Can MiRBase provide positive data for machine learning for the detection of MiRNA hairpins?

Experimental detection and validation of miRNAs is a tedious, time-consuming, and expensive process. Computational methods for miRNA gene detection are being developed so that the number of candidates that need experimental validation can be reduced to a manageable amount. Computational methods involve homology-based and ab inito algorithms. Both approaches are dependent on positive and negative training examples. Positive examples are usually derived from miRBase, the main resource for experimentally validated miRNAs. We encountered some problems with miRBase which we would like to report here. Some problems, among others, we encountered are that folds presented in miRBase are not always the fold with the minimum free energy; some entries do not seem to conform to expectations of miRNAs, and some external accession numbers are not valid. In addition, we compared the prediction accuracy for the same negative dataset when the positive data came from miRBase or miRTarBase and found that the latter led to more precise prediction models. We suggest that miRBase should introduce some automated facilities for ensuring data quality to overcome these problems.