miRPara predicts most probable mature miRNA coding regions from genome scale sequences in a species specific manner. We classified sequences from miRBase into animal, plant and overall categories and used a support vector machine (SVM) to train three models based on an initial set of 77 parameters related to the physical properties of the pre-miRNA and its miRNAs. By applying parameter filtering we found a subset of ~25 parameters produced higher prediction ability compared to the full set.
:: MORE INFORMATION
Wu Y., Wei B., Liu H., Li T., Rayner S.
MiRPara: a SVM-based software tool for prediction of most probable microRNA coding regions in genome scale sequences.
BMC Bioinformatics. 2011 Apr 19; 12(1):107