DHU-Pred: accurate prediction of dihydrouridine sites using position and composition variant features on diverse classifiers

Abstract

Background: Dihydrouridine (D) is a modified transfer RNA post-transcriptional modification (PTM) that occurs abundantly in bacteria, eukaryotes, and archaea. The D modification assists in the stability and conformational flexibility of tRNA. The D modification is also responsible for pulmonary carcinogenesis in humans. Objective: For the detection of D sites, mass spectrometry and site-directed mutagenesis have been developed. However, both are labor-intensive and time-consuming methods. The availability of sequence data has provided the opportunity to build computational models for enhancing the identification of D sites. Based on the sequence data, the DHU-Pred model was proposed in this study to find possible D sites. Methodology: The model was built by employing comprehensive machine learning and feature extraction approaches. It was then validated using in-demand evaluation metrics and rigorous experimentation and testing approaches. Results: The DHU-Pred revealed an accuracy score of 96.9%, which was considerably higher compared to the existing D site predictors. Availability and Implementation: A user-friendly web server for the proposed model was also developed and is freely available for the researchers.