Provides a target prediction method that does not require sequence conservation, using instead, machine learning by a naïve Bayes classifier. NbmiRTar generates a model from sequence and miRNA:mRNA duplex information from validated targets and artificially generated negative examples. Both the ‘seed’ and ‘out-seed’ segments of the miRNA:mRNA duplex are used for target identification. The method produces fewer false positive predictions and fewer target candidates to be tested.
This project is funded in part by U01 CA85060 and the Pennsylvania Department of Health (PA DOH Commonwealth Universal Research Enhancement Program), and Tobacco Settlement grants ME01-740 and SAP 4100020718, NSF RCN 0090286.