A Bayes Network Model to Determine MiRNA Gene Silence Mechanism
MicroRNAs (miRNAs) are small noncoding RNAs that silence gene expression by base pairing to mRNAs. They play important gene regulatory roles via hybridization to target mRNAs. The functional characterization of miRNAs relies heavily on the identification of their target mRNAs. Determining whether mRNA genes are regulated by translational repression or by post-transcriptional degradation is the premise of accurately identifying miRNA target genes. Combining expression profiling method with computational sequence analysis method, we present a Bayes network model to identify miRNA target genes as well as to determine the gene silence mechanism. The result shows that the learning algorithm of the model has detected 49 % candidate miRNA target genes at 5 % false detection rate and has determined 80 % genes regulated by post-transcriptional degradation mechanism at 3 % false detection rate. Our model precisely predicts miRNA gene silence mechanism and presents an efficient method to find out miRNA targets.
KeywordsMiRNA target identification Gene silence mechanism Bayes network EM algorithm Variational learning
- 6.Huang JC, Morris QD, Frey BJ (2006) Detecting microRNA targets by linking sequence, microRNA and gene expression data. In: Proceedings of the tenth annual conference on research in computational molecular biologyGoogle Scholar
- 7.Jordan MI, Ghahramani Z, Jaakkola TS et al (1999) An introduction to variational methods for graphical models. Learning in graphical models. MIT Press, CambridgeGoogle Scholar
- 8.Neal RM, Hinton GE (1998) A view of the EM algorithm that justifies incremental, sparse, and other variants, learning in graphical models. Kluwer Academic Publishers, BostonGoogle Scholar
- 12.Zhang Y, Rajapakse JC (2009) Machine learning in bioinformatics. Wiley, New JerseyGoogle Scholar