Objective：The weighted gene co-expression network（WGCNA）and least absolute shrinkage and selection operator（LASSO）were used to investigate the prognostic value of transcription factor SOX12 in the occurrence and development of hepatocellular carcinoma（HCC）. Methods：Using Gene Expression Omnibus（GEO）and The Cancer Genome Atlas（TCGA）corresponding information，Kaplan-Meier（K-M）survival curve and single factor，multivariate Cox regression were used to analyze the clinical value of SOX12 gene expression in HCC. ESTIMATE and CIBERSORT algorithms were used to study the correlation between SOX12 gene expression and tumor immune microenvironment. The WGCNA and LASSO algorithms were used to establish a risk prognosis model to further evaluate the effect of SOX12 gene expression in the high and low risk groups on the mutations of HCC genes. Results：In HCC tumor tissues，the expression of SOX12 was significantly increased，which was related to age，gender，tumor grade，disease stage，and was significantly related to the survival and prognosis of patients. In the risk prognosis model of immune-related genes（IRGs） showed that the overall survival rate of the high-risk group was worse than that of the low-risk group. The risk prognosis model had a significant prognostic prediction effect，and its 1-year，3-year and 5-year AUCs were 0.823，0.811 and 0.824，respectively. The proportion of TP53 gene mutations in the high SOX12 expression group（40%）was significantly higher than that in the low SOX12 expression group（25%）. The results indicated that the high and low SOX12 expression in the high and low risk groups affects the frequency of HCC genetic mutations. Conclusion：The expression of SOX12 is associated with HCC immune infiltration and disease gene mutations，suggesting that it may become a potential target for prognostic evaluation of HCC patients.