iDNA-ABT: advanced deep learning model for detecting DNA methylation with adaptive features and transductive information maximization.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: DNA methylation plays an important role in epigenetic modification, the occurrence, and the development of diseases. Therefore, identification of DNA methylation sites is critical for better understanding and revealing their functional mechanisms. To date, several machine learning and deep learning methods have been developed for the prediction of different DNA methylation types. However, they still highly rely on manual features, which can largely limit the high-latent information extraction. Moreover, most of them are designed for one specific DNA methylation type, and therefore cannot predict multiple methylation sites in multiple species simultaneously. In this study, we propose iDNA-ABT, an advanced deep learning model that utilizes adaptive embedding based on Bidirectional Encoder Representations from Transformers (BERT) together with transductive information maximization (TIM).

Authors

  • Yingying Yu
    School of Software, Shandong University, Jinan, China.
  • Wenjia He
    School of Software at Shandong University, China.
  • Junru Jin
    School of Software, Shandong University, Jinan, China.
  • Guobao Xiao
    Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University), Fuzhou, China.
  • Lizhen Cui
    School of Software, Shandong University, Jinan, 250101, China.
  • Rao Zeng
    Department of Software Engineering, Xiamen University, Xiamen, China.
  • Leyi Wei
    School of Computer Science and Technology, Tianjin University, Tianjin, 30050, China.