Abstract: MicroRNAs (miRNAs) may serve as diagnostic and predictive biomarkers for cancer. The aim of this study was to see if an ensemble technique would identify novel cancer biomarkers from miRNA datasets, in addition to those already known. We applied an ensemble technique to three published miRNA cancer datasets (liver, breast, and brain). In addition to confirming many known biomarkers, the main contribution of this study is that seven miRNAs have been newly identified by our ensemble methodology as possible important biomarkers for hepatocellular carcinoma or breast cancer, pending wet lab confirmation. These biomarkers were identified from miRNA expression datasets by combining multiple feature selection techniques (i.e., creating an ensemble), and then classified by different learners. Generally speaking, creating a subset of features by selecting only the highest ranking features (miRNAs) improved upon results generated when using all the miRNAs, and the ensemble approach outperformed individual feature selection methods.
Keywords: Bioinformatics, data mining, feature selection, ensemble learning, machine learning, microRNA, biomarkers, cancer
