Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k -mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k -mer co-occurrence information with recent advances in deep learning.

Authors

  • Xu Min
  • Wanwen Zeng
    MOE Key Laboratory of Bioinformatics and Bioinformatics Division, TNLIST, Tsinghua University, Beijing, China.
  • Ning Chen
    Department of General Surgery, Peking University Third Hospital, Beijing, P. R. China.
  • Ting Chen
    CAS Key Laboratory of Tropical Marine Bio-resources and Ecology (LMB), Guangdong Provincial Key Laboratory of Applied Marine Biology (LAMB), South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China. chan1010@scsio.ac.cn.
  • Rui Jiang
    Department of Urology, The Affiliated Hospital of Southwest Medical University, Luzhou, China.