Bioinformatics-Driven Identification of Ferroptosis-Related Gene Signatures Distinguishing Active and Latent Tuberculosis

Abstract

Background: Tuberculosis (TB) remains a major global public health challenge, and diagnosing it can be difficult due to issues such as distinguishing active TB from latent TB infection (LTBI), as well as the sample collection process, which is often time-consuming and lacks sensitivity and specificity. Ferroptosis is emerging as an important factor in TB pathogenesis; however, its underlying molecular mechanisms are not fully understood. Thus, there is a critical need to establish ferroptosis-related diagnostic biomarkers for tuberculosis (TB).

Methods: This study aimed to identify and validate potential ferroptosis-related genes in TB infection while enhancing clinical diagnostic accuracy through bioinformatics-driven gene identification. The microarray expression profile dataset GSE28623 from the Gene Expression Omnibus (GEO) database was used to identify ferroptosis-related differentially expressed genes (FR-DEGs) associated with TB. Subsequently, these genes were used for immune cell infiltration, Gene Set Enrichment Analysis (GSEA), functional enrichment and correlation analyses. Hub genes were identified using Weighted Gene Co-expression Network Analysis (WGCNA) and validated in independent datasets GSE37250, GSE39940, GSE19437, and GSE31348.

Results: A total of 21 FR-DEGs were identified. Among them, four hub genes (ACSL1, PARP9, TLR4, and ATG3) were identified as diagnostic biomarkers. These biomarkers were enriched in immune-response related pathways and were validated. Immune cell infiltration, GSEA, functional enrichment and correlation analyses revealed that multiple immune cell types could be activated by FR-DEGs. Throughout anti-TB therapy, the expression of the four hub gene signatures significantly decreased in patients cured of TB.

Conclusions: In conclusion, ferroptosis plays a key role in TB pathogenesis. These four hub gene signatures are linked with TB treatment effectiveness and show promise as biomarkers for differentiating TB from LTBI.

Keywords: biomarkers; ferroptosis; gene expression; immune response; tuberculosis.

Figure 1

The flowchart outlines the gene expression analysis pipeline for the GSE28623 dataset, highlighting differential expression, ferroptosis-related genes, hub modules, and validation steps.

Figure 2

Heatmaps and sPLS-DA analysis of GSE28623 dataset. (A) The heatmap displayed gene expression profiles with hierarchical clustering, distinguishing LTBI (red) and TB (green) samples based on expression levels. (B) The sPLS-DA plot showed the overlapping of LTBI (red) and TB (green) groups, illustrating variability between the two conditions.

Figure 3

Changes in immune cell characteristics between LTBI and TB groups in GSE28623 dataset. (A) Boxplot compares the fractions of immune cell types in LTBI and TB groups, with significant differences marked by asterisks. * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001. (B) Barplot illustrates the estimated proportions of immune cells across individual LTBI and TB samples.

Figure 4

Gene Set Enrichment Analysis (GSEA) in the GSE28623 dataset. The enrichment plots illustrate the “immune response to tuberculosis” and “ferroptosis” pathways analyzed in the GSE28623 dataset, with high normalized enrichment scores (NES) of 2.516 and 2.3057, respectively, and significant P.adj and FDR values, indicating their strong association with TB pathogenesis.

Figure 5

Identification of analysis of FR-DEGs: (A) Venn diagram depicting overlapped genes between DEGs and FRGs. (B) STRING showing the interaction of 21 FR-DEGs. (C) The correlation analysis represents the degree of correlation between the 21 FR-DEGs.

Figure 6

Functional enrichment, pathway, and GOCircle analysis of 21 FR-DEGs. (A) The lollipop chart describes the GO and KEGG enrichment analysis, highlighting significant biological processes, cellular components, molecular functions, and pathways associated with TB and ferroptosis. (B) WikiPathway analysis of FR-DEGs based on logFC values and z-score showed the top 10 most important pathways including ferroptosis, emphasizing their potential involvement in TB pathogenesis and immune regulation.

Figure 7

Identification of hub modules in GSE28623 dataset. (A) Scale-free topology model fit (R² = 0.8) and mean connectivity against soft threshold power values (power, β = 7), assessing network independence and module stability. (B) The cluster dendrogram, illustrating hierarchical gene clustering with distinct module colors representing functional groups. The colored row below the dendrogram indicates modules as determined by the module cuttree height of 0.3. (C) Heatmap showing module–trait relationships, with colored bars on the left indicating different modules. Rows represent Pearson correlation coefficient and p-values between gene modules and TB/LTBI conditions. (D) Scatterplots of gene significance for TB (y-axis) vs. module membership (x-axis) of the yellow module, with a correlation of 0.69 and p-value of 8.4 × 10⁻¹⁸⁸, suggesting strong association with disease traits.

Figure 8

Selection of hub genes and volcano plot: (A) Venn diagram showing the overlap between WGCNA-yellow module genes (n = 226) and 21 FR-DEGs, resulting in the identification of five hub genes. (B) The volcano plot displays differential gene expression, highlighting significantly upregulated genes in red, downregulated genes in blue, and non-significant genes in gray, highlighting 5 hub genes.

Figure 9

The lollipop plots illustrate the correlation of immune cell types with ACSL1, PARP9, TLR4, and ATG3 expression, showing variations in correlation strength and statistical significance, which may provide insights into TB-related immune responses.

Figure 10

Validation of 4 hub genes in GSE37250, GSE39940, and GSE19439 datasets. (A–C) illustrate the expression levels of ACSL1, PARP9, TLR4, and ATG3 in LTBI and TB samples, highlighting significant differences in gene regulation. (D–F) present the ROC analysis for ACSL1, PARP9, TLR4, and ATG3 from the same datasets, demonstrating their diagnostic potential for TB based on high AUC values. ** p < 0.01, *** p < 0.001, **** p < 0.0001, ns—non-significant.

Figure 11

Association of hub gene signatures with anti-TB treatment efficacy at 5 distinct time points in GSE31348 dataset. (A–D) The expression levels of ACSL1, PARP9, TLR4, and ATG3 change significantly across different time points during TB treatment (diagnosis, week 1, week 2, week 4, and week 26), highlighting their dynamic regulation in disease progression. In each scatter plot, the central horizontal line represents the median, while the endpoints indicate the first quartile (Q1) and third quartile (Q3), defining the interquartile range (IQR). The endpoints of the central vertical line mark the minimum and maximum values. * p < 0.05, ** p < 0.01, *** p < 0.001, **** p < 0.0001, ns—non-significant.