Related Experiment Video
Updated: Jan 15, 2026
Author Spotlight: Advancing Reproductive Immunology with a Protocol for the Quantitative Evaluation of Endometrial Immune Cells
Published on: October 13, 2023
Serum Fingerprinting-Based Integrative Dual-Omics Machine Learning for Endometriosis-Associated Ovarian Cancer
Man Zhang1, Yunqiang Zhang2, Yanchao Zhang1
1Department of Chemistry, Department of Gastroenterology and Hepatology, Zhongshan Hospital, Fudan University, Shanghai 200433, China.
This study introduces a dual-omics approach using functionalized mesoporous nanoparticle-coupled laser desorption/ionization mass spectrometry (fMNPLDI-MS) for early detection and subtyping of endometriosis-associated ovarian cancer (EAOC). Integrating serum metabolic fingerprints and serum peptide fingerprints significantly improved diagnostic accuracy.
Area of Science:
- Biochemistry
- Analytical Chemistry
- Oncology
Background:
- Complex diseases like endometriosis-associated ovarian cancer (EAOC) require comprehensive molecular insights.
- Single omics approaches may lack the depth for accurate early detection and subtyping.
Purpose of the Study:
- To develop and validate a dual-omics platform for enhanced screening and subtyping of EAOC.
- To integrate serum metabolic fingerprints (SMFs) and serum peptide fingerprints (SPFs) for improved diagnostic performance.
Main Methods:
- Development of a functionalized mesoporous nanoparticle-coupled laser desorption/ionization mass spectrometry (fMNPLDI-MS) platform.
- High-throughput extraction of SMFs and SPFs from trace serum samples.
- Application of machine learning algorithms to integrated dual-omics data for classification and subtyping.
Main Results:
- The dual-omics integration strategy achieved an AUC of 0.989 and 93.1% accuracy in distinguishing EAOC from benign controls, outperforming single omics.
- For subtype classification, dual-omics yielded an AUC of 0.875 and 86.7% accuracy, surpassing individual metabolomics and peptidomics.
- The fMNPLDI-MS platform enabled rapid analysis (within 50 s) of dual omics data.
Conclusions:
- The developed high-throughput fMNPLDI-MS dual-omics platform offers a powerful tool for EAOC early screening and subtyping.
- Integrating metabolic and peptide fingerprints significantly enhances diagnostic capabilities for EAOC.
- This approach paves the way for precision management and early detection of ovarian cancer.
