期刊
METHODS
卷 204, 期 -, 页码 14-21出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.ymeth.2022.02.001
关键词
Deep learning; DNA N6-methyladenine; Convolution neural network; Graph neural network
资金
- National Natural Science Foundation of China [62072223]
- Natural Science Foundation of Fujian Province [2020J01131199]
In this study, a neural network-based bioinformatics model, GC6mA-Pred, is proposed to predict N6-methyladenine modifications in DNA sequences. The model extracts information from both sequence and graph levels and shows better performance on a newly built dataset.
Motivation: DNA N6-methyladenine (6mA) is a pivotal DNA modification for various biological processes. More accurate prediction of 6mA methylation sites plays an irreplaceable part in grasping the internal rationale of related biological activities. However, the existing prediction methods only extract information from a single dimension, which has some limitations. Therefore, it is very necessary to obtain the information of 6mA sites from different dimensions, so as to establish a reliable prediction method. Results: In this study, a neural network based bioinformatics model named GC6mA-Pred is proposed to predict N6-methyladenine modifications in DNA sequences. GC6mA-Pred extracts significant information from both sequence level and graph level. In the sequence level, GC6mA-Pred uses a three-layer convolution neural network (CNN) model to represent the sequence. In the graph level, GC6mA-Pred employs graph neural network (GNN) method to integrate various information contained in the chemical molecular formula corresponding to DNA sequence. In our newly built dataset, GC6mA-Pred shows better performance than other existing models. The results of comparative experiments have illustrated that GC6mA-Pred is capable of producing a marked effect in accurately identifying DNA 6mA modifications.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据