Identification of a novel five ferroptosis-related gene signature as a promising prognostic model for breast cancer

Abstract

Background: Breast cancer (BCa) is a major challenge for women's health worldwide. Ferroptosis is closely related to tumorigenesis and cancer progression. However, the prognostic value of ferroptosis-related genes in BCa remains unclear, and more accurate prognostic models are urgently needed.

Methods: Gene expression profiles and clinical information of BCa patients were collected from public databases. LASSO and multivariate Cox regression analysis were utilized to construct the prognostic gene signature. Kaplan-Meier plotter, receiver operating characteristic (ROC) curves, and nomogram were used to validate the prognostic value of the gene signature. Gene set enrichment analysis was performed to explore the molecular functions and signaling pathways.

Results: Differentially expressed ferroptosis-related genes between BCa samples and normal tissues were obtained. A novel five-gene signature including BCL2, SLC40A1, TFF1, APOOL, and PRAME was established for prognosis prediction. Patients stratified into high-risk or low-risk group displayed significantly different survival. Kaplan-Meier and ROC curves showed a good performance for survival prediction in different cohorts. Biological function analysis revealed that the five-gene signature was associated with cancer progression, immune infiltration, immune response, and drug resistance. Nomogram including the five-gene signature was established.

Conclusion: A novel five ferroptosis-related gene signature and nomogram could be used for prognostic prediction in BCa.

Keywords: Breast cancer; Ferroptosis; Gene signature; Overall survival; Prognosis.

Fig. 1

Overview of the process of this study

Fig. 2

Clustering and identification of ferroptosis-related genes. A Relative change in area under CDF curve. B CDF curves of Ks (from 2 to 10). C Heat map showing sample clustering results, with consensus K identified as 4. D Clustering consistency plots for Ks (from 2 to 10). E Kaplan–Meier curves for cluster C3 and C4. F Volcano map of the differentially expressed ferroptosis-related genes between C3 and C4. Significantly upregulated and downregulated genes are shown in red and green, respectively. G Heat map of the differentially expressed ferroptosis-related genes between C3 and C4

Fig. 3

Construction of ferroptosis-related model. A LASSO regression analysis of 15 ferroptosis-related genes associated with prognosis. B Optimal penalty parameter λ identified by tenfold cross-validation. C Forest plot showing Cox regression analysis of five ferroptosis-related genes and overall survival. D Kaplan–Meier curves showing the overall survival of patients in high-risk group and low-risk group. E ROC curves of the five-gene signature prediction model. F Correlations among risk score, heat map of gene expression, and survival status of patients

Fig. 4

Validation of the five-gene signature model in the TCGA and GEO. Kaplan–Meier curves showing the overall survival of patients in high-risk group and low-risk group in TCGA (A), GSE20685 (C), GSE20711 (E), GSE42568 (G), and GSE131769 (I) cohorts. ROC curves of the five-gene signature model in TCGA (B), GSE20685 (D), GSE20711 (F), GSE42568 (H), and GSE131769 (J) cohorts

Fig. 5

Elucidation of molecular functions and pathways. A Heat map of the differentially expressed genes between high-risk and low-risk groups. B Protein–protein interaction network of the differentially expressed genes between high-risk and low-risk groups downloaded from the STRING database. C KEGG analysis showing many cancer-related molecular pathways and drug resistance pathways. D GO analysis showing enrichment of biological processes. E GO analysis showing enrichment of cell components. F GO analysis showing enrichment of molecular functions

Fig. 6

Association between signature and clinicopathological features. Kaplan–Meier curves showing the overall survival of patients expressed high or low level of BCL2 (A), APOOL (B), SLC40A1 (C), PRAME (D), and TFF1 (E). Relationship between different subtypes of BCa and expression levels of BCL2 (F), APOOL (G), SLC40A1 (H), PRAME (I), and TFF1 (J). K Trend plot showing gene expression tendency in different pathological stages of BCa. L Prediction and analysis of genes that were functionally similar to these five genes

Fig. 7

Functional study of the five signature genes. A Correlation between gene expression and immune infiltration in BCa. B Correlation between gene methylation and immune infiltration in BCa. C Correlation between gene expression and drug sensitivity (top 30) in pan-cancer. D Pie plot showing the copy number variation percentage of the five signature genes in BCa. Hete. (heterozygous); Homo. (homozygous); Amp. (amplification); Dele. (deletion). E Pathway activated or inhibited by the five signature genes. F Upstream miRNA regulatory network

Fig. 8

Expression of the five ferroptosis-related genes at gene and histological level. Expression levels of BCL2 (A), SLC40A1 (B), TFF1 (C), APOOL (D), and PRAME (E) in five pairs of BCa samples and adjacent normal breast tissues obtained from own hospital. *** P < 0.001. F Immunohistochemical analysis in the HPA database showing the expressions of BCL2, APOOL, SLC40A1, PRAME, and TFF1 proteins in BCa tissues and normal tissues

Fig. 9

Construction of a predictive nomogram for BCa patients based on risk score and clinical features. A Forrest plot of the univariate Cox regression analysis. B Forrest plot of the multivariate Cox regression analysis. C Nomogram for predicting 3-year, 5-year, and 7-year overall survival of BCa patients. Calibration curves for predicting 3-year (D), 5-year (E), and 7-year (F) overall survival of BCa patients. G ROC curves for 3-year, 5-year, and 7-year overall survival of the nomogram

Fig. 10

Comparison of the nomogram. Nomogram with age, metastasis status, clinical stage, the five-gene prognostic signature, and the combined model for predicting 3-year (A), 5-year (B), and 7-year (C) overall survival of BCa patients