|
|
基于机器学习的RNA甲基化修饰位点预测的研究进展
|
Abstract:
RNA修饰，特别是RNA甲基化，在人类多种生物活动中起着非常重要的调控作用，最常见的修饰包括N6-腺苷酸甲基化(m6A)、N1-腺苷酸甲基化(m1A)、胞嘧啶羟基化(m5C)等。RNA甲基化修饰位点的准确识别对预测多种人类遗传学疾病以及药物研发发挥着关键作用。随着数据集的大量积累，序列数据的分析需求不断增多，一些基于机器学习的预测方法被开发出来，用于甲基化位点的识别。本工作分别从RNA修饰、数据集来源、预测结果的评估标准以及用于预测的算法模型优缺点等方面进行综述，最后指出了RNA甲基化修饰位点预测未来的研究方向。
RNA modification, especially RNA methylation, plays a very important regulatory role in a variety of human biological activities. The most common modifications include N6-adenylate methylation (m6A), N1-adenylate methylation (m1A), cytosine hydroxylation (m5C), etc. Accurate identification of RNA methylation modification sites is crucial for predicting a variety of human genetic diseases and drug development. With the accumulation of a large number of data sets, the requirements of analyzing sequence data are increasing, and some prediction methods based on machine learning have been developed for the identification of methylation sites. This work reviews RNA modification, data set sources, evaluation criteria for prediction results, and advantages and disadvantages of algorithm models used for prediction, and finally presents the research direction of RNA methylation modification site prediction in the future.
| [1] | Meyer, K.D. and Jaffrey, S.R. (2014) The Dynamic Epitranscriptome: N6-methyladenosine and Gene Expression Con-trol. Nature Reviews Molecular Cell Biology, 15, 313-326. https://doi.org/10.1038/nrm3785 |
| [2] | Djebali, S., Davis, C.A., Merkel, A., et al. (2012) Landscape of Transcription in Human Cells. Nature, 489, 101-108.
https://doi.org/10.1038/nature11233 |
| [3] | Hauenschild, R., Tserovski, L., Schmid, K., Thüring, K., Winz, M.L., Sharma, S., Entian, K.D., Wacheul, L., Lafontaine, D.L. anderson, J., Alfonzo, J., Hildebrandt, A., J？schke, A., Motorin, Y. and Helm, M. (2015) The Reverse Transcription Signature of N-1-methyladenosine in RNA-Seq Is Sequence De-pendent. Nucleic Acids Research, 43, 9950-9964. https://doi.org/10.1093/nar/gkv895 |
| [4] | Bohnsack, K.E., H？bartner, C. and Bohnsack, M.T. (2019) Eukaryotic 5-methylcytosine (m5C) RNA Methyltransferases: Mechanisms, Cellular Functions, and Links to Disease. Genes, 10, 102. https://doi.org/10.3390/genes10020102 |
| [5] | Barrett, T., Wilhite, S.E., Ledoux, P., Evangelista, C., Kim, I.F., Tomashevsky, M., Marshall, K.A., Phillippy, K.H., Sherman, P.M., Holko, M., Yefanov, A., Lee, H., Zhang, N., Robertson, C.L., Serova, N., Davis, S. and Soboleva, A. (2013) NCBIGEO: Archive for Functional Genomics Data Sets—Update. Nucleic Acids Research, 41, D991-D995.
