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

Muhammad Taseer Suleman; Tamim Alkhalifah; Fahad Alturise; Yaser Daanial Khan

doi:10.7717/peerj.14104

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

PeerJ. 2022 Oct 27:10:e14104. doi: 10.7717/peerj.14104. eCollection 2022.

Authors

Muhammad Taseer Suleman¹, Tamim Alkhalifah², Fahad Alturise², Yaser Daanial Khan¹

Affiliations

¹ Department of Computer Science, School of Systems and Technology, University of Management & Technology, Lahore, Pakistan.
² Department of Computer, College of Science and Arts in Ar Rass Qassim University, Ar Rass, Qassim, Saudi Arabia.

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.

Keywords: Classification; DHU-Pred; Dihydrouridine; Machine learning; Post Transcriptional Modification; Prediction; RNA; Random Forest; Statistical moments; Uridine modifications.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Computational Biology* / methods
Eukaryota
Humans
Machine Learning
RNA, Transfer*

Substances

RNA, Transfer

Grants and funding

This project was supported by the Deanship of Scientific Research, Qassim University. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.