m7GPredictor: An improved machine learning-based model for predicting internal m7G modifications using sequence properties

Li, Xudong; Liu, Ze; Mao, Xiuli; Li, Quanwu

doi:10.1016/j.ab.2020.113905

Cited by 22 publications

(15 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It used SVM and m7GFinder [66] , a feature extraction approach based on likelihood ratio (LR), reaching an accuracy of 76% on an independent dataset obtained using three approaches (m7G-Seq, m7G-MeRIP-Seq, and m7G-miCLIP-Seq) [67] . m7GPredictor [68] is another SVM based approach that combined NP, K-mer, PseDNC, Ksnpf, and PseKNC features to reach an accuracy of 86%. XG-m7G [29] is a technique that uses the XGboost algorithm along with multiple features (ND, NCP, ENAC, CKSNAP), followed by SHAP (Shapley additive interpretations) to predict the modification sites.…”

Section: Machine Learning Approaches For Rna Modification Sites Predictionmentioning

confidence: 99%

“… Predictor ML- Algorithm Features Testing NS WS Sn Sp ACC ROC Link iRNA-m7G [12] SVM NPF,SSC, PseDNC 10-fold cross validation 1482 41 bp 88.66% 90.96% 89.81% 94.6% http://lin-group.cn/server/iRNA-m7G/ XG-m7G [29] XGBoost CKS-P, E-C, NCP,ND 10-fold cross validation 1482 41 bp 91.48% 90.96% 91.22% 97.2% - m7g model [66] SVM One hot, NCP, NC, k-mer, PseKNC 10-fold cross validation 1482 41 bp 95.11% 93.74% 94.67% 98.2% https://github.com/MapFM/m7g_model m7GHub [27] SVM Sequence and genome derived features. Independent test - 30 bp 84.20% 71.00% 76.00% 85.5% - m7GPredictor [68] SVM NP, K-mer, PseDNC, Ksnpf, PseKNC Independent test 300 50 bp 84.00% 88.00% 86.00% 93.3% https://github.com/NWAFU-LiuLab/m7Gpredictor …”

Section: Machine Learning Approaches For Rna Modification Sites Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning applications in RNA modification sites prediction

Allali¹,

Elhamraoui²,

Daoud³

2021

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

show abstract

Section: Machine Learning Approaches For Rna Modification Sites Predictionmentioning

confidence: 99%

Section: Machine Learning Approaches For Rna Modification Sites Predictionmentioning

confidence: 99%

Machine learning applications in RNA modification sites prediction

Allali¹,

Elhamraoui²,

Daoud³

2021

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, computational methods have been proposed as alternative approaches. A series of bioinformatics tools using machine learning algorithms for predicting m6A ( Wei Chen et al, 2015 ; Zhou et al, 2016 ; Huang et al, 2018 ; Kunqi Chen et al, 2019 ; Zou et al, 2019 ), m5C ( Qiu et al, 2017 ; Sabooh et al, 2018 ; Akbar et al, 2020 ; Dou et al, 2020 ), m7G ( Wei Chen et al, 2019 , 7; Liu X. et al, 2020 ; Yang et al, 2020 ; Dai et al, 2021 ), and many others have been developed. A recent review article has elaborated on the differences between these studies, in the aspect of benchmarking datasets, feature encoding schemes, and the main algorithms ( Chen et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

i5hmCVec: Identifying 5-Hydroxymethylcytosine Sites of Drosophila RNA Using Sequence Feature Embeddings

Liu

2022

Front. Genet.

View full text Add to dashboard Cite

5-Hydroxymethylcytosine (5hmC), one of the most important RNA modifications, plays an important role in many biological processes. Accurately identifying RNA modification sites helps understand the function of RNA modification. In this work, we propose a computational method for identifying 5hmC-modified regions using machine learning algorithms. We applied a sequence feature embedding method based on the dna2vec algorithm to represent the RNA sequence. The results showed that the performance of our model is better that of than state-of-art methods. All dataset and source codes used in this study are available at: https://github.com/liu-h-y/5hmC_model.

show abstract

“…According to Zhao et al, the internal mRNA m7G methyltransferase METTL1, and not WDR4, is a key responder to post-ischemic insults, resulting in a global reduction in m7G methylation inside mRNA [8]. In addition, Liu et al introduced m7GPredictor for predicting internal m7G modification sites using sequence properties [9]. In this model, the authors used various numerical descriptor methods and a random forest was used for the selection of optimal feature sets.…”

Section: Introductionmentioning

confidence: 99%

An Effective Deep Learning-Based Architecture for Prediction of N7-Methylguanosine Sites in Health Systems

et al. 2022

View full text Add to dashboard Cite

N7-methylguanosine (m7G) is one of the most important epigenetic modifications found in rRNA, mRNA, and tRNA, and performs a promising role in gene expression regulation. Owing to its significance, well-equipped traditional laboratory-based techniques have been performed for the identification of N7-methylguanosine (m7G). Consequently, these approaches were found to be time-consuming and cost-ineffective. To move on from these traditional approaches to predict N7-methylguanosine sites with high precision, the concept of artificial intelligence has been adopted. In this study, an intelligent computational model called N7-methylguanosine-Long short-term memory (m7G-LSTM) is introduced for the prediction of N7-methylguanosine sites. One-hot encoding and word2vec feature schemes are used to express the biological sequences while the LSTM and CNN algorithms have been employed for classification. The proposed “m7G-LSTM” model obtained an accuracy value of 95.95%, a specificity value of 95.94%, a sensitivity value of 95.97%, and Matthew’s correlation coefficient (MCC) value of 0.919. The proposed predictive m7G-LSTM model has significantly achieved better outcomes than previous models in terms of all evaluation parameters. The proposed m7G-LSTM computational system aims to support the drug industry and help researchers in the fields of bioinformatics to enhance innovation for the prediction of the behavior of N7-methylguanosine sites.

show abstract

m7GPredictor: An improved machine learning-based model for predicting internal m7G modifications using sequence properties

Cited by 22 publications

References 32 publications

Machine learning applications in RNA modification sites prediction

Machine learning applications in RNA modification sites prediction

i5hmCVec: Identifying 5-Hydroxymethylcytosine Sites of Drosophila RNA Using Sequence Feature Embeddings

An Effective Deep Learning-Based Architecture for Prediction of N7-Methylguanosine Sites in Health Systems

Contact Info

Product

Resources

About