Key Laboratory of Ministry of Education for Gastrointestinal Cancer, School of Basic Medical Sciences, Fujian Medical University, Fuzhou 350004, China.
Department of Molecular, Cell, and Developmental Biology, University of California, Santa Cruz, Santa Cruz, CA 95064, USA.
Genes (Basel). 2022 Apr 12;13(4):677. doi: 10.3390/genes13040677.
5-methylcytosine (m5C) is a common post-transcriptional modification observed in a variety of RNAs. m5C has been demonstrated to be important in a variety of biological processes, including RNA structural stability and metabolism. Driven by the importance of m5C modification, many projects focused on the m5C sites prediction were reported before. To better understand the upstream and downstream regulation of m5C, we present a bioinformatics framework, m5CRegpred, to predict the substrate of m5C writer NSUN2 and m5C readers YBX1 and ALYREF for the first time. After features comparison, window lengths selection and algorism comparison on the mature mRNA model, our model achieved AUROC scores 0.869, 0.724 and 0.889 for NSUN2, YBX1 and ALYREF, respectively in an independent test. Our work suggests the substrate of m5C regulators can be distinguished and may help the research of m5C regulators in a special condition, such as substrates prediction of hyper- or hypo-expressed m5C regulators in human disease.
5- 甲基胞嘧啶（m5C）是在多种 RNA 中观察到的一种常见的转录后修饰。m5C 已被证明在多种生物学过程中很重要，包括 RNA 结构稳定性和代谢。由于 m5C 修饰的重要性，之前已经有许多项目专注于 m5C 位点的预测。为了更好地理解 m5C 的上游和下游调控，我们提出了一个生物信息学框架 m5CRegpred，首次预测 m5C 写入器 NSUN2 和 m5C 读取器 YBX1 和 ALYREF 的底物。在成熟 mRNA 模型上进行特征比较、窗口长度选择和算法比较后，我们的模型在独立测试中分别为 NSUN2、YBX1 和 ALYREF 实现了 0.869、0.724 和 0.889 的 AUROC 评分。我们的工作表明 m5C 调节剂的底物可以区分，并且可能有助于在特殊条件下研究 m5C 调节剂，例如在人类疾病中高表达或低表达 m5C 调节剂的底物预测。
