PseUpred-ELPSO Is an Ensemble Learning Predictor with Particle Swarm Optimizer for Improving the Prediction of RNA Pseudouridine Sites

Overview

Journal Biology (Basel)

Publisher MDPI

Specialty Biology

Date 2024 Apr 26

PMID 38666860

Authors

Xiao Wang

Pengfei Li

Rong Wang

Xu Gao

Affiliations

Soon will be listed here.

Abstract

RNA pseudouridine modification exists in different RNA types of many species, and it has a significant role in regulating the expression of biological processes. To understand the functional mechanisms for RNA pseudouridine sites, the accurate identification of pseudouridine sites in RNA sequences is essential. Although several fast and inexpensive computational methods have been proposed, the challenge of improving recognition accuracy and generalization still exists. This study proposed a novel ensemble predictor called PseUpred-ELPSO for improved RNA pseudouridine site prediction. After analyzing the nucleotide composition preferences between RNA pseudouridine site sequences, two feature representations were determined and fed into the stacking ensemble framework. Then, using five tree-based machine learning classifiers as base classifiers, 30-dimensional RNA profiles are constructed to represent RNA sequences, and using the PSO algorithm, the weights of the RNA profiles were searched to further enhance the representation. A logistic regression classifier was used as a meta-classifier to complete the final predictions. Compared to the most advanced predictors, the performance of PseUpred-ELPSO is superior in both cross-validation and the independent test. Based on the PseUpred-ELPSO predictor, a free and easy-to-operate web server has been established, which will be a powerful tool for pseudouridine site identification.

References

Xuan J, Chen L, Chen Z, Pang J, Huang J, Lin J . RMBase v3.0: decode the landscape, mechanisms and functions of RNA modifications. Nucleic Acids Res. 2023; 52(D1):D273-D284. PMC: 10767931. DOI: 10.1093/nar/gkad1070. View

Wu H, Wu Y, Jiang Y, Zhou B, Zhou H, Chen Z . scHiCStackL: a stacking ensemble learning-based method for single-cell Hi-C classification using cell embedding. Brief Bioinform. 2021; 23(1). DOI: 10.1093/bib/bbab396. View

Lovejoy A, Riordan D, Brown P . Transcriptome-wide mapping of pseudouridines: pseudouridine synthases modify specific mRNAs in S. cerevisiae. PLoS One. 2014; 9(10):e110799. PMC: 4212993. DOI: 10.1371/journal.pone.0110799. View

Jiang M, Shao Y, Zhang Y, Zhou W, Pang S . A deep learning method for drug-target affinity prediction based on sequence interaction information mining. PeerJ. 2023; 11:e16625. PMC: 10720480. DOI: 10.7717/peerj.16625. View

Li X, Zhu P, Ma S, Song J, Bai J, Sun F . Chemical pulldown reveals dynamic pseudouridylation of the mammalian transcriptome. Nat Chem Biol. 2015; 11(8):592-7. DOI: 10.1038/nchembio.1836. View

Bi Y, Xiang D, Ge Z, Li F, Jia C, Song J . An Interpretable Prediction Model for Identifying N-Methylguanosine Sites Based on XGBoost and SHAP. Mol Ther Nucleic Acids. 2020; 22:362-372. PMC: 7533297. DOI: 10.1016/j.omtn.2020.08.022. View

Luo Z, Su W, Lou L, Qiu W, Xiao X, Xu Z . DLm6Am: A Deep-Learning-Based Tool for Identifying N6,2'-O-Dimethyladenosine Sites in RNA Sequences. Int J Mol Sci. 2022; 23(19). PMC: 9570463. DOI: 10.3390/ijms231911026. View

Zhou B, Ding M, Feng J, Ji B, Huang P, Zhang J . EVlncRNA-Dpred: improved prediction of experimentally validated lncRNAs by deep learning. Brief Bioinform. 2022; 24(1). PMC: 9851331. DOI: 10.1093/bib/bbac583. View

Li Y, Zhang G, Cui Q . PPUS: a web server to predict PUS-specific pseudouridine sites. Bioinformatics. 2015; 31(20):3362-4. DOI: 10.1093/bioinformatics/btv366. View

10.

Ge J, Yu Y . RNA pseudouridylation: new insights into an old modification. Trends Biochem Sci. 2013; 38(4):210-8. PMC: 3608706. DOI: 10.1016/j.tibs.2013.01.002. View

11.

Aylward A, Petrus S, Mamerto A, Hartwick N, Michael T . PanKmer: k-mer-based and reference-free pangenome analysis. Bioinformatics. 2023; 39(10). PMC: 10603592. DOI: 10.1093/bioinformatics/btad621. View

12.

Jia J, Wei Z, Sun M . EMDL_m6Am: identifying N6,2'-O-dimethyladenosine sites based on stacking ensemble deep learning. BMC Bioinformatics. 2023; 24(1):397. PMC: 10598967. DOI: 10.1186/s12859-023-05543-2. View

13.

Chen W, Tang H, Ye J, Lin H, Chou K . iRNA-PseU: Identifying RNA pseudouridine sites. Mol Ther Nucleic Acids. 2017; 5:e332. PMC: 5330936. DOI: 10.1038/mtna.2016.37. View

14.

Schwartz S, Bernstein D, Mumbach M, Jovanovic M, Herbst R, Leon-Ricardo B . Transcriptome-wide mapping reveals widespread dynamic-regulated pseudouridylation of ncRNA and mRNA. Cell. 2014; 159(1):148-162. PMC: 4180118. DOI: 10.1016/j.cell.2014.08.028. View

15.

Avila Santos A, de Almeida B, Bonidia R, Stadler P, Stefanic P, Mandic-Mulec I . BioDeepfuse: a hybrid deep learning approach with integrated feature extraction techniques for enhanced non-coding RNA classification. RNA Biol. 2024; 21(1):1-12. PMC: 10968306. DOI: 10.1080/15476286.2024.2329451. View

16.

OShea J, Chou M, Quader S, Ryan J, Church G, Schwartz D . pLogo: a probabilistic approach to visualizing sequence motifs. Nat Methods. 2013; 10(12):1211-2. DOI: 10.1038/nmeth.2646. View

17.

de Crecy-Lagard V, Hutinet G, Cediel-Becerra J, Yuan Y, Zallot R, Chevrette M . Biosynthesis and function of 7-deazaguanine derivatives in bacteria and phages. Microbiol Mol Biol Rev. 2024; 88(1):e0019923. PMC: 10966956. DOI: 10.1128/mmbr.00199-23. View

18.

Wu H, Liu M, Zhang P, Zhang H . iEnhancer-SKNN: a stacking ensemble learning-based method for enhancer identification and classification using sequence information. Brief Funct Genomics. 2023; 22(3):302-311. DOI: 10.1093/bfgp/elac057. View

19.

Lv Z, Zhang J, Ding H, Zou Q . RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites. Front Bioeng Biotechnol. 2020; 8:134. PMC: 7054385. DOI: 10.3389/fbioe.2020.00134. View

20.

Wang H, Liu H, Huang T, Li G, Zhang L, Sun Y . EMDLP: Ensemble multiscale deep learning model for RNA methylation site prediction. BMC Bioinformatics. 2022; 23(1):221. PMC: 9178860. DOI: 10.1186/s12859-022-04756-1. View