https://doi.org/10.1093/nar/gks1193 |
| [6] | Xuan, J.J., Sun, W.J., Lin, P.H., Zhou, K.R., Liu, S., Zheng, L.L., Qu, L.H. and Yang, J.H. (2018) RMBase v2.0: Deciphering the Map of RNA Modifications from Epitranscriptome Se-quencing Data. Nucleic Acids Research, 46, D327-D334. https://doi.org/10.1093/nar/gkx934 |
| [7] | Chen, W., Feng, P., Ding, H., Lin, H. and Chou, K.C. (2015) iRNA-Methyl: Identifying n6-methyladenosine Sites Using Pseudo Nucleo-tide Composition. Analytical Biochemistry, 490, 26-33. https://doi.org/10.1016/j.ab.2015.08.021 |
| [8] | Zhou, Y., Zeng, P., Li, Y.H., et al. (2016) SRAMP: Prediction of Mammalian N6-methyladenosine (m6A) Sites Based on Se-quence-Derived Features. Nucleic Acids Research, 44, e91. https://doi.org/10.1093/nar/gkw104 |
| [9] | Qiang, X., Chen, H., Ye, X., et al. (2018) M6AMRFS: Robust Prediction of N6-methyladenosine Sites with Sequence-Based Fea-tures in Multiple Species. Frontiers in Genetics, 9, Article No. 495.
https://doi.org/10.3389/fgene.2018.00495 |
| [10] | Nazari, I., Tahir, M., Tayara, H., et al. (2019) iN6-Methyl (5-Step): Identifying RNA N6-methyladenosine Sites Using Deep Learning Mode via Chou’s 5-Step Rules and Chou’s General PseKNC. Chemometrics and Intelligent Laboratory Systems, 193, Article ID: 103811. https://doi.org/10.1016/j.chemolab.2019.103811 |
| [11] | Alam, W., Ali, S.D., Tayara, H., et al. (2020) A CNN-Based RNA N6-methyladenosine Site Predictor for Multiple Species Using Heterogeneous Features Representation. IEEE Ac-cess, 8, 138203-138209.
https://doi.org/10.1109/ACCESS.2020.3002995 |
| [12] | Rehman, M.U., Hong, K.J., Tayara, H., et al. (2021) m6A-NeuralTool: Convolution Neural Tool for RNA N6-Methy- ladenosine Site Identification in Different Species. IEEE Access, 9, 17779-17786.
https://doi.org/10.1109/ACCESS.2021.3054361 |
| [13] | Feng, P., Ding, H., Chen, W., et al. (2016) Identifying RNA 5-methylcytosine Sites via Pseudo Nucleotide Compositions. Molecular BioSystems, 12, 3307-3311. https://doi.org/10.1039/C6MB00471G |
| [14] | Qiu, W.R., Jiang, S.Y., Xu, Z.C., et al. (2017) iRNAm5C-PseDNC: Identifying RNA 5-methylcytosine Sites by Incorporating Physical-Chemical Properties into Pseudo Dinucleotide Com-position. Oncotarget, 8, 41178-41188.
https://doi.org/10.18632/oncotarget.17104 |
| [15] | Chen, Z., Zhao, P., Li, F., et al. (2020) iLearn: An Integrated Plat-form and Meta-Learner for Feature Engineering, Machine-Learning Analysis and Modeling of DNA, RNA and Protein Sequence Data. Briefings in Bioinformatics, 21, 1047-1057. https://doi.org/10.1093/bib/bbz041 |
| [16] | Fang, T., Zhang, Z., Sun, R., et al. (2019) RNAm5CPred: Prediction of RNA 5-methylcytosine Sites Based on Three Different Kinds of Nucleotide Composition. Molecular Therapy-Nucleic Acids, 18, 739-747.
https://doi.org/10.1016/j.omtn.2019.10.008 |
| [17] | Chen, W., Feng, P., Tang, H., et al. (2016) RAMPred: Identifying the N1-methyladenosine Sites in Eukaryotic Transcriptomes. Scientific Reports, 6, Article No. 31080. https://doi.org/10.1038/srep31080 |
| [18] | Liu, L., Lei, X., Meng, J., et al. (2020) ISGm1A: Integration of Sequence Features and Genomic Features to Improve the Prediction of Human m1A RNA Methylation Sites. IEEE Access, 8, 81971-81977.
https://doi.org/10.1109/ACCESS.2020.2991070 |
