Heterogeneous ensemble approach with discriminative features and modified-SMOTEbagging for pre-miRNA classification

Abstract

An ensemble classifier approach for microRNA precursor (pre-miRNA) classification was proposed based upon combining a set of heterogeneous algorithms including support vector machine (SVM), k-nearest neighbors (kNN) and random forest (RF), then aggregating their prediction through a voting system. Additionally, the proposed algorithm, the classification performance was also improved using discriminative features, self-containment and its derivatives, which have shown unique structural robustness characteristics of pre-miRNAs. These are applicable across different species. By applying preprocessing methods—both a correlation-based feature selection (CFS) with genetic algorithm (GA) search method and a modified-Synthetic Minority Oversampling Technique (SMOTE) bagging rebalancing method—improvement in the performance of this ensemble was observed. The overall prediction accuracies obtained via 10 runs of 5-fold cross validation (CV) was 96.54%, with sensitivity of 94.8% and specificity of 98.3%—this is better in trade-off sensitivity and specificity values than those of other state-of-the-art methods. The ensemble model was applied to animal, plant and virus pre-miRNA and achieved high accuracy, >93%. Exploiting the discriminative set of selected features also suggests that pre-miRNAs possess high intrinsic structural robustness as compared with other stem loops. Our heterogeneous ensemble method gave a relatively more reliable prediction than those using single classifiers. Our program is available at http://ncrna-pred.com/premiRNA.html.

miRBoost: boosting support vector machines for microRNA precursor classification

“…miRBoost was compared with several existing computational tools of pre-miRNA classification in order to evaluate its performance: CSHMM (Agarwal et al 2010) and triplet-SVM (Xue et al 2005), which do not take into account the imbalance problem; HeteroMirPred (Lertampaiporn et al 2013), microPred (Batuwita and Palade 2009), MiPred (Jiang et al 2007), and mirExplorer (Guan et al 2011), which deal with imbalanced data; and MIReNA (Mathelier and Carbone 2010), which does not apply machine learning techniques for classification. These tools are described in more detail in the Materials and Methods.…”

“…As mentioned in the Results, we used several of them for comparison with miRBoost: CSHMM (Agarwal et al 2010), triplet-SVM (Xue et al 2005), microPred (Batuwita and Palade 2009), HeteroMirPred (Lertampaiporn et al 2013), MiPred (Jiang et al 2007), mirExplorer (Guan et al 2011), and MIReNA (Mathelier and Carbone 2010), which are described as follows.…”

“…Such methods include microPred (Batuwita and Palade 2009), MiRenSVM (Ding et al 2010), mirExplorer (Guan et al 2011), HeteroMirPred (Lertampaiporn et al 2013), and HuntMi (Gudys et al 2013).…”

Genome-wide discovery of miRNAs using ensembles of machine learning algorithms and logistic regression

“…MiPred relies on MFE, triplet structure features and a p-value for how significantly different the MFE is from that of random sequences, while HuntMi relies on the features used by microPred and seven additional features. Finally, miR-BAG (Jha et al, 2012) and HeteroMirPred (Lertampaiporn et al, 2012) are ensemble-based. While miR-BAG combines SVMs, naïve Bayes and best-first tree, HeteroMirPred uses SVMs, k-nearest neighbours and random forests.…”

Heterogeneous Ensemble for Imaginary Scene Classification

“…The keypoint approach was originally created to classify text datasets, and was found to be useful for image classification as conducted in this experiment and others, including in (Lowe, 2004), (Ke and Sukthankar, 2004), (Mikolajczyk and Schmid, 2004). (Lertampaiporn et al, 2013) applied a heterogeneous ensemble for pre-miRNA in their experiment by using voting for a set of classifiers including a support vector machine, k-NN and random forests.…”