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

被引:0
作者
Hu, Xi [1 ,2 ,3 ]
Shi, Yuwei [1 ,2 ,3 ]
Cheng, Suk Hang [1 ,2 ,3 ]
Huang, Zhaoyang [4 ,5 ]
Zhou, Ze [1 ,2 ,3 ]
Shi, Xiaoyu [4 ,5 ]
Zhang, Yi [4 ,5 ]
Liu, Jing [1 ,2 ,3 ]
Ma, Mary-Jane L. [1 ,2 ,3 ]
Ding, Spencer C. [1 ,2 ,3 ]
Deng, Jiaen [1 ,2 ,3 ]
Qiao, Rong [1 ,2 ,3 ]
Peng, Wenlei [1 ,2 ,3 ]
Choy, L. Y. Lois [1 ,2 ,3 ,6 ]
Yu, Stephanie C. Y. [1 ,2 ,3 ]
Lam, W. K. Jacky [1 ,2 ,3 ,6 ]
Chan, K. C. Allen [1 ,2 ,3 ,6 ]
Li, Hongsheng [4 ,5 ]
Jiang, Peiyong [1 ,2 ,3 ,6 ]
Lo, Y. M. Dennis [1 ,2 ,3 ,6 ]
机构
[1] Hong Kong Sci Pk, Ctr Novost, Pak Shek Kok, Hong Kong, Peoples R China
[2] Chinese Univ Hong Kong, Li Ka Shing Inst Hlth Sci, Shatin, Hong Kong, Peoples R China
[3] Chinese Univ Hong Kong, Prince Wales Hosp, Dept Chem Pathol, Shatin, Hong Kong, Peoples R China
[4] Chinese Univ Hong Kong, Dept Elect Engn, Shatin, Hong Kong, Peoples R China
[5] Chinese Univ Hong Kong, Multimedia Lab, Shatin, Hong Kong, Peoples R China
[6] Chinese Univ Hong Kong, Prince Wales Hosp, State Key Lab Translat Oncol, Shatin, Hong Kong, Peoples R China
关键词
CELL-FREE DNA; 5-HYDROXYMETHYLCYTOSINE SIGNATURES; 5-METHYLCYTOSINE; METHYLATION;
D O I
10.1038/s42003-025-08009-8
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
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.
引用
收藏
页数:12
相关论文
empty
未找到相关数据