A novel copper-induced cell death-related lncRNA prognostic signature associated with immune infiltration and clinical value in gastric cancer

Abstract

Background: Gastric cancer (GC) is one of the most important malignancies and has a poor prognosis. Copper-induced cell death, recently termed cuproptosis, may directly affect the outcome of GC. Long noncoding RNAs (lncRNAs), possessing stable structures, can influence the prognosis of cancer and may serve as potential prognostic prediction factors for various cancers. However, the role of copper cell death-related lncRNAs (CRLs) in GC has not been thoroughly investigated. Here, we aim to elucidate the role of CRLs in predicting prognosis, diagnosis, and immunotherapy in GC patients.

Methods: RNA expression data for 407 GC patients from The Cancer Genome Atlas (TCGA) were gathered, and differentially expressed CRLs were identified. Subsequently, the researchers applied univariate, LASSO, and multivariate Cox regression to construct a prognostic signature consisting of 5 lncRNAs based on the CRLs. Stratified by the median CRLSig risk score, Kaplan-Meier analysis was utilized to compare overall survival (OS) between the high- and low-risk groups. Among the two groups, gene set enrichment analysis (GSEA), tumor microenvironment (TME), drug sensitivity analysis, and immune checkpoint analysis were conducted. In addition, consensus clustering and nomogram analysis were performed to predict OS. Cell experiments and 112 human serum samples were employed to verify the effect of lncRNAs on GC. Furthermore, the diagnostic value of the CRLSig in the serum of GC patients was analyzed by the receiver operating characteristic (ROC) curve.

Results: A prognostic signature for GC patients was constructed based on CRLs, composed of AC129926.1, AP002954.1, AC023511.1, LINC01537, and TMEM75. According to the K-M survival analysis, high-risk GC patients had a lower OS rate and progression-free survival rate than low-risk GC patients. Further support for the model's accuracy was provided by ROC, principal component analysis, and the validation set. The area under the curve (AUC) of 0.772 for GC patients showed a better prognostic value than any other clinicopathological variable. Furthermore, immune infiltration analysis showed that the high-risk group had greater antitumor immune responses in the tumor microenvironment. In the high-risk subgroup, 23 immune checkpoint genes had significantly higher expression levels than in the low-risk subgroup (p < 0.05). The half-maximal inhibitory concentrations (IC50) of 86 drugs were found to be significantly different in the two groups. Accordingly, the model is capable of predicting the effectiveness of immunotherapy. In addition, the five CRLs in GC serum exhibited statistically significant expression levels. The AUC of this signature in GC serum was 0.894, with a 95% CI of 0.822-0.944. Moreover, lncRNA AC129926.1 was significantly overexpressed in GC cell lines and the serum of GC patients. Importantly, colony formation, wound healing, and transwell assays further confirmed the oncogenic role of AC129926.1 in GC.

Conclusion: In this study, a prognostic signature model consisting of five CRLs was developed to improve OS prediction accuracy in GC patients. The model also has the potential to predict immune infiltration and immunotherapy effectiveness. Furthermore, the CRLSig might serve as a novel serum biomarker to differentiate GC patients from healthy individuals.

Keywords: Biomarker; Copper induced cell death; Gastric cancer; Prognostic signature; lncRNA.

Fig. 1

Identification of the differentially expressed CRLs in GC. A Identification of the differentially expressed RNAs of GC in the TCGA database through a Venn diagram. B Heatmap of the differentially expressed copper cell death related genes. C Analysis of crosstalk in the lncRNA-CRG relationship. D Heatmap for the differentially expressed CRLs in GC. E–G GO enrichment analysis of CRGs. H KEGG enrichment analysis of CRGs. CRLs copper cell death-related lncRNAs, CRGs copper cell death related genes

Fig. 2

Establishment and verification of the 5 CRLSig risk model in all cohorts, and the training and testing cohorts. A The forest plots of the univariate Cox regression analysis between the 12 CRLs and OS of GC. B Heatmap of the 12 CRLs in GC. C Ten CRLs were selected by the LASSO regression model according to minimum criteria. D The coefficient of CRLs was calculated by LASSO regression. E–G Kaplan–Meier survival curves of the OS of high-risk and low-risk patients in the three cohorts. H–J The distributions of risk scores in the two risk groups for the three cohorts. K–M Different patterns of survival status and survival time in the two risk groups for the three cohorts. N–P Heatmap of the expression of the 5 prognostic lncRNAs in the three cohorts. Q–S The 1-, 3-, and 5-year ROC curves of the risk model in the three cohorts. T–V The discriminatory power of the risk model and other clinical factors shown by the ROC curve of OS in the three cohorts

Fig. 3

Independent prognostic value of the CRLSig for patients with GC. A–B Validation of the independence of the CRLSig in OS through the univariate Cox regression analysis (A) and multivariate Cox regression analysis (B). C–F The prognostic value was evaluated based on stage (C–D) and age (E–F) in the total TCGA cohort. G A nomogram was constructed based on the independent prognostic factors to predict the prognosis of GC. H The calibration curves for 1-, 3- and 5-year OS plots comparing the actual to predicted values in the TCGA cohort. I KEGG pathway analysis for high and low-risk GC patients

Fig. 4

Tumor immune microenvironment analysis and immunotherapy response and drug sensitivity analysis. Tumor immune microenvironment analysis (A–F). A Bubble plot of immune cell infiltration related to the risk model was obtained by different algorithms. B–D The ESTIMATE, immune, and stromal scores for the tumor microenvironment of GC patients in the high- and low-risk groups. E–F The ssGSEA scores of immune cells and immune functions in the two risk groups. Immunotherapy response and drug sensitivity analysis. G The difference in common immune checkpoint expression in the two risk groups. H–W The typical antitumor drug chemotherapeutic responses in the low- and high-risk groups. *p < 0.05, **p < 0.01, ***p < 0.001

Fig. 5

CRLSig levels in the serum of GC patients and healthy controls. A–E The five CRLSig levels in the serum of GC patients and healthy controls. F The expression level of serum lncRNA AC129926.1 in different stages in patients with GC. G ROC curve of the combined five CRLs in serum for the diagnosis of GC. H–J Expression and prognosis of AC129926.1 in GC cell lines and TCGA database. H Relative AC129926.1 expression in GES-1, HGC-27 and AGS cells. I AC129926.1 expression in TCGA database. J Prognosis of AC129926.1 in GC in TCGA database. *p < 0.05, **p < 0.05 and ***p < 0.001

Fig. 6

Biological function of AC129926.1 in gastric cancer. A, B Wound scratch assay results showing that AC129926.1 promotes HGC-27 and AGS cell migration, magnification 100 × . C, D AC129926.1 significantly promotes the migration of HGC-27 and AGS cells, as detected by Transwell assays. E, F AC129926.1 enhances the colony formation of HGC-27 and AGS cells in vitro. *p < 0.05, **p < 0.01