Computational prediction of microRNA regulatory pathways

Abstract

MicroRNAs (miRNAs) are known to regulate transcription and/or protein translation of hundreds of genes. Despite their importance, the functions of most human miRNAs are still poorly understood. In this paper, we proposed a SVM based algorithm - PathMicrO that elucidates the miRNA function by predicting the miRNA regulated pathways. PathMicrO combines the sequence-level target predictions with the gene expression profiling from the miRNA transfection experiments. The performance of PathMicrO is evaluated with cross-validation using a careful constructed training data and two independent testing data. Compared to other prediction algorithms, PathMicrO attains 77% more in sensitivity when false positive rate is equal to 0.21 and achieves much larger area under the receiver operating characteristic (ROC) curve.