Metabolic Detection of Pancreatic Ductal Adenocarcinoma through Machine Learning and Lipidomics
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers characterized with rapid progression, metastasis and difficulty in diagnosis. However, there are no effective liquid-based testing methods available for PDAC detection. Here we introduce a minimally invasive approach that employs machine learning and lipidomics to establish a metabolic method to detect PDAC. Through greedy algorithm and mass spectrum feature selection, we optimized 17 characteristic metabolites as detection features and developed a LC-MS-based targeted assay. In this study, 1033 patients with PDAC at various stages were examined. This approach has achie
Resource information
- DOI
- 10.5281/zenodo.5148042
- Credit basis
- Creators in DataCite DOI metadata
- Publisher
- Zenodo
- Upstream last modified
- Jul 30, 2021
- Access
- Files remain with the original publisher
- Last checked
- Nov 6, 2026
- License
- Creative Commons Attribution 4.0 International
- Last record update
- Nov 6, 2026
About this resource
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers characterized with rapid progression, metastasis and difficulty in diagnosis. However, there are no effective liquid-based testing methods available for PDAC detection. Here we introduce a minimally invasive approach that employs machine learning and lipidomics to establish a metabolic method to detect PDAC. Through greedy algorithm and mass spectrum feature selection, we optimized 17 characteristic metabolites as detection features and developed a LC-MS-based targeted assay. In this study, 1033 patients with PDAC at various stages were examined. This approach has achieved 86.74% accuracy with an AUC of 0.9351 in the large independent external validation cohort, and 85.00% accuracy with 0.9389 AUC in the prospective clinical cohort. Accordingly, single-cell sequencing, proteomics and mass spectrometry imaging were applied and revealed significant alterations of selected lipids in PDAC tissues. We propose that the ML-aided lipidomics approach is used for early detection of PDAC.