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

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 i...

Full description

Saved in:
Bibliographic Details
Published in:PeerJ (San Francisco, CA) CA), 2022-10, Vol.10, p.e14104, Article e14104
Main Authors: Suleman, Muhammad Taseer, Alkhalifah, Tamim, Alturise, Fahad, Khan, Yaser Daanial
Format: Article
Language:English
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
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2167-8359
2167-8359
DOI:10.7717/peerj.14104