PseUdeep: RNA Pseudouridine Site Identification with Deep Learning Algorithm

Zhuang, Jujuan; Liu, Danyang; Lin, Meng; Qiu, Wei; Liu, Jinyang; Chen, Size

doi:10.3389/fgene.2021.773882

Cited by 11 publications

(8 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used several widely used performance metrics to evaluate and compare the function of PseU-ST and other existing methods. The metrics are sensitivity (Sn), specificity (Sp), accuracy (ACC), Matthew’s Correlation Coefficient (MCC), and area under the receiver operating curve (AUC) ( Mu et al, 2020 ; Li et al, 2021a ; Zhuang et al, 2021 ). Sn, Sp, ACC, and MCC are defined as follows:

where TP, TN, FP, and FN represent the true positive, true negative, false positive, and false negative, respectively.…”

Section: Methodsmentioning

confidence: 99%

“…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.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Zhang

Wang²,

Xie³

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

Background: Pseudouridine (Ψ) is one of the most abundant RNA modifications found in a variety of RNA types, and it plays a significant role in many biological processes. The key to studying the various biochemical functions and mechanisms of Ψ is to identify the Ψ sites. However, identifying Ψ sites using experimental methods is time-consuming and expensive. Therefore, it is necessary to develop computational methods that can accurately predict Ψ sites based on RNA sequence information.Methods: In this study, we proposed a new model called PseU-ST to identify Ψ sites in Homo sapiens (H. sapiens), Saccharomyces cerevisiae (S. cerevisiae), and Mus musculus (M. musculus). We selected the best six encoding schemes and four machine learning algorithms based on a comprehensive test of almost all of the RNA sequence encoding schemes available in the iLearnPlus software package, and selected the optimal features for each encoding scheme using chi-square and incremental feature selection algorithms. Then, we selected the optimal feature combination and the best base-classifier combination for each species through an extensive performance comparison and employed a stacking strategy to build the predictive model.Results: The results demonstrated that PseU-ST achieved better prediction performance compared with other existing models. The PseU-ST accuracy scores were 93.64%, 87.74%, and 89.64% on H_990, S_628, and M_944, respectively, representing increments of 13.94%, 6.05%, and 0.26%, respectively, higher than the best existing methods on the same benchmark training datasets.Conclusion: The data indicate that PseU-ST is a very competitive prediction model for identifying RNA Ψ sites in H. sapiens, M. musculus, and S. cerevisiae. In addition, we found that the Position-specific trinucleotide propensity based on single strand (PSTNPss) and Position-specific of three nucleotides (PS3) features play an important role in Ψ site identification. The source code for PseU-ST and the data are obtainable in our GitHub repository (https://github.com/jluzhangxinrubio/PseU-ST).

show abstract

where TP, TN, FP, and FN represent the true positive, true negative, false positive, and false negative, respectively.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Zhang

Wang²,

Xie³

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

show abstract

“… Zhuang et al (2021) built PseUdeep, an RNA Pseudouridine Site Identification framework with DL Algorithm. PseUdeep outperformed the best traditional ML model available, which was evaluated through 10-fold cross-validation and two independent testing data sets ( Zhuang et al, 2021 ).…”

Section: Methods To Detect Rna Modificationsmentioning

confidence: 99%

“…• PA-PseU (Wang and Zhang, 2021), XG-PseU (Liu et al, 2020d), Aziz et al's model (Aziz et al, 2021, Porpoise (Li et al, 2021a), PseUdeep (Zhuang et al, 2021)…”

Section: Targets Of Rna Modificationmentioning

confidence: 98%

Dynamic regulation and key roles of ribonucleic acid methylation

Zou

Liu

Tan

et al. 2022

Front. Cell. Neurosci.

View full text Add to dashboard Cite

Ribonucleic acid (RNA) methylation is the most abundant modification in biological systems, accounting for 60% of all RNA modifications, and affects multiple aspects of RNA (including mRNAs, tRNAs, rRNAs, microRNAs, and long non-coding RNAs). Dysregulation of RNA methylation causes many developmental diseases through various mechanisms mediated by N6-methyladenosine (m6A), 5-methylcytosine (m5C), N1-methyladenosine (m1A), 5-hydroxymethylcytosine (hm5C), and pseudouridine (Ψ). The emerging tools of RNA methylation can be used as diagnostic, preventive, and therapeutic markers. Here, we review the accumulated discoveries to date regarding the biological function and dynamic regulation of RNA methylation/modification, as well as the most popularly used techniques applied for profiling RNA epitranscriptome, to provide new ideas for growth and development.

show abstract

“…In keeping with the general trend in artificial intelligence (AI), there has been a switch from classical machine learning to deep learning in newly developed RNA modification predictors. For instance, the m 6 A site predictors DeepM6ASeq ( Zhang and Hamada, 2018 ), PM6ACNN ( Alam et al, 2020 ), and DNN-m6A ( Zhang et al, 2021b ); Ψ site predictors iPseU-CNN ( Tahir et al, 2019a ), MU-PseUDeep ( Khan et al, 2020 ), and PseUdeep ( Zhuang et al, 2021 ); 5hmC site predictor iRhm5CNN ( Ali et al, 2021 ); 2’-O-Me site predictors Deep-2’-O-Me ( Mostavi et al, 2018 ), iRNA-PseKNC (2methyl) ( Tahir et al, 2019b ), and DeepOMe ( Li et al, 2021 ); ac4C site predictors DeepAc4C and CNNLSTMac4CPred ( Wang et al, 2021 ; Zhang et al, 2022 ); and a disease-associated m 7 G site predictor HN-CNN ( Zhang et al, 2021a ). A strength of these predictors is that they can learn modification determinants directly from sequencing data, avoiding biased user-defined features.…”

Section: Introductionmentioning

confidence: 99%

Evaluation and development of deep neural networks for RNA 5-Methyluridine classifications using autoBioSeqpy

Zhang

et al. 2023

Front. Microbiol.

View full text Add to dashboard Cite

Post-transcriptionally RNA modifications, also known as the epitranscriptome, play crucial roles in the regulation of gene expression during development. Recently, deep learning (DL) has been employed for RNA modification site prediction and has shown promising results. However, due to the lack of relevant studies, it is unclear which DL architecture is best suited for some pyrimidine modifications, such as 5-methyluridine (m5U). To fill this knowledge gap, we first performed a comparative evaluation of various commonly used DL models for epigenetic studies with the help of autoBioSeqpy. We identified optimal architectural variations for m5U site classification, optimizing the layer depth and neuron width. Second, we used this knowledge to develop Deepm5U, an improved convolutional-recurrent neural network that accurately predicts m5U sites from RNA sequences. We successfully applied Deepm5U to transcriptomewide m5U profiling data across different sequencing technologies and cell types. Third, we showed that the techniques for interpreting deep neural networks, including LayerUMAP and DeepSHAP, can provide important insights into the internal operation and behavior of models. Overall, we offered practical guidance for the development, benchmark, and analysis of deep learning models when designing new algorithms for RNA modifications.

show abstract

PseUdeep: RNA Pseudouridine Site Identification with Deep Learning Algorithm

Cited by 11 publications

References 38 publications

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

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

Dynamic regulation and key roles of ribonucleic acid methylation

Evaluation and development of deep neural networks for RNA 5-Methyluridine classifications using autoBioSeqpy

Contact Info

Product

Resources

About