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

• Published in: PeerJ (San Francisco, CA) Vol. 10; p. e14104
• Main Authors: Suleman, Muhammad Taseer, Alkhalifah, Tamim, Alturise, Fahad, Khan, Yaser Daanial
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 27-10-2022; PeerJ, Inc; PeerJ Inc
• Subjects: Accuracy; Bacteria; Bioinformatics; Carcinogenesis; Classification; Computational Biology; Computational Biology - methods; Computer applications; Data Mining and Machine Learning; Datasets; Dihydrouridine; Enzymes; Eukaryota; Feature selection; Gene expression; Genetic transcription; Genomics; Humans; Machine Learning; Mass spectrometry; Mass spectroscopy; Mathematical models; Methods; Post-transcription; Prediction; RNA modification; RNA, Transfer; Site-directed mutagenesis; Statistical moments; Statistics; Support vector machines; Transfer RNA; tRNA; tRNA Ala; Uridine modifications; DHU-Pred; Dihydrouridine; RNA; Classification; Machine learning; Prediction; Post Transcriptional Modification; Uridine modifications; Statistical moments; Random Forest
• ISSN: 2167-8359; 2167-8359
• DOI: 10.7717/peerj.14104

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.
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.
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.
The DHU-Pred revealed an accuracy score of 96.9%, which was considerably higher compared to the existing D site predictors.
A user-friendly web server for the proposed model was also developed and is freely available for the researchers.