Construction of a lipid metabolism-related risk model for hepatocellular carcinoma by single cell and machine learning analysis.

One of the most common cancers is hepatocellular carcinoma (HCC). Numerous studies have shown the relationship between abnormal lipid metabolism-related genes (LMRGs) and malignancies. In most studies, the single LMRG was studied and has limited clinical application value. This study aims to develop a novel LMRG prognostic model for HCC patients and to study its utility for predictive, preventive, and personalized medicine. We used the single-cell RNA sequencing (scRNA-seq) dataset and TCGA dataset of HCC samples and discovered differentially expressed LMRGs between primary and metastatic HCC patients. By using the least absolute selection and shrinkage operator (LASSO) regression machine learning algorithm, we constructed a risk prognosis model with six LMRGs (, , , , , and ). The risk prognosis model was further validated in an external cohort of ICGC. We also constructed a nomogram that could accurately predict overall survival in HCC patients based on cancer status and LMRGs. Further investigation of the association between the LMRG model and somatic tumor mutational burden (TMB), tumor immune infiltration, and biological function was performed. We found that the most frequent somatic mutations in the LMRG high-risk group were , , , , , and . Moreover, naïve CD8+ T cells, common myeloid progenitors, endothelial cells, granulocyte-monocyte progenitors, hematopoietic stem cells, M2 macrophages, and plasmacytoid dendritic cells were significantly correlated with the LMRG high-risk group. Finally, gene set enrichment analysis showed that RNA degradation, spliceosome, and lysosome pathways were associated with the LMRG high-risk group. For the first time, we used scRNA-seq and bulk RNA-seq to construct an LMRG-related risk score model, which may provide insights into more effective treatment strategies for predictive, preventive, and personalized medicine of HCC patients.