Frontiers in Genetics (Jan 2012)

Accurate microRNA target prediction using detailed binding site accessibility and machine learning on proteomics data

  • Martin eReczko,
  • Martin eReczko,
  • Manolis eMaragkakis,
  • Manolis eMaragkakis,
  • Panagiotis eAlexiou,
  • Panagiotis eAlexiou,
  • Giorgio L. Papadopoulos,
  • Artemis Georgia Hatzigeorgiou,
  • Artemis Georgia Hatzigeorgiou

DOI
https://doi.org/10.3389/fgene.2011.00103
Journal volume & issue
Vol. 2

Abstract

Read online

MicroRNAs (miRNAs) are a class of small regulatory genes regulating gene expression by targetingmessenger RNA. Though computational methods for miRNA target prediction are the prevailingmeans to analyze their function, they still miss a large fraction of the targeted genes and additionallypredict a large number of false positives. Here we introduce a novel algorithm called DIANAmicroT-ANN which combines multiple novel target site features through an artificial neural network(ANN) and is trained using recently published high-throughput data measuring the change of proteinlevels after miRNA overexpression, providing positive and negative targeting examples. The featurescharacterizing each miRNA recognition element include binding structure, conservation level and aspecific profile of structural accessibility. The ANN is trained to integrate the features of eachrecognition element along the 3’ untranslated region into a targeting score, reproducing the relativerepression fold change of the protein. Tested on two different sets the algorithm outperforms otherwidely used algorithms and also predicts a significant number of unique and reliable targets notpredicted by the other methods. For 542 human miRNAs DIANA-microT-ANN predicts 120,000targets not provided by TargetScan 5.0. The algorithm is freely available athttp://microrna.gr/microT-ANN.

Keywords