United multi-omics and machine learning refine regulatory T cell-defined hepatocellular carcinoma subtypes.

Hepatocellular carcinoma (HCC) is highly heterogeneous and aggressive, and the absence of precision individual treatment regimen enables repeated immune escape. Exploiting regulatory T cell (Treg) marker genes as key classifiers, we used 10 clustering algorithms to integrate the multi-omics HCC patient data and combined them with 10 machine learning (ML) algorithms to delineate molecular subtypes predictive of prognosis and immune response. We identified two cancer subtypes (CSs) that are associated with prognosis, with the second subtype (CS2) showing the most favorable prognostic outcomes. Subsequently, 9 key genes were screened for HCC model scoring, stratifying patients into low-risk (good prognosis, responsive to immunotherapy) and high-risk (poor outcome, not responsive to immunotherapy) groups. The high-risk group may be effective against the mTOR inhibitor AZD8055. Comprehensive multi-omics data and multiple ML algorithms offer key insights into HCC occurrence and evolution, with model scores guiding patient prognosis and treatment clinically.