Identification of acetylation-related gene biomarkers for gallbladder carcinoma via multi-dataset and machine learning, with insights into immune microenvironment modulation

Abstract Gallbladder cancer (GBC) is a malignant digestive system tumor, and patients are often only diagnosed at an advanced stage, resulting in high mortality and poor prognosis. Insufficiently specific and sensitive biomarkers impede early screening and diagnosis, highlighting the need to improve early diagnostic capabilities and identify reliable molecular biomarkers. Two GBC datasets and 3,252 acetylation-related genes were compiled from GeneCards and PubMed. Key genes were then identified using four machine learning algorithms, and their diagnostic performance and correlations with immune cell infiltration were evaluated. There were 848 identified differentially expressed genes (DEGs), of which 203 were acetylation-related DEGs. Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis revealed associations with biological processes. Machine learning approaches identified seven key genes that were used to develop a diagnostic model. The model’s performance was assessed using receiver operating characteristic curves and decision curve analysis. Immune infiltration analysis revealed links between the principal genes and immune cell populations, with NCOA1 showing the strongest positive correlation with activated natural killer cells. This study systematically characterizes acetylation-related genes in GBC, develops a high-accuracy diagnostic model, and provides preliminary insights into potential links between epigenetic regulation and the immune microenvironment.