Prediction of C-to-U RNA editing sites in higher plant mitochondria using only nucleotide sequence features

RNA editing is a class of post-transcriptional processing which contributes to the organism complexity. C-to-U RNA editing is commonly observed in higher plant mitochondria. The in vivo mechanism of recognizing C-to-U RNA editing sites is still unknown. In recent years, many efforts have been made to computationally predict C-to-U RNA editing sites. But all existing methods require using knowledge other than an RNA sequence. In the present work, we propose the first method for predicting C-to-U RNA editing sites using only nucleotide sequence features. This method was developed based on the SVM algorithm combined with a triplet scoring model. Our method can achieve 84% overall accuracy which is comparable to other methods. We also computationally found that several triplets never appear upstream near an edited cytidine, indicating that these triplets may protect a cytidine from being edited. This discovery suggests the need for further experimental research and may be helpful in understanding the editing site recognition mechanism.