Technical Report Number
More recent evidence has shown that access of animal microRNAs (miRNAs) to their complementary sites in target mRNAs is determined by more sequence-specific determinants than the seed regions in the 5' end of miRNAs. Although these factors have been shown to be related to the repressive power of miRNAs and used, in separate programs, to predict the efficacy of miRNA complementary sites, it remains unclear whether these factors can help to improve miRNA target prediction. We develop a new miRNA target prediction algorithm, called Hitsensor, by incorporating more sequence-specific features that determine complementarities between miRNAs and their targets, in addition to the canonical seed regions in the 5' ends of miRNAs. We evaluate the performance of our algorithm on 720 known animal miRNA:target pairs in four species, Homo sapiens, Mus musculus, Drosophila melanogaster and Caenorhabditis elegans. Our prediction results show that Hitsensor outperforms five popular existing algorithms, indicating that our unique scheme to quantify the determinants of complementary sites is effective in improving the performance of a miRNA target prediction algorithm. Unlike most existing algorithms, our method does not use conservation information and can find many unconserved miRNA:target pairs.
Zheng, Yun and Zhang, Weixiong, "Animal microRNA Target Prediction By Incorporating Diverse Sequence-Specific Determinants" Report Number: WUCSE-2008-20 (2008). All Computer Science and Engineering Research.
Permanent URL: http://dx.doi.org/10.7936/K7G73BZT