miRNAs expression pattern and machine learning models elucidate risk for gastric GIST

Abstract

BACKGROUND: Gatrointestinal stromal tumors (GISTs) are the main mesenchymal tumors found in the gastrointestinal system. GISTs clinical phenotypes differ significantly and their molecular basis is not yet completely known. microRNAs (miRNAs) have been involved in carcinogenesis pathways by regulating gene expression at post-transcriptional level. OBJECTIVE: The aim of the present study was to elucidate the expression profiles of miRNAs relevant to gastric GIST carcinogenesis, and to identify miRNA signatures that can discriminate the GIST from normal cases. METHODS: miRNA expression was tested by miScript™miRNA PCR Array Human Cancer PathwayFinder kit and then we used machine learning in order to find a miRNA profile that can predict the risk for GIST development. RESULTS: A number of miRNAs were found to be differentially expressed in GIST cases compared to healthy controls. Among them the hsa-miR-218-5p was found to be the best predictor for GIST development in our cohort. Additionally, hsa-miR-146a-5p, hsa-miR-222-3p, and hsa-miR-126-3p exhibit significantly lower expression in GIST cases compared to controls and were among the top predictors in all our predictive models. CONCLUSIONS: A machine learning classification approach may be accurate in determining the risk for GIST development in patients. Our findings indicate that a small number of miRNAs, with hsa-miR218-5p as a focus, may strongly affect the prognosis of GISTs.