Jornal de Proteômica e Bioinformática
Acesso livre

Abstrato

Performance and Evaluation of MicroRNA Gene Identification Tools

Swati Sinha, T.S. Vasulu and Rajat K. De

MicroRNAs are small single stranded RNA molecules o f ~ 22 nt in length which play important role in po st transcriptional gene regulation either by translati onal repression of mRNA or by their cleavage. Since their discovery, continuous efforts to identify the miRNA genes led to the discovery of several miRNAs in plants as wel l as animals. Owing to the limitations of the molecular genetic t echniques of miRNA identification, computational ap proaches were introduced for better and affordable in silico- miRNA predictions. Here, we compared a few miRNA ge ne identification tools, such as ‘MiPred’, ‘Triplet-SVM ’, ‘BayesMiRNAfind’, ‘OneClassmiRNAfind’and ‘BayesSVMmiRNAfind’ to evaluate the performance of its predictability based on the real and pseudo pre cursor miRNA datasets. Of all the tools examined MiPred is more sensitive (96%) in identifying pseudo miRNAs than Triplet-SVM for real/pseudo miRNA classification, w hereas for mature miRNA prediction ‘one-class’ SVM classifier shows best specificity (96%), while BayesSVMmiRNAfi nd shows least specificity (8%).