Early diagnosis and molecular classification of gastric cancer peritoneal metastasis by deep learning-driven single-cell lipidomics
7 affiliations
- 1Department of Chemistry, Tsinghua University, Beijing 100084, China
- 2Department of Surgical Oncology and General Surgery, The First Affiliated Hospital of China Medical University, Shenyang 110001, China
- 3Key Laboratory of Precision Diagnosis and Treatment of Gastrointestinal Tumors, Ministry of Education, China Medical University, Shenyang 110001, China
- 4Institute of Health Sciences, China Medical University, Shenyang 110001, China
- 5Department of Pathology, College of Basic Medical Sciences, China Medical University, Shenyang 110122, China
- 6Department of Pathology, The First Hospital of China Medical University, Shenyang 110001, China
- 7Division of Chemical Metrology and Analytical Science, National Institute of Metrology, Beijing 100029, China
Abstract
Peritoneal metastasis is the most lethal manifestation of gastric cancer (GC), as conventional diagnostic methods cannot reliably detect occult free GC cells in the peritoneal cavity at an early stage. Here, we present a workflow for early detection and molecular classification of free GC cells using label-free metabolite-based mass cytometry for single-cell lipidomic profiling integrated with deep learning. We obtain 41,627 single-cell lipidomic profiles from 92 samples in total and identify a distinct lipidomic fingerprint that robustly discriminates between free GC cells and benign peritoneal cells. To further interpret complex lipidomic profiles, we develop a deep learning-based graph neural network classifier to identify rare free GC cells within peritoneal ecosystem. Beyond diagnostic discrimination, we propose a clinically relevant metabolic classification based on HER2 subtype-specific lipidomic heterogeneity. Our study advances the early diagnosis and molecular classification of peritoneal metastasis in GC, offering potential for metabolism-guided intervention.
Related
- Single-cell transcriptomic analysis reveals seed cells and microenvironmental crosstalk in gastric cancer peritoneal metastasis
- Association of gut Fusobacteria abundance with peritoneal metastasis in gastric signet-ring cell carcinoma: a cross-sectional study.
- TAMs-derived exosomal PD-L1 drives mitochondrial dysfunction and aberrant fatty acid oxidation via PGC-1α/PPARα axis to promote peritoneal metastasis in epithelial ovarian cancer
- S-HPABA, a marine fungal-derived bioactive compound, exhibits potent lipid-lowering efficacy and safety in modulating lipid dysregulation revealed by integrative lipidomics and molecular biology approaches.
- Exercise Training, Lipoprotein Subfractions, and Molecular Lipidomics: Mechanistic Insights into Atherogenic Risk Phenotypes—A Structured Narrative Review
BibTeX
@article{pan2026early,
title = {{Early diagnosis and molecular classification of gastric cancer peritoneal metastasis by deep learning-driven single-cell lipidomics}},
author = {Siyuan Pan and Xiaowan Chen and Wen Xu and Jiale Chen and Kexin Xu and Peng Gao and Yuan Li and Jinming Zhao and Jinlei Yang and Murong Du and Runsong Cheng and Jingya Cao and Jiayi Li and Xinyu Zhao and Tong Qiao and Tianzi Chen and Xuan Li and Chunyu Lu and Siqi Xiong and Huan Yao and Xuanzhang Huang and Sichun Zhang and Xinrong Zhang and Zhenning Wang},
journal = {Cell Reports Medicine},
year = {2026},
month = sep,
doi = {10.1016/j.xcrm.2026.103055},
url = {https://doi.org/10.1016/j.xcrm.2026.103055},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Early diagnosis and molecular classification of gastric cancer peritoneal metastasis by deep learning-driven single-cell lipidomics
AU - Siyuan Pan
AU - Xiaowan Chen
AU - Wen Xu
AU - Jiale Chen
AU - Kexin Xu
AU - Peng Gao
AU - Yuan Li
AU - Jinming Zhao
AU - Jinlei Yang
AU - Murong Du
AU - Runsong Cheng
AU - Jingya Cao
AU - Jiayi Li
AU - Xinyu Zhao
AU - Tong Qiao
AU - Tianzi Chen
AU - Xuan Li
AU - Chunyu Lu
AU - Siqi Xiong
AU - Huan Yao
AU - Xuanzhang Huang
AU - Sichun Zhang
AU - Xinrong Zhang
AU - Zhenning Wang
PY - 2026
DA - 2026/09/21
JO - Cell Reports Medicine
DO - 10.1016/j.xcrm.2026.103055
UR - https://doi.org/10.1016/j.xcrm.2026.103055
AB - Peritoneal metastasis is the most lethal manifestation of gastric cancer (GC), as conventional diagnostic methods cannot reliably detect occult free GC cells in the peritoneal cavity at an early stage. Here, we present a workflow for early detection and molecular classification of free GC cells using label-free metabolite-based mass cytometry for single-cell lipidomic profiling integrated with deep learning. We obtain 41,627 single-cell lipidomic profiles from 92 samples in total and identify a distinct lipidomic fingerprint that robustly discriminates between free GC cells and benign peritoneal cells. To further interpret complex lipidomic profiles, we develop a deep learning-based graph neural network classifier to identify rare free GC cells within peritoneal ecosystem. Beyond diagnostic discrimination, we propose a clinically relevant metabolic classification based on HER2 subtype-specific lipidomic heterogeneity. Our study advances the early diagnosis and molecular classification of peritoneal metastasis in GC, offering potential for metabolism-guided intervention.
SN - 2666-3791
ER -