A novel ferroptosis phenotype-related clinical-molecular prognostic signature for hepatocellular carcinoma

Abstract

Ferroptosis is a newly identified cell death mechanism and potential biomarker for hepatocellular carcinoma (HCC) therapy; however, its clinical relevance and underlying mechanism remain unclear. In this study, transcriptome and methylome data from 374 HCC cases were investigated for 41 ferroptosis-related genes to identify ferroptosis activity-associated subtypes. These subtypes were further investigated for associations with clinical and pathological variables, gene mutation landscapes, deregulated pathways and tumour microenvironmental immunity. A gene expression signature and predictive model were developed and validated using an additional 232 HCC cases from another independent cohort. Two distinct ferroptosis phenotypes (Ferroptosis-H and Ferroptosis-L) were identified according to ferroptosis gene expression and methylation in the patients with HCC. Patients with the Ferroptosis-H had worse overall and disease-specific survival, and the molecular subtypes were significantly associated with different clinical characteristics, mRNA expression patterns, tumour mutation profiles and microenvironmental immune status. Furthermore, a 15-gene ferroptosis-related prognostic model (FPM) for HCC was developed and validated which demonstrated accurate risk stratification ability. A nomogram included the FPM risk score, ECOG PS and hepatitis B status was developed for eventual clinical translation. Our results suggest that HCC subtypes defined by ferroptosis gene expression and methylation may be used to stratify patients for clinical decision-making.

Keywords: co-expression network; ferroptosis; hepatocellular carcinoma; prognostic signature; risk-stratification.

FIGURE 1

The landscape of ferroptosis‐related HCC subgroups in the TCGA cohort. (A) Two ferroptosis subgroups were generated via unsupervised consensus clustering. (B) Heatmaps of two ferroptosis‐related subgroups in the TCGA cohort. 15 mRNA expression level and 8 methylation level which were highly related to the prognosis of patients with HCC and used for clustering were illustrated. Clinicopathology characteristics were correspondingly listed. (C‐D) The survival time curve of two ferroptosis‐related subgroups. Ferroptosis‐H group had a worse OS (C) and DSS (D) than the Ferroptosis‐L group

FIGURE 2

Differently expressed genes and enrichment analysis of two ferroptosis phenotype groups. (A) The volcano plot showed the significantly DEGs with FDR <0.05 and |log₂FC| >1 between two ferroptosis phenotype. (B‐G) DEGs enrichment analysis. The bubble plot (B), circular plot (C) and cluster plot (D) of the biological process enriched for the DEGs between two ferroptosis phenotypes. The bubble plot (E), circular plot (F) and cluster plot (G) of KEGG pathways enriched for the DEGs between two ferroptosis phenotypes. (H‐I) The GSEA results for biological process (H) and KEGG pathways (I)

FIGURE 3

The mutation signature profile of HCC. The plots showed the TMB landscape in patients with HCC (A) and the correlation between these mutations (B). (C) Genes with the significantly differentially mutational burden in different ferroptosis‐related subgroup were showed by the waterfall plot, the central bar plot summarized the proportion of TMB of each gene in two different groups. (D) The lollipop plot of TP53 gene showed the exact mutational position with type and its frequency

FIGURE 4

The immune landscape of two ferroptosis‐related subgroups. The ESTIMATE score (A) and immune checkpoints‐related gene expression (B) of two different ferroptosis phenotype groups. The proportional differences of 22 kinds of immune cells between patients with HCC were showed by radar plot (C) and violin plot (D). Scatter plots showed the significant correlation of tumour‐infiltrating immune cells proportion with ferroptosis score calculated by ssGSEA (P < .05) (E)

FIGURE 5

Identification of ferroptosis‐related risk gene and relationship with ferroptosis‐related gene. (A) Selecting the key differentially expressed genes related to the two ferroptosis subgroups in the LASSO model (λ). (B) LASSO coefficient spectrum of 508 genes enrolled and generate a coefficient distribution map for a logarithmic (λ) sequence. (C)The plot showed a significant correlation (P < .001) of the ferroptosis gene (left part) and risk gene (right part) with a correlation index higher than 0.3. (D) Sankey plot of significant correlation index ferroptosis gene (first column) and risk gene (second column) higher than 0.4 (P < .001)

FIGURE 6

Construction and validation of FPM. (A) Selecting the best parameters for FPM in the LASSO model (λ). (B) LASSO coefficient spectrum of 84 genes enrolled and generate a coefficient distribution map for a logarithmic (λ) sequence. In the TCGA cohort, the FPM risk score of each patient was plotted and the high‐risk and low‐risk group were divided using median cut‐off value (C). The distribution of survival state (D), survival curve (E) and ROC curve (F) for the high‐risk and low‐risk group in the TCGA cohort were showed. The same cut‐off value of the FPM risk score was deployed in the ICGC cohort for risk stratification (G), and the survival state (H), survival curve (I) and ROC curve (J) of the high‐risk and low‐risk group in the ICGC cohort were showed

FIGURE 7

Establishment and assessment of the nomogram. Univariate (A) and multivariate (B) Cox regression analysis of the relationship between the FPM and clinicopathological characteristics regarding OS. (C) Nomogram constructed combined with ECOG PS and FPM. ROC (D) and calibration curve (E) of the nomogram for predicting the probability of 1‐, 3‐ and 5 years OS in the TCGA cohort