FCGR2C: An emerging immune gene for predicting sepsis outcome

Abstract

Background: Sepsis is a life-threatening disease associated with immunosuppression. Immunosuppression could ultimately increase sepsis mortality. This study aimed to identify the prognostic biomarkers related to immunity in sepsis.

Methods: Public datasets of sepsis downloaded from the Gene Expression Omnibus (GEO) database were divided into the discovery cohort and the first validation cohort. We used R software to screen differentially expressed genes (DEGs) and analyzed DEGs' functional enrichment in the discovery dataset. Immune-related genes (IRGs) were filtered from the GeneCards website. A Lasso regression model was used to screen candidate prognostic genes from the intersection of DEGs and IRGs. Then, the candidate prognostic genes with significant differences were identified as prognostic genes in the first validation cohort. We further validated the expression of the prognostic genes in the second validation cohort of 81 septic patients recruited from