Genome-Wide DNA methylation profiling of tissue-plasma pairs identifies Novel cfDNA biomarkers for the diagnosis of gastric cancer
4 affiliations
- 1The First Affiliated Hospital of Guangxi University of Chinese Medicine, Nanning, Guangxi, China
- 2The Yangtze River Delta Biological Medicine Research and Development Center of Zhejiang Province, Yangtze Delta Region Institution of Tsinghua University, Hangzhou, Zhejiang, China
- 3Department of Gastrointestinal Surgery, Guangxi Medical University Cancer Hospital, Nanning, Guangxi, China
- 4State Key Laboratory of Targeting Oncology, Guangxi Medical University, Nanning, Guangxi, China
Abstract
Screening for gastric cancer (GC) is critical for improving patient survival, yet current clinical methods suffer from invasiveness and limited sensitivity. The aim of this study is to develop a machine learning model for the non-invasive diagnosis of GC using the whole-genome methylation profile of circulating free DNA (cfDNA) in plasma. Plasma cfDNA from 61 patients with GC and 29 healthy controls. First, whole‑genome bisulfite sequencing (WGBS) was performed on 29 paired GC and adjacent normal tissues to identify differentially methylated regions (DMRs). These tissue DMRs were then mapped to plasma cfDNA methylation data, yielding 32 stable DMRs that changed consistently in both tissues and plasma. Using LASSO and Random Forest (RF) algorithms, eight core diagnostic markers were selected. Four machine learning algorithms (Support Vector Machine, RF, K-Nearest Neighbor, Naïve Bayes) were used to build diagnostic models. WGBS revealed global hypomethylation and CpG island hypermethylation in GC, consistent with plasma cfDNA methylation patterns. The RF model built on the eight cfDNA methylation markers (annotated to genes including ATP8A2) performed best, achieving AUC values of 0.978 and 0.938 in the training and independent test sets, respectively, with an accuracy of 88.46%, sensitivity of 94.44%, and specificity of 75.00%. After adjusting for age, the model achieved an AUC of 0.924 on the test set, still demonstrating high discriminatory performance. Functional analysis implicated these markers in pathways such as phagocytosis and axon guidance, and showed significant correlation with immune cell infiltration. Notably, these core DMRs are not covered by the probes on the methylation arrays (450K and EPIC v2), highlighting the advantage of WGBS for novel biomarker discovery. In conclusion, tissue-plasma concordance analysis identified a panel of plasma cfDNA methylation biomarkers with strong diagnostic potential. The resulting RF model provides a promising non-invasive strategy for GC screening. Author summary: In this study, we set out to address the lack of non‑invasive and efficient tools for the detection of gastric cancer. Cancer cells release DNA fragments with specific methylation patterns into the bloodstream. By analyzing plasma samples from patients and healthy individuals, we used machine learning to identify eight key methylation signals from whole‑genome sequencing data. The diagnostic model we built, based on the Random Forest algorithm, performed remarkably well: it distinguished gastric cancer patients from healthy controls with high accuracy in an independent test set, achieving a sensitivity of over 94%. After adjusting for age, the model achieved an AUC of 0.924 on the test set, demonstrating high discriminatory performance. Importantly, the eight methylation markers we identified were overlooked by traditional epigenomic association studies based on microarrays (450K and EPIC v2). This was possible because we employed a technology that captures the entire methylation landscape. Our findings suggest that a simple blood test combined with our machine learning model has the potential to serve as a practical and noninvasive method for screening for gastric cancer. We believe this work brings us one step closer to making precision cancer detection more accessible and less burdensome for patients.
Related
- Integrated DNA methylation and gene expression analysis identifies CpG biomarkers in breast cancer
- Genome-Wide DNA Methylation Sequencing Identifies Methylation-Associated Genes Related to Porcine Skeletal Muscle Fiber Diversity
- Integrated transcriptome and single-cell RNA sequencing identifies transient receptor potential channel-related biomarkers in ulcerative colitis
- High-Throughput Plasma Proteomic Profiling Identifies Novel Biomarker Candidates in Parkinson’s Disease with Cognitive Decline
- Epigenome-Wide DNA Methylation Profiling of Matched Primary Breast Cancers and Brain Metastases Reveals Epigenetic Markers linked to Metastatic Progression: A Preliminary Study.
BibTeX
@article{ou2026genomewide,
title = {{Genome-Wide DNA methylation profiling of tissue-plasma pairs identifies Novel cfDNA biomarkers for the diagnosis of gastric cancer}},
author = {Hailing Ou and Jinli Miao and Fusheng Ling and Jie Gao and Tingan Wang and Zhihua Ye and Chunbo Zhang and Mingwei Huang and Yuzhou Qin},
journal = {PLOS Genetics},
year = {2026},
month = oct,
doi = {10.1371/journal.pgen.1012322},
url = {https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1012322},
note = {CC BY},
}
RIS
TY - JOUR
TI - Genome-Wide DNA methylation profiling of tissue-plasma pairs identifies Novel cfDNA biomarkers for the diagnosis of gastric cancer
AU - Hailing Ou
AU - Jinli Miao
AU - Fusheng Ling
AU - Jie Gao
AU - Tingan Wang
AU - Zhihua Ye
AU - Chunbo Zhang
AU - Mingwei Huang
AU - Yuzhou Qin
PY - 2026
DA - 2026/10/01
JO - PLOS Genetics
DO - 10.1371/journal.pgen.1012322
UR - https://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1012322
AB - Screening for gastric cancer (GC) is critical for improving patient survival, yet current clinical methods suffer from invasiveness and limited sensitivity. The aim of this study is to develop a machine learning model for the non-invasive diagnosis of GC using the whole-genome methylation profile of circulating free DNA (cfDNA) in plasma. Plasma cfDNA from 61 patients with GC and 29 healthy controls. First, whole‑genome bisulfite sequencing (WGBS) was performed on 29 paired GC and adjacent normal tissues to identify differentially methylated regions (DMRs). These tissue DMRs were then mapped to plasma cfDNA methylation data, yielding 32 stable DMRs that changed consistently in both tissues and plasma. Using LASSO and Random Forest (RF) algorithms, eight core diagnostic markers were selected. Four machine learning algorithms (Support Vector Machine, RF, K-Nearest Neighbor, Naïve Bayes) were used to build diagnostic models. WGBS revealed global hypomethylation and CpG island hypermethylation in GC, consistent with plasma cfDNA methylation patterns. The RF model built on the eight cfDNA methylation markers (annotated to genes including ATP8A2) performed best, achieving AUC values of 0.978 and 0.938 in the training and independent test sets, respectively, with an accuracy of 88.46%, sensitivity of 94.44%, and specificity of 75.00%. After adjusting for age, the model achieved an AUC of 0.924 on the test set, still demonstrating high discriminatory performance. Functional analysis implicated these markers in pathways such as phagocytosis and axon guidance, and showed significant correlation with immune cell infiltration. Notably, these core DMRs are not covered by the probes on the methylation arrays (450K and EPIC v2), highlighting the advantage of WGBS for novel biomarker discovery. In conclusion, tissue-plasma concordance analysis identified a panel of plasma cfDNA methylation biomarkers with strong diagnostic potential. The resulting RF model provides a promising non-invasive strategy for GC screening. Author summary: In this study, we set out to address the lack of non‑invasive and efficient tools for the detection of gastric cancer. Cancer cells release DNA fragments with specific methylation patterns into the bloodstream. By analyzing plasma samples from patients and healthy individuals, we used machine learning to identify eight key methylation signals from whole‑genome sequencing data. The diagnostic model we built, based on the Random Forest algorithm, performed remarkably well: it distinguished gastric cancer patients from healthy controls with high accuracy in an independent test set, achieving a sensitivity of over 94%. After adjusting for age, the model achieved an AUC of 0.924 on the test set, demonstrating high discriminatory performance. Importantly, the eight methylation markers we identified were overlooked by traditional epigenomic association studies based on microarrays (450K and EPIC v2). This was possible because we employed a technology that captures the entire methylation landscape. Our findings suggest that a simple blood test combined with our machine learning model has the potential to serve as a practical and noninvasive method for screening for gastric cancer. We believe this work brings us one step closer to making precision cancer detection more accessible and less burdensome for patients.
SN - 1553-7404
SN - 1553-7390
ER -