This study aimed to identify genes regulating cancer stemness of head and neck squamous cell carcinoma (HNSCC) and evaluate the ability of these genes to predict clinical outcomes.
The stemness index (mRNAsi) was obtained using a one-class logistic regression machine learning algorithm based on sequencing data of HNSCC patients. Stemness-related genes were identified by weighted gene co-expression network analysis and least absolute shrinkage and selection operator analysis (LASSO). The coefficient of LASSO was applied to construct a diagnostic risk score model. The Cancer Genome Atlas database, the Gene Expression Omnibus database, Oncomine database and the Human Protein Atlas database were used to validate the expression of key genes. Interaction network analysis was performed using String database and DisNor database. The Connectivity Map database was used to screen potential compounds. The expressions of stemness-related genes were validated using quantitative real‐time polymerase chain reaction (qRT‐PCR).
TTK, KIF14, KIF18A and DLGAP5 were identified. Stemness-related genes were upregulated in HNSCC samples. The risk score model had a significant predictive ability. CDK inhibitor was the top hit of potential compounds.
Stemness-related gene expression profiles may be a potential biomarker for HNSCC.