Cargando…

DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads

Detecting cancer signals in cell-free DNA (cfDNA) high-throughput sequencing data is emerging as a novel noninvasive cancer detection method. Due to the high cost of sequencing, it is crucial to make robust and precise predictions with low-depth cfDNA sequencing data. Here we propose a novel approac...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Jiaqi, Wei, Lei, Zhang, Xianglin, Zhang, Wei, Wang, Haochen, Zhong, Bixi, Xie, Zhen, Lv, Hairong, Wang, Xiaowo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8575022/
https://www.ncbi.nlm.nih.gov/pubmed/34245239
http://dx.doi.org/10.1093/bib/bbab250
_version_ 1784595603314966528
author Li, Jiaqi
Wei, Lei
Zhang, Xianglin
Zhang, Wei
Wang, Haochen
Zhong, Bixi
Xie, Zhen
Lv, Hairong
Wang, Xiaowo
author_facet Li, Jiaqi
Wei, Lei
Zhang, Xianglin
Zhang, Wei
Wang, Haochen
Zhong, Bixi
Xie, Zhen
Lv, Hairong
Wang, Xiaowo
author_sort Li, Jiaqi
collection PubMed
description Detecting cancer signals in cell-free DNA (cfDNA) high-throughput sequencing data is emerging as a novel noninvasive cancer detection method. Due to the high cost of sequencing, it is crucial to make robust and precise predictions with low-depth cfDNA sequencing data. Here we propose a novel approach named DISMIR, which can provide ultrasensitive and robust cancer detection by integrating DNA sequence and methylation information in plasma cfDNA whole-genome bisulfite sequencing (WGBS) data. DISMIR introduces a new feature termed as ‘switching region’ to define cancer-specific differentially methylated regions, which can enrich the cancer-related signal at read-resolution. DISMIR applies a deep learning model to predict the source of every single read based on its DNA sequence and methylation state and then predicts the risk that the plasma donor is suffering from cancer. DISMIR exhibited high accuracy and robustness on hepatocellular carcinoma detection by plasma cfDNA WGBS data even at ultralow sequencing depths. Further analysis showed that DISMIR tends to be insensitive to alterations of single CpG sites’ methylation states, which suggests DISMIR could resist to technical noise of WGBS. All these results showed DISMIR with the potential to be a precise and robust method for low-cost early cancer detection.
format Online
Article
Text
id pubmed-8575022
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-85750222021-11-09 DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads Li, Jiaqi Wei, Lei Zhang, Xianglin Zhang, Wei Wang, Haochen Zhong, Bixi Xie, Zhen Lv, Hairong Wang, Xiaowo Brief Bioinform Problem Solving Protocol Detecting cancer signals in cell-free DNA (cfDNA) high-throughput sequencing data is emerging as a novel noninvasive cancer detection method. Due to the high cost of sequencing, it is crucial to make robust and precise predictions with low-depth cfDNA sequencing data. Here we propose a novel approach named DISMIR, which can provide ultrasensitive and robust cancer detection by integrating DNA sequence and methylation information in plasma cfDNA whole-genome bisulfite sequencing (WGBS) data. DISMIR introduces a new feature termed as ‘switching region’ to define cancer-specific differentially methylated regions, which can enrich the cancer-related signal at read-resolution. DISMIR applies a deep learning model to predict the source of every single read based on its DNA sequence and methylation state and then predicts the risk that the plasma donor is suffering from cancer. DISMIR exhibited high accuracy and robustness on hepatocellular carcinoma detection by plasma cfDNA WGBS data even at ultralow sequencing depths. Further analysis showed that DISMIR tends to be insensitive to alterations of single CpG sites’ methylation states, which suggests DISMIR could resist to technical noise of WGBS. All these results showed DISMIR with the potential to be a precise and robust method for low-cost early cancer detection. Oxford University Press 2021-07-09 /pmc/articles/PMC8575022/ /pubmed/34245239 http://dx.doi.org/10.1093/bib/bbab250 Text en © The Author(s) 2021. Published by Oxford University Press. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Problem Solving Protocol
Li, Jiaqi
Wei, Lei
Zhang, Xianglin
Zhang, Wei
Wang, Haochen
Zhong, Bixi
Xie, Zhen
Lv, Hairong
Wang, Xiaowo
DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title_full DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title_fullStr DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title_full_unstemmed DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title_short DISMIR: Deep learning-based noninvasive cancer detection by integrating DNA sequence and methylation information of individual cell-free DNA reads
title_sort dismir: deep learning-based noninvasive cancer detection by integrating dna sequence and methylation information of individual cell-free dna reads
topic Problem Solving Protocol
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8575022/
https://www.ncbi.nlm.nih.gov/pubmed/34245239
http://dx.doi.org/10.1093/bib/bbab250
work_keys_str_mv AT lijiaqi dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT weilei dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT zhangxianglin dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT zhangwei dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT wanghaochen dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT zhongbixi dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT xiezhen dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT lvhairong dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads
AT wangxiaowo dismirdeeplearningbasednoninvasivecancerdetectionbyintegratingdnasequenceandmethylationinformationofindividualcellfreednareads