Find in Library

<p>Abstract</p> <p>Background</p> <p>Virtually all currently available microRNA target site prediction algorithms require the presence of a (conserved) seed match to the 5' end of the microRNA. Recently however, it has been shown that this requirement might be too stringent, leading to a substantial number of missed target sites.</p> <p>Results</p> <p>We developed <it>TargetSpy</it>, a novel computational approach for predicting target sites regardless of the presence of a seed match. It is based on machine learning and automatic feature selection using a wide spectrum of compositional, structural, and base pairing features covering current biological knowledge. Our model does not rely on evolutionary conservation, which allows the detection of species-specific interactions and makes <it>TargetSpy </it>suitable for analyzing unconserved genomic sequences.</p> <p>In order to allow for an unbiased comparison of <it>TargetSpy </it>to other methods, we classified all algorithms into three groups: I) no seed match requirement, II) seed match requirement, and III) conserved seed match requirement. <it>TargetSpy </it>predictions for classes II and III are generated by appropriate postfiltering. On a human dataset revealing fold-change in protein production for five selected microRNAs our method shows superior performance in all classes. In <it>Drosophila melanogaster </it>not only our class II and III predictions are on par with other algorithms, but notably the class I (no-seed) predictions are just marginally less accurate. We estimate that <it>TargetSpy </it>predicts between 26 and 112 functional target sites without a seed match per microRNA that are missed by all other currently available algorithms.</p> <p>Conclusion</p> <p>Only a few algorithms can predict target sites without demanding a seed match and <it>TargetSpy </it>demonstrates a substantial improvement in prediction accuracy in that class. Furthermore, when conservation and the presence of a seed match are required, the performance is comparable with state-of-the-art algorithms. <it>TargetSpy </it>was trained on mouse and performs well in human and drosophila, suggesting that it may be applicable to a broad range of species. Moreover, we have demonstrated that the application of machine learning techniques in combination with upcoming deep sequencing data results in a powerful microRNA target site prediction tool <url>http://www.targetspy.org</url>.</p>