Huang Qianfei, Zhang Jun, Wei Leyi, Guo Fei, Zou Quan
College of Intelligence and Computing, Tianjin University, Tianjin, China.
Rehabilitation Department, Heilongjiang Province Land Reclamation Headquarters General Hospital, Harbin, China.
Front Plant Sci. 2020 Jan 31;11:4. doi: 10.3389/fpls.2020.00004. eCollection 2020.
The biological function of -methyladenine DNA (6mA) in plants is largely unknown. Rice is one of the most important crops worldwide and is a model species for molecular and genetic studies. There are few methods for 6mA site recognition in the rice genome, and an effective computational method is needed.
In this paper, we propose a new computational method called 6mA-Pred to identify 6mA sites in the rice genome. 6mA-Pred employs a feature fusion method to combine advantageous features from other methods and thus obtain a new feature to identify 6mA sites. This method achieved an accuracy of 87.27% in the identification of 6mA sites with 10-fold cross-validation and achieved an accuracy of 85.6% in independent test sets.
植物中N6-甲基腺嘌呤DNA（6mA）的生物学功能在很大程度上尚不清楚。水稻是全球最重要的作物之一，也是分子和遗传研究的模式物种。在水稻基因组中识别6mA位点的方法很少，因此需要一种有效的计算方法。
在本文中，我们提出了一种名为6mA-Pred的新计算方法，用于识别水稻基因组中的6mA位点。6mA-Pred采用特征融合方法，结合其他方法的优势特征，从而获得一种用于识别6mA位点的新特征。该方法在10倍交叉验证中识别6mA位点的准确率达到87.27%，在独立测试集中的准确率达到85.6%。
