Bioinformatics-led discovery of ferroptosis-associated diagnostic biomarkers and molecule subtypes for tuberculosis patients

Abstract

Background: Ferroptosis is closely associated with the pathophysiological processes of many diseases, such as infection, and is characterized by the accumulation of excess lipid peroxides on the cell membranes. However, studies on the ferroptosis-related diagnostic markers in tuberculosis (TB) is still lacking. Our study aimed to explore the role of ferroptosis-related biomarkers and molecular subtypes in TB.

Methods: GSE83456 dataset was applied to identify ferroptosis-related genes (FRGs) associated with TB, and GSE42826, GSE28623, and GSE34608 datasets for external validation of core biomarkers. Core FRGs were identified using weighted gene co-expression network analysis (WGCNA). Subsequently, two ferroptosis-related subtypes were constructed based on ferroptosis score, and differently expressed analysis, GSEA, GSEA, immune cell infiltration analysis between the two subtypes were performed.Affiliations: Please check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary.correctly RESULTS: A total of 22 FRGs were identified, of which three genes (CHMP5, SAT1, ZFP36) were identified as diagnostic biomarkers that were enriched in pathways related to immune-inflammatory response. In addition, TB patients were divided into high- and low-ferroptosis subtypes (HF and LF) based on ferroptosis score. HF patients had activated immune- and inflammation-related pathways and higher immune cell infiltration levels than LF patients.

Conclusion: Three potential diagnostic biomarkers and two ferroptosis-related subtypes were identified in TB patients, which would help to understand the pathogenesis of TB.Author names: Kindly check and confirm the process of the author names [2,4]correctly.

Keywords: Diagnostic biomarkers; Ferroptosis; Molecular types; Tuberculosis; xCell.

Fig. 1

Flow chart of the data analysis process. The GSE83456 dataset was used to find FRGs associated with TB. The core FRGs were identified using WGCNA, and validated using the GSE42826, GSE28623, GSE34608 datasets and qRT-PCR analysis. Two subtypes related to ferroptosis were then created based on the ferroptosis score. Differential expression analysis, GSEA, and immune cell infiltration analysis were performed between the two subtypes

Fig. 2

Expression profile of FRGs in TB. A The GSEA results suggested that ferroptosis is important in the pathogenesis of TB. B Volcano plot of the FRGs (the green dots represented the down-regulated FRGs and red dots represented the up-regulated FRGs). C The correlation plot represented the degree of correlation of the 22 FRGs. D Box plots depicted the differentially expressed FRGs between the HC and TB groups. *p < 0.05, **p < 0.01, ***p < 0.001

Fig. 3

Identification of core FRGs by WGCNA. A Key modules identified by WGCNA. B The Venn diagram represented the genes that are shared between the FRGs and the WGCNA. C The ROC curves of CHMP5, SAT1, and ZFP36 genes in the GSE83456 dataset

Fig. 4

Validation of core FRGs using independent datasets. The gene expression levels A–C and ROC curves D–F of CHMP5, SAT1, and ZFP36 genes in the GSE42826, GSE28623, and GSE34608 datasets. *p < 0.05, **p < 0.01, ***p < 0.001

Fig. 5

The core FRGs were analyzed using GSEA, which revealed potential signaling pathways. The immune-inflammatory pathways are significantly enriched in high expression of CHMP5 A, SAT1 B, and ZFP36 C

Fig. 6

Differences in immune characteristics between the HC and TB groups. A Box plots depicted the landscape of immune cells infiltration between the HC and TB groups. *p < 0.05, **p < 0.01, ***p < 0.001. B–D Correlation between three core FRGs and immune cell infiltration levels. *p < 0.05, **p < 0.01, ***p < 0.001

Fig. 7

Identification of ferroptosis-related subtypes. A Box plots depicted the ferroptosis score between the HC and TB groups. *p < 0.05. B Volcano plot exhibited the DEGs between the LF and HF subgroups. C GSEA was performed to explore the potential pathways between the two subgroups

Fig. 8

GSVA was carried out to investigate the potential pathways between the two subgroups

Fig. 9

Differences in immune characteristics between the two subgroups. Heatmap A and box B plots depicted the landscape of immune cells infiltration between the LF and HF groups. *p < 0.05, **p < 0.01, ***p < 0.001

Fig. 10

Validation of core genes by qRT-PCR. The gene expression levels of CHMP5 A, SAT1 B, and ZFP36 C genes in the clinical blood samples. **p < 0.01, ***p < 0.001