A novel prognostic zinc finger gene model for hepatocellular carcinoma via machine learning

Le résumé fourni par la source

BACKGROUND: Hepatocellular carcinoma (HCC) is a highly lethal malignancy with poor prognosis, and effective biomarkers for predicting immunotherapy response are lacking. Immune checkpoint blockade has advanced HCC treatment, yet heterogeneous responses and inadequate predictive signatures remain key challenges. Zinc finger proteins (ZFPs), the largest transcription factor family, regulate cancer progression and immune function, but the roles of immune-related ZFP genes in HCC have not been systematically investigated. METHODS: We developed a ZFP immune regulatory algorithm to identify immune pathway-associated ZFP genes in HCC. Using multiple machine learning methods, we constructed a prognostic risk model based on these key ZFPs, and stratified HCC patients into high- and low-risk groups to validate the model's prognostic and immunotherapy response predictive performance. RESULTS: The ZFP-based prognostic model effectively stratified HCC patients into high- and low-risk groups with significantly different survival outcomes, and exhibited strong predictive power for patients' response to immunotherapy. CONCLUSION: This study reveals the critical involvement of ZFPs in HCC immune regulation, and establishes a novel ZFP-based gene signature. This signature serves as a reliable biomarker for HCC prognostic stratification and immunotherapy response prediction, which may facilitate personalized clinical management of HCC patients.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.