A Feature Fusion Predictor for RNA Pseudouridine Sites with Particle Swarm Optimizer Based Feature Selection and Ensemble Learning Approach

Abstract

RNA pseudouridine modification is particularly important in a variety of cellular biological and physiological processes. It plays a significant role in understanding RNA functions, RNA structure stabilization, translation processes, etc. To understand its functional mechanisms, it is necessary to accurately identify pseudouridine sites in RNA sequences. Although some computational methods have been proposed for the identification of pseudouridine sites, it is still a challenge to improve the identification accuracy and generalization ability. To address this challenge, a novel feature fusion predictor, named PsoEL-PseU, is proposed for the prediction of pseudouridine sites. Firstly, this study systematically and comprehensively explored different types of feature descriptors and determined six feature descriptors with various properties. To improve the feature representation ability, a binary particle swarm optimizer was used to capture the optimal feature subset for six feature descriptors. Secondly, six individual predictors were trained by using the six optimal feature subsets. Finally, to fuse the effects of all six features, six individual predictors were fused into an ensemble predictor by a parallel fusion strategy. Ten-fold cross-validation on three benchmark datasets indicated that the PsoEL-PseU predictor significantly outperformed the current state-of-the-art predictors. Additionally, the new predictor achieved better accuracy in the independent dataset evaluation—accuracy which is significantly higher than that of its existing counterparts—and the user-friendly webserver developed by the PsoEL-PseU predictor has been made freely accessible.

Fuzzy kernel evidence Random Forest for identifying pseudouridine sites

“…In this section, we thoroughly assess and compare the predictive performance of PseU-FKeERF with other methods, using the same benchmark training and independent testing data sets utilized by several previous state-of-the-art methods. Tables 8 and 9 summarize the performance comparisons between the PseU-FKeERF and several state-of-the-art predictors including iRNA-PseU [ 22 ], PseUI [ 23 ], iPseU-CNN [ 24 ], XG-PseU [ 25 ], EnsemPseU [ 26 ], RF-PseU [ 27 ], MU-PseUDeep [ 28 ], Porpoise [ 29 ], PsoEL-PseU [ 31 ] and PseUdeep [ 30 ] on the same benchmark training and independent testing dataset, respectively. Compared to other existing methods using the same training dataset, PseU-FKeERF performed better on two important measures for three species, namely ACC and MCC.…”

“…Wang et al . established PsoEL-PseU, a feature fusion predictor, for the identification of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\Psi $\end{document} sites [ 31 ].While computational methods for predicting \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $\Psi $\end{document} sites have made significant strides, there are still limitations that must be addressed to develop more robust and accurate approaches, as shown in Supplementary Table S1 .…”

PseU-ST: A new stacked ensemble-learning method for identifying RNA pseudouridine sites

“…Then, Li et al (2021b) proposed a computational model called Porpoise, which selects four optimal types of features and fed them into a stacked model to predict Ψ sites. Zhuang et al (2021) proposed PseUdeep, a deep learning framework, and Wang et al (2021) proposed a feature fusion predictor named PsoEL-PseU in the same year; however, their performance are unsatisfactory. The accuracy scores of the best existing methods mentioned above are 79.70%, 81.69%, and 89.34% in H. sapiens , S. cerevisiae , and M. musculus , respectively, so there is still much opportunity for improvement.…”