Improving bioinformatics prediction of microRNA targets by ranks aggregation

Abstract

microRNAs are non-coding RNAs which down-regulate a large number of target mRNAs and modulate cell activity. Despite continued progress, bioinformatics prediction of microRNA targets remains a challenge since available softwares still suffer from a lack of accuracy and sensitivity. Moreover, these tools show fairly inconsistent results from one another. Thus, in an attempt to circumvent these difficulties, we aggregated all human results of three important prediction algorithms (miRanda, PITA and SVmicrO) showing additional characteristics in order to rerank them into a single list. This database is freely available through a webtool called miRabel (http://bioinfo.univ-rouen.fr/mirabel/) which can take either a list of miRNAs, genes or signaling pathways as search inputs. Receiver Operating Characteristic curves and Precision-Recall curves analysis carried out using experimentally validated data and very large datasets show that miRabel significantly improves the prediction of miRNA targets compared to the three algorithms used separatly. Moreover, using the same analytical methods, miRabel shows significantly better predictions than other popular algorithms such as MBSTAR and miRWalk. Interestingly, a F-score analysis revealed that miRabel also significantly improves the relevance of the top results. The aggregation of results from different databases is therefore a powerful and generalizable approach to many other species to improve miRNA target predictions. Thus, miRabel is an efficient tool to accurately identify miRNA targets and integrate them into a biological context.