DEPI-MS: Density-Equalized Pseudo-Image Learning for Drift-Tolerant LC−MS Metabolomics Classification
Analytical Chemistry · 12.11.2026
DOI: 10.1021/acs.analchem.6c03243 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 12.11.2026. Verfasst von Xiaohui Lin und 10 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: Natural Science Foundation of Fujian Province, National Natural Science Foundation of China (NSFC), National Cancer Institute of the National Institutes of Health.
Abstract (Originalsprache)
Liquid chromatography−mass spectrometry (LC−MS)-based metabolomics captures system-level biochemical variation, but classification remains difficult under realistic acquisition variability. Conventional peak-table workflows reduce the continuous retention time (RT)−m/z intensity field to discrete features, thereby losing structural information such as peak morphology, co-elution patterns, and local background. Pseudo-image learning provides a way to preserve this signal field, yet current approaches often allocate image resolution inefficiently, rely on generic image backbones, and remain sensitive to chromatographic drift. Here, we present DEPI-MS, a Density-Equalized Pseudo-Image learning for LC-MS-based metabolomics. DEPI-MS combines three practical design choices tailored to LC−MS data. First, it preserves uniform RT binning while using QC-derived nonuniform m/z binning, assigning more pixels to signal-dense mass regions without disrupting chromatographic interpretation. Second, a compact multi-scale classifier aggregates local peak-like responses and broader RT−m/z context through channel-wise global feature reweighting. Third, differentiable RT-axis warping is applied during training to reduce sensitivity to smooth chromatographic displacement without regenerating pseudo-images from raw files. In a nasopharyngeal carcinoma serum cohort, DEPI-MS achieved an AUC of 0.984 on an independent external validation set and remained stable under a 60 s RT-drift stress test, outperforming representative peak-table and pseudo-image baselines. Cohort-level attribution further localized recurrent model evidence to RT−m/z regions, providing candidate signal loci for biochemical follow-up. These results support DEPI-MS as a practical route toward transferable LC−MS metabolomics classification under acquisition variability.
Förderung
- Natural Science Foundation of Fujian Province
- National Natural Science Foundation of China (NSFC)
- National Cancer Institute of the National Institutes of Health
Zitieren
APA
Lin, X., Gao, S., Yang, J., Huang, X., Gu, X., Xu, X., Cheng, K., Ye, A., Fei, Z., Raftery, D., & Dong, J. (2026). DEPI-MS: Density-Equalized Pseudo-Image Learning for Drift-Tolerant LC−MS Metabolomics Classification. Analytical Chemistry. https://doi.org/10.1021/acs.analchem.6c03243
Vancouver
Lin X, Gao S, Yang J, Huang X, Gu X, Xu X, et al. DEPI-MS: Density-Equalized Pseudo-Image Learning for Drift-Tolerant LC−MS Metabolomics Classification. Analytical Chemistry. 2026. doi:10.1021/acs.analchem.6c03243
BibTeX
@article{Lin2026,
author = {Lin, Xiaohui and Gao, Shuang and Yang, Jie and Huang, Xunhua and Gu, Xiumei and Xu, Xiangnan and Cheng, Kian-Kai and Ye, Aihua and Fei, Zhaodong and Raftery, Daniel and Dong, Jiyang},
title = {DEPI-MS: Density-Equalized Pseudo-Image Learning for Drift-Tolerant LC−MS Metabolomics Classification},
journal = {Analytical Chemistry},
year = {2026},
doi = {10.1021/acs.analchem.6c03243}
}
EUVIMED