MicroRNAs regulate their target mRNAs before they are translated into proteins. Although it has been demonstrated that the regulation is through partial binding of the microRNA’s seed region and its targets, the mechanism of this process is not fully discovered. Biological experiments have shown that even perfect base pairing in the seed region does not always guarantee the down-regulation.
In this project, we investigate a microRNAs-transfected microarray data, with the aim of identifying additional features that might differentiate the down-regulated mRNAs from those not down-regulated ones provided both sets have perfect seed match with microRNAs. By employing feature selection techniques in combination with several classification methods, we have been able to identify a set of features that may facilitate the down-regulation of mRNAs. Computationally, our results can be incorporated into target prediction algorithms to further improve their performances. Biologically, the features identified may lead to the discovery of new targeting mechanisms.