Integrated multi-omics analysis and machine learning refine molecular subtypes and prognosis in hepatocellular...

O-glycosylation significantly influences cellular physiological processes and disease regulation by modulating the structure, function, and stability of proteins. However, there is a notable gap in research focusing on O-glycosylation in relation to the prognosis of HCC patients. The study aimed to explore the expression and function of O-glycosylation genes in HCC from both bulk- and single-cell perspectives. Multi-omics data related to O-glycosylation identified by weighted gene co-expression network analysis (WGCNA). This was then combined with ten different clustering algorithms to construct molecular subtypes of high-resolution HCC. Cancer subtype 1 (CS1) is characterized by significant genomic variation, moderate immune cell infiltration, and immune function enrichment. Patients with CS2 have a better prognosis and are characterized by a stable genomic structure, an immune-hot phenotype with rich immune cell infiltration, and sensitivity to immunotherapy. CS3 is characterized by poor prognosis, outstanding genomic instability, and an immune-cold phenotype, but can benefit more from treatment with drugs such as sorafenib, cisplatin, paclitaxel, and gemcitabine. To further emphasize the role of O-glycosylation genes in individual HCC patients, we employed 59 machine-learning methods to construct and assess prognostic traits with improved generalizability. Microarray results indicated a pronounced upregulation of glycosylation hub genes involved in HCC stratification and modeling within HCC tumorous tissues. Altogether, our study highlights the importance of O-glycosylation for the assessment of HCC prognosis and treatment options by redefining HCC subtypes and constructing a consensus machine learning-driven prognostic signature (CMLS). This research establishes an optimized decision-making platform that enables the precise stratification of HCC patients, refines tumor treatment plans, and predicts patient survivability, with broad clinical implications.