ZBP1, an M1 Macrophage-Associated Biomarker Identified by Machine Learning, Suppresses Tumorigenesis and Predicts Immunotherapy Response in Head and Neck Squamous Cell Carcinoma

Head and neck squamous cell carcinoma (HNSCC) is a highly aggressive Cancer with restricted therapeutic options and unfavourable survival outcomes. To identify novel prognostic biomarkers and therapeutic targets, we investigated the role of macrophage polarisation in HNSCC progression. Using integrative computational approaches, including biological network algorithms and molecular subtyping, we established a robust gene signature associated with M1/M2 macrophage balance, which exhibited significant prognostic value in HNSCC patients. Further analysis employing multi-model machine learning algorithms pinpointed ZBP1 as the pivotal gene, linking it to key clinical and immunological features, including disease progression, immune microenvironment remodelling, tumour mutational burden, and response to immune checkpoint inhibitors. Mechanistic studies confirmed ZBP1's tumour-suppressive function, demonstrating its ability to inhibit HNSCC cell proliferation and migration in vitro. Moreover, macrophage co-culture assays revealed that ZBP1 modulates immune regulation by restricting macrophage recruitment and altering polarisation dynamics. Collectively, our findings highlight ZBP1 as a promising prognostic biomarker and a potential immunotherapeutic target in HNSCC. This study not only enhances our understanding of macrophage-mediated tumour immunity but also provides mechanistic insights into how ZBP1 integrates tumour-intrinsic and immune-regulatory pathways to influence HNSCC progression. These discoveries may contribute to the development of more precise therapeutic strategies for this aggressive malignancy.

HNSCC; ZBP1; immunotherapy; machine learning; tumour microenvironment.