Title: miRNA target recognition using features of suboptimal alignments

Authors: Ali Katanforoush; Ehsan Mahdavi

Addresses: Department of Computer Science, Faculty of Mathematical Sciences, Shahid Beheshti University, G.C., Evin, Tehran, Iran ' Department of Computer Software Engineering, Faculty of Computer and Electrical Engineering, Isfahan Univerity of Technology, Esfahan, Iran

Abstract: MicroRNAs (miRNAs) are a class of short RNA molecules that regulate gene expression by binding directly to messenger RNAs. Conventional approaches to miRNA target prediction estimate the accessibility of target sites and the strength of the binding miRNA by finding optimums of some energy models, which involves O(n³) computations. Alternatively, we narrow down potential binding sites of miRNAs to suboptimal hits of a pairwise alignment algorithm called Fitting Alignment in O(n²). We invoke a same algorithm, once for all candidate sites to measure the site accessibilities. These features are applied to a binary classifier being learned to predict true associations between miRNAs and target genes. Training the classifier requires the negative samples indicating non-affected genes. The experiments verifying such negative associations have been rarely performed, so we exploit tissue-specific gene expression data to impute the negative associations. The recall rate of our method is above 70% (at precision 85%).

Keywords: miRNA target prediction; target genes; RNA accessibility; fitting alignment; post-transcriptional regulation; bioinformatics; target recognition; suboptimal alignments; binding sites; pairwise alignment; gene expression data.

DOI: 10.1504/IJDMB.2015.071523

International Journal of Data Mining and Bioinformatics, 2015 Vol.13 No.2, pp.171 - 180

Received: 31 Dec 2012
Accepted: 19 Oct 2013
Published online: 31 Aug 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article