Five-Gene Expression Formula Accurately Detects Hepatocellular Carcinoma Tumors

Area of Science:

• Oncology
• Bioinformatics
• Genomics

Background:

• Hepatocellular carcinoma (HCC) is a major global cause of cancer mortality.
• Current diagnostic methods like imaging and Alpha-Fetoprotein (AFP) testing are limited to later disease stages.
• Transcriptomic analysis shows potential for early HCC detection, but machine learning approaches face challenges in clinical adoption.

Purpose of the Study:

• To develop a novel, interpretable, and efficient predictive formula for early hepatocellular carcinoma (HCC) detection.
• To address limitations of existing machine learning models in transcriptomic data analysis for cancer detection.
• To identify key gene expression biomarkers for HCC diagnosis.

Main Methods:

• Development of a predictive formula using the Kolmogorov-Arnold Network (KAN).
• Utilized transcriptomic data from the GSE25097 dataset.
• The formula is based on the expression levels of five specific genes: VIPR1, CYP1A2, FCN3, ECM1, and LIFR.

Main Results:

• The novel KAN-based formula achieved 99% accuracy on the GSE25097 test set.
• The formula demonstrated robust performance on six independent datasets, with accuracies exceeding 90% in all cases.
• Identified VIPR1, CYP1A2, FCN3, ECM1, and LIFR as critical biomarkers for HCC detection.

Conclusions:

• The developed formula provides a simple, interpretable, efficient, and accessible method for HCC identification.
• The five identified genes serve as promising biomarkers for early HCC detection.
• This approach lays the groundwork for advancing HCC diagnostic strategies and clinical applications.