Related Experiment Video
Updated: Jul 7, 2026
08:08
Quantitative Mass Spectrometric Profiling of Cancer-cell Proteomes Derived From Liquid and Solid Tumors
Published on: February 27, 2015
Machine Learning-Assisted SERS Quantification of Sialylated Alpha-Fetoprotein: From Single-Cell Analysis to
Yu Xiao1,2, Baolin Li1, Chengyao Geng2
1Department of Medical Laboratory, Affiliated Hospital of Southwest Medical University, Luzhou, China.
Small Methods
|July 6, 2026
Summary
This study developed a novel sensor for detecting sialylated alpha-fetoprotein (sAFP), a key marker for liver cancer (hepatocellular carcinoma, HCC). Machine learning algorithms enhance sAFP detection accuracy for clinical HCC risk assessment.
Area of Science:
- Biomedical Engineering
- Nanotechnology
- Machine Learning
Background:
- Sialylated alpha-fetoprotein (sAFP) is a crucial biomarker for hepatocellular carcinoma (HCC) research and clinical evaluation.
- Accurate and sensitive quantification of sAFP is essential for understanding HCC pathogenesis and patient assessment.
- Existing detection methods require improvement in specificity and quantifiability across diverse clinical scenarios.
Purpose of the Study:
- To develop a highly specific and sensitive detection system for sAFP.
- To integrate machine learning algorithms for enhanced sAFP quantification, imaging, and clinical risk assessment of HCC.
- To create a practical tool for real-world clinical application in HCC management.
Main Methods:
- Fabrication of functionalized gold/silver nanocube-encapsulated microgels (Au/AgNC-MG) for sAFP capture via dual aptamer recognition.
- Utilizing a heterogeneous bimetallic Surface-Enhanced Raman Spectroscopy (SERS) system for sensitive signal generation.
- Development of machine learning algorithms for sAFP classification, single-cell imaging, and clinical HCC risk stratification.
- Creation of an online HCC Risk Assessment website for accessible clinical use.
Main Results:
- The Au/AgNC-MG system demonstrated specific capture and sensitive Raman signal generation for sAFP.
- Machine learning algorithms successfully enabled accurate sAFP quantification, imaging of secreted sAFP, and robust HCC risk assessment.
- The integrated system provides a comprehensive platform for laboratory and clinical applications in HCC.
Conclusions:
- The developed Au/AgNC-MG combined with ML algorithms offers a powerful, generalizable paradigm for HCC research and clinical practice.
- This approach significantly advances the potential for early detection and personalized management of hepatocellular carcinoma.
- The online risk assessment tool facilitates the translation of advanced diagnostics into routine clinical workflows.
