A stratification model of hepatocellular carcinoma based on expression profiles of cells in the tumor microenvironment

Background A malignancy of the liver, hepatocellular carcinoma (HCC) is among the most common and second-leading causes of cancer-related deaths worldwide. A reliable prognosis model for guidance in choosing HCC therapies has yet to be established. Methods A consensus clustering approach was used to determine the number of immune clusters in the Cancer Genome Atlas and Liver Cancer-RIKEN, JP (LIRI_JP) datasets. The differentially expressed genes (DEGs) among these groups were identified based on RNA sequencing data. Then, to identify hub genes among signature genes, a co-expression network was constructed. The prognostic value and clinical characteristics of the immune clusters were also explored. Finally, the potential key genes for the immune clusters were determined. Results After conducting survival and correlation analyses of the DEGs, three immune clusters (C1, C2, and C3) were identified. Patients in C2 showed the longest survival time with the greatest abundance of tumor microenvironment (TME) cell populations. MGene mutations in Ffibroblast growth factor-19 (FGF19) and catenin (cadherin-associated protein),beta 1(CTNNB1) were mostly observed in C2 and C3, respectively. The signature genes of C1, C2, and C3 were primarily enriched in 5, 23, and 26 pathways, respectively. Conclusions This study sought to construct an immune-stratification model for the prognosis of HCC by dividing the expression profiles of patients from public datasets into three clusters and discovering the unique molecular characteristics of each. This stratification model provides insights into the immune and clinical characteristics of HCC subtypes, which is beneficial for the prognosis of HCC.