Fig. 3From: Mirnacle: machine learning with SMOTE and random forest for improving selectivity in pre-miRNA ab initio predictionTraining set construction. Each stage has its own training set for building its specific machine learning model. Real pre-miRNAs are used as positive examples, while negative examples are comprised of snRNAs, snoRNAs, tRNAs, miscRNAs, and pseudo hairpinsBack to article page