Development of a novel lncRNA-derived immune gene score using machine learning-based ensembles for predicting the survival of HCC

• DOI: 10.1007/s00432-024-05608-6
• Publication Date: 2024-02-09T16:02:11Z
• Authors: Qun Cai; Guoqi Li; Mingyan Zhu; Tingting Zhuo; Jiaying Xiao
• Keywords: Hematology

Abstract Background Long noncoding RNAs (lncRNAs) are implicated in the tumor immunology of hepatocellular carcinoma (HCC). Methods HCC mRNA and lncRNA expression profiles were used to extract immune-related genes with ImmPort database, lncRNAs ImmLnc algorithm. The MOVICS package was cluster mRNA, lncRNA, gene mutation methylation data on from TCGA. GEO ICGC datasets validate model. Data single-cell sequencing determine model various immune cell types. Results With this model, area under curve (AUC) for 1-, 3- 5-year survival patients 0.862, 0.869 0.912, respectively. Single-cell showed EREG significantly expressed a variety Knockdown target resulted significant anti-apoptosis, pro-proliferation pro-migration effects HepG2 HUH7 cells. Moreover, serum liver tissue levels higher than those healthy control patients. Conclusion We built prognostic good accuracy predicting patient survival. is potential immunotherapeutic promising biomarker.