Affordable Access

Access to the full text

MRCNN: a deep learning model for regression of genome-wide DNA methylation

  • Tian, Qi1
  • Zou, Jianxiao1
  • Tang, Jianxiong1
  • Fang, Yuan1
  • Yu, Zhongli1
  • Fan, Shicai1, 2
  • 1 University of Electronic Science and Technology of China, School of Automation Engineering, Chengdu, Sichuan, China , Chengdu (China)
  • 2 University of Electronic Science and Technology of China, Center for Informational Biology, Chengdu, Sichuan, China , Chengdu (China)
Published Article
BMC Genomics
Springer (Biomed Central Ltd.)
Publication Date
Apr 04, 2019
Suppl 2
DOI: 10.1186/s12864-019-5488-5
Springer Nature


BackgroundDetermination of genome-wide DNA methylation is significant for both basic research and drug development. As a key epigenetic modification, this biochemical process can modulate gene expression to influence the cell differentiation which can possibly lead to cancer. Due to the involuted biochemical mechanism of DNA methylation, obtaining a precise prediction is a considerably tough challenge. Existing approaches have yielded good predictions, but the methods either need to combine plenty of features and prerequisites or deal with only hypermethylation and hypomethylation.ResultsIn this paper, we propose a deep learning method for prediction of the genome-wide DNA methylation, in which the Methylation Regression is implemented by Convolutional Neural Networks (MRCNN). Through minimizing the continuous loss function, experiments show that our model is convergent and more precise than the state-of-art method (DeepCpG) according to results of the evaluation. MRCNN also achieves the discovery of de novo motifs by analysis of features from the training process.ConclusionsGenome-wide DNA methylation could be evaluated based on the corresponding local DNA sequences of target CpG loci. With the autonomous learning pattern of deep learning, MRCNN enables accurate predictions of genome-wide DNA methylation status without predefined features and discovers some de novo methylation-related motifs that match known motifs by extracting sequence patterns.

Report this publication


Seen <100 times