El Allali A, Elhamraoui Zahra, Daoud Rachid
African Genome Center, University Mohamed VI Polytechnic, Morocco.
Comput Struct Biotechnol J. 2021 Sep 29;19:5510-5524. doi: 10.1016/j.csbj.2021.09.025. eCollection 2021.
Ribonucleic acid (RNA) modifications are post-transcriptional chemical composition changes that have a fundamental role in regulating the main aspect of RNA function. Recently, large datasets have become available thanks to the recent development in deep sequencing and large-scale profiling. This availability of transcriptomic datasets has led to increased use of machine learning based approaches in epitranscriptomics, particularly in identifying RNA modifications. In this review, we comprehensively explore machine learning based approaches used for the prediction of 11 RNA modification types, namely, , , , , , , , , , , and . This review covers the life cycle of machine learning methods to predict RNA modification sites including available benchmark datasets, feature extraction, and classification algorithms. We compare available methods in terms of datasets, target species, approach, and accuracy for each RNA modification type. Finally, we discuss the advantages and limitations of the reviewed approaches and suggest future perspectives.
核糖核酸（RNA）修饰是转录后的化学成分变化，在调节RNA功能的主要方面起着基础性作用。近来，由于深度测序和大规模分析技术的最新发展，大量数据集得以获取。这些转录组数据集的可得性使得基于机器学习的方法在表观转录组学中的应用日益增加，特别是在识别RNA修饰方面。在本综述中，我们全面探讨了用于预测11种RNA修饰类型的基于机器学习的方法，即 、 、 、 、 、 、 、 、 、 、 和 。本综述涵盖了预测RNA修饰位点的机器学习方法的生命周期，包括可用的基准数据集、特征提取和分类算法。我们针对每种RNA修饰类型，在数据集、目标物种、方法和准确性方面比较了现有方法。最后，我们讨论了所综述方法的优点和局限性，并提出了未来展望。
