Transformer-based deep learning for accurate detection of multiple base modifications using single molecule real-time sequencing.

Journal: Communications biology
PMID:

Abstract

We had previously reported a convolutional neural network (CNN) based approach, called the holistic kinetic model (HK model 1), for detecting 5-methylcytosine (5mC) by single molecule real-time sequencing (Pacific Biosciences). In this study, we constructed a hybrid model with CNN and transformer layers, named HK model 2. We improve the area under the receiver operating characteristic curve (AUC) for 5mC detection from 0.91 for HK model 1 to 0.99 for HK model 2. We further demonstrate that HK model 2 can detect other types of base modifications, such as 5-hydroxymethylcytosine (5hmC) and N6-methyladenine (6mA). Using HK model 2 to analyze 5mC patterns of cell-free DNA (cfDNA) molecules, we demonstrate the enhanced detection of patients with hepatocellular carcinoma, with an AUC of 0.97. Moreover, HK model 2-based detection of 6mA enables the detection of jagged ends of cfDNA and the delineation of cellular chromatin structures. HK model 2 is thus a versatile tool expanding the applications of single molecule real-time sequencing in liquid biopsies.

Authors

  • Xi Hu
  • Yuwei Shi
    Chronic Disease Research Institute, The Children's Hospital, and National Clinical Research Center for Child Health, School of Public Health, School of Medicine, Zhejiang University, No.866 Yu Hang Tang Road, Hangzhou, 310058, Zhejiang, China.
  • Suk Hang Cheng
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Zhaoyang Huang
    School of Computer Science and Technology, Xidian University, Xi'an, 710071, Shaanxi, China.
  • Ze Zhou
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Xiaoyu Shi
    Department of Pathophysiology, Bengbu Medical University, Bengbu, Anhui, China.
  • Yi Zhang
    Department of Thyroid Surgery, China-Japan Union Hospital of Jilin University, Jilin University, Changchun, China.
  • Jing Liu
    Department of Ophthalmology, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China.
  • Mary-Jane L Ma
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Spencer C Ding
    Center for Novostics, Hong Kong Science Park, Pak Shek Kok, New Territories, Hong Kong SAR, China.
  • Jiaen Deng
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Rong Qiao
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Wenlei Peng
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • L Y Lois Choy
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Stephanie C Y Yu
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • W K Jacky Lam
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • K C Allen Chan
    Centre for Novostics, Hong Kong Science Park, Pak Shek Kok, Hong Kong SAR, China.
  • Hongsheng Li
  • Peiyong Jiang
    Center for Novostics, Hong Kong Science Park, Pak Shek Kok, New Territories, Hong Kong SAR, China.
  • Y M Dennis Lo
    Center for Novostics, Hong Kong Science Park, Pak Shek Kok, New Territories, Hong Kong SAR, China; loym@cuhk.edu.hk.