Screening key lncRNAs with diagnostic and prognostic value for head and neck squamous cell carcinoma based on machine learning and mRNA-lncRNA co-expression network analysis.

摘要: Background Head and neck squamous cell carcinoma (HNSCC) is the seventh most common type of cancer around world. The aim this study was to seek long non-coding RNAs (lncRNAs) acting as diagnostic prognostic biomarker HNSCC. Methods Base on TCGA dataset, differentially expressed mRNAs (DEmRNAs) lncRNAs (DElncRNAs) were identified between HNSCC normal tissue. machine learning survival analysis performed estimate potential value for We also build co-expression network functional annotation. expression selected candidate validated by Quantitative real time polymerase chain reaction (qRT-PCR). Results A total 3363 DEmRNAs (1822 down-regulated 1541 up-regulated mRNAs) 32 DElncRNAs (13 19 lncRNAs) tissue obtained. 13 (IL12A.AS1, RP11.159F24.6, RP11.863P13.3, LINC00941, FOXCUT, RNF144A.AS1, RP11.218E20.3, HCG22, HAGLROS, LINC01615, RP11.351J23.1, AC024592.9 MIR9.3HG) defined optimal biomarkers area under curve (AUC) support vector (SVM) model, decision tree model random forests 0.983, 0.842 specificity sensitivity three 95.5% 96.2%, 77.3% 97.6% 93.2% 97.8%, respectively. Among them, AC024592.9, LINC01615 MIR9-3HG not only an biomarkers, but related time. focal adhesion, ECM-receptor interaction, pathways in cytokine-cytokine receptor interaction four significantly enriched co-expressed with lncRNAs. But DElncRNAs, consistent our integrated results, including TGA6 MMP13. Conclusion a biomarkers.