammatory, human papilloma virus (HPV)-like, classical, hypoxia associated, and mesenchymal. Our findings highlighted a more aggressive behavior for mesenchymal and hypoxia-associated subtypes. The Genomics Drug Sensitivity Project was used to identify potential associations with drug sensitivity and significant differences were observed among the six subtypes. To conclude, we report a robust molecularly defined subtype classification in HNSCC that can improve patient selection and pave the way to the development of appropriate therapeutic strategies.

Keywords: HNSCC; gene expression; meta-analysis; microarray; tumor subtypes.

Figure 1. Study outline

Figure 2. Molecular classification in HNSCC

Results are produced by ConsensusClusterPlus for 527 cases on 4950 most variable genes. A. Consensus matrix heatmap imposing six subtypes on the dataset: Cl1 (n = 89; 17%); Cl2 (n = 77; 15%); Cl3 (n = 154; 29%); Cl4 (n = 79; 15%); Cl5 (n = 81; 15%); Cl6 (n = 47; 9%). The consensus values range from 0 (white, samples that never cluster together) to 1 (blue, samples showing high clustering affinity). B. Silhouette plot analysis. Since the actual number of subtypes in HNSCC is not known, we should take into account that the number of subtypes may be greater than six with some subtypes not sufficiently represented in our dataset. To ascertain whether some samples are forced to belong to a certain cluster, silhouette plot analysis was carried out. The widths indicate a strong similarity of the samples within their subgroup compared with the samples belonging to other subgroups.

Figure 3. Heatmap of pathways enriched in the six subtypes

The molecular pathways and onco-signatures enriched in each subtype as investigated through GSEA. A. The relative enrichment of 17 gene-ontology pathways related to biological processes. B. The relative enrichment of 11 onco-signatures.

Figure 4. Comparison of genome-wide molecular pattern between our and previously reported subtype classification

The analysis was performed using Subclass Mapping. A. MetaHNC-A is compared with the molecular subtypes defined by Walter et al. ((48); GSE39368). B. MetaHNC-A is compared to the subtypes reported by Chung et al. ((47); GSE686). Red color indicates high confidence for correspondence (p < 0.05); blue color indicates lack of correspondence. BA, basal; MS, mesenchymal; AT, atypical; CL, classical subtypes in the study by Walter et al. G1, G2, G3, G4 refer to the four subtypes identified in the study by Chung et al. C. Table summarizing the correspondence between our subtyping classification and those previously published for HNSCC by Chung et al. (47) and Walter et al. (48).

Figure 5. Progression analysis of disease

The average distance of each tumor from the normal state has been assessed. A. 603 genes were identified associated to PAD. The upper bar illustrates to which subtype belongs each tumor sample. B. The box plots show the distance from normal state of each tumor was in relation to the six subtypes. Y-axis represents the distance from normal state computed as average bin-membership by PAD and depicted in Figure S4.

Figure 6. Distribution of the PAM classifier genes in the HNSCC subtypes identified in the training dataset

Heatmap of the expression values of the 2843 classifier genes.

Figure 7. Survival analysis by Kaplan-Meier for each subtype

The cases entering into the six subtypes identified on both validation datasets were used for the Kaplan-Meier analysis. A. TCGA dataset: log rank p = 0.0006; B. GSE39368 dataset: log rank p = 0.576; C. MetaHNC-B dataset: log rank p = 0.0312. OS, overall survival; RFS, relapse free survival.

Figure 8. Prediction drug sensitivity in HNSCC subtypes

Drug sensitivity was predicted for each case entering the MetaHNC-A dataset. Five therapeutic agents were investigated: A. Afatinib; B. Paclitaxel; C. Z-LLNle-CHO; D. Nutlin 3a; E. Rapamycin. Box-plots depict the predicted drug sensitivity in the six subtypes and the ROC curves estimate prediction accuracy of the more sensitive subtype against the others. p = Kruskal-Wallis test; AUC, area under the curve.