Introduction: Mutation patterns have been extensively explored to decipher the etiologies of hepatocellular carcinoma (HCC). However, the study and potential clinical role of mutation patterns to stratify high-risk patients and optimize precision therapeutic strategies remain elusive in HCC.
Methods: Using exon-sequencing data in public (n=362) and in-house (n=30) cohorts, mutation signatures were extracted to decipher relationships with the etiology and prognosis in HCC. The proteomics (n=159) and cell-line transcriptome data (n=1019) were collected to screen the implication of sensitive drugs. A novel multi-step machine-learning framework was then performed to construct a classification predictor, including recognizing stable reversed gene pairs, establishing a robust prediction model, and validating the robustness of the predictor in five independent cohorts (n=900).
Results: Two heterogeneous mutation signature clusters were identified, and a high-risk prognosis cluster was recognized for further analysis. Notably, mutation signature cluster 1 (MSC1) was featured by activated anti-tumor immune and metabolism dysfunctional states, higher genomic instability (high TMB, SNV neoantigen, indel neoantigens, and total neoantigens), and a dismal prognosis. Notably, MSC performed as an independent risk factor than clinical traits (eg, stage, vascular invasion). Additionally, afatinib and canertinib were recognized which might have potential therapeutic implications in MSC1, and the targets of these drugs presented a higher expression in both gene and protein levels in HCC.
Discussion: Our studies may provide a promising platform for improving prognosis and tailoring therapy in HCC.
Keywords: gene pairs; hepatocellular carcinoma; machine learning; mutation signature; precision therapy; prognosis.
© 2023 Zhang et al.