Two-stage clustering based effective sample selection for classification of pre-miRNAs

To solve the class imbalance problem in classification of pre-miRNAs with ab initio method, a novel sample selection method is proposed according to the characteristics of pre-miRNAs. Real/pseudo pre-miRNAs are clustered based on their stem similarity and their distribution in high dimensional sample space respectively. The training samples are selected according to the sample density of each cluster. Experimental results are validated by the cross validation and other testing datasets composed of human real/pseudo pre-miRNAs. When compared with the previous study, microPred, our classifier miRNAPred is nearly 12% greater in total accuracy. Our sample selection algorithm is useful to construct more efficient classifier for classification of real pre-miRNAs and pseudo hairpin sequences.