BACKGROUND An increasing number of nucleic acid modifications have been profiled with the development of sequencing technologies. DNA N6-methyladenine (6mA), which is a prevalent epigenetic modification, plays important roles in a series of biological processes. So far, identification of DNA 6mA relies primarily on time-consuming and expensive experimental approaches. However, in silico methods can be implemented to conduct preliminary screening to save experimental resources and time, especially given the rapid accumulation of sequencing data. RESULTS In this study, we constructed a 6mA predictor, p6mA, from a series of sequence-based features, including physicochemical properties, position-specific triple-nucleotide propensity (PSTNP), and electron-ion interaction pseudopotential (EIIP). We performed maximum relevance maximum distance (MRMD) analysis to select key features and used the Extreme Gradient Boosting (XGBoost) algorithm to build our predictor. Results demonstrated that p6mA outperformed other existing predictors using different datasets. CONCLUSIONS p6mA can predict the methylation status of DNA adenines, using only sequence files. It may be used as a tool to help the study of 6mA distribution pattern. Users can download it from https://github.com/Konglab404/p6mA.

中文翻译：

---

通过整合序列特征鉴定DNA N6-甲基腺嘌呤位点。

背景技术随着测序技术的发展，已经描述了越来越多的核酸修饰。DNA N6-甲基腺嘌呤（6mA）是一种普遍的表观遗传修饰，在一系列生物学过程中起着重要作用。到目前为止，DNA 6mA的鉴定主要依靠耗时且昂贵的实验方法。但是，可以采用计算机方法进行初步筛选，以节省实验资源和时间，尤其是在快速积累测序数据的情况下。结果在本研究中，我们从一系列基于序列的特征中构建了6mA预测子p6mA，包括理化特性，位置特异性三核苷酸倾向（PSTNP）和电子离子相互作用假电位（EIIP）。我们执行了最大相关性最大距离（MRMD）分析以选择关键特征，并使用极限梯度增强（XGBoost）算法来构建预测变量。结果表明，使用不同的数据集，p6mA优于其他现有预测指标。结论p6mA可以仅使用序列文件来预测DNA腺嘌呤的甲基化状态。它可以用作帮助研究6mA分布模式的工具。用户可以从https://github.com/Konglab404/p6mA下载。它可以用作帮助研究6mA分布模式的工具。用户可以从https://github.com/Konglab404/p6mA下载。它可以用作帮助研究6mA分布模式的工具。用户可以从https://github.com/Konglab404/p6mA下载。