GEOapplication/xmlftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE92nnn/GSE92595/primaryOK2000000GenomicsHomo sapiensNon-coding RNA profiling by arrayhttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE92595GEOGSE0falsemiRNA profiling in relapsed or metastatic HNSCC patients treated with cetuximab and platinum therapyBy gene expression profiling (GEP) of head and neck squamous cell carcinomas (HNSCC) we were able to identify candidate biomarkers of progression free survival (PFS) in patients treated with cetuximab-based approaches (Bossi et al, Clinical Cancer Research 2016) . Here, the same samples were used for miRNA expression profiling. Integration of miRNA and gene expression data highlighted 16 miRNAs and 84 genes interconnected in a total of 245 interactions. After feature selection by smoothed t-statistic support vector machine, we identified a network 3 miRNAs and 5 genes that resulted the most relevant in predicting PFS (AUC=0.992). Overall, using a well defined clinical setting we gave the proof of principle that an integrative miRNA-mRNA expression could greatly contribute to refinement of the biology behind and to the potential identification of a predictive model.2017/03/08GSE92595GSM2433192GSM2433170GSM2433191GSM2433190GSM2433174GSM2433196GSM2433195GSM2433173GSM2433172GSM2433194GSM2433171GSM2433193GSM2433178GSM2433177GSM2433199GSM2433198GSM2433176GSM2433175GSM2433197GSM2433179GSM2433181GSM2433180GSM2433185GSM2433184GSM2433183GSM2433182GSM2433200GSM2433189GSM2433167GSM2433166GSM2433188GSM2433187GSM2433186GSM2433204GSM2433203GSM2433169GSM2433202GSM2433201GSM2433168GSM24332052096892595Homo sapiens[28098823]