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

PeerJ

article

Muhammad Taseer Suleman¹  Tamim Alkhalifah²  Fahad Alturise²  Yaser Daanial Khan¹ 

[1] Department of Computer Science, School of Systems and Technology, University of Management & Technology;Department of Computer, College of Science and Arts in Ar Rass Qassim University

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

DOI  :  10.7717/peerj.14104

学科分类：社会科学、人文和艺术（综合）

来源: Inra

【 摘 要 】

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

【 授权许可】

CC BY