Discovery of novel diagnostic biomarkers of hepatocellular carcinoma associated with immune infiltration

Abstract Objective The diagnosis of hepatocellular carcinoma (HCC) remains challenging for clinicians. Machine learning approaches and big data analysis are viable strategies to identify HCC diagnostic markers. Materials and methods For this study, we downloaded mRNA expression profiles of HCC from the GEO database and used random forest and machine learning algorithms such as Lasso to screen for reliable diagnostic genes. DO, KEGG, GSEA enrichment analysis for exploring differential gene function, disease pathways. CIBERSORT was performed to calculate the immune cell infiltration of HCC and to calculate the correlation of diagnostic genes with immune cells. Results The results indicated that ECM1, NPC1L1, and RSPO3 were downregulated in HCC compared with the normal group (P < 0.05), and furthermore, ECM1, NPC1L1, and RSPO3 had a high diagnostic value for HCC in both the training and test cohorts (AUC > 0.75). Immuno-infiltration analysis revealed that ECM1 and RSPO3 were highly positively correlated with neutrophil and macrophage M2, whereas they were negatively correlated with Tregs. Conclusion The present study identifies ECM1, NPC1L1, and RSPO3 as new diagnostic biomarkers for HCC based on normal and disease samples from HCC and correlated with immune cell infiltration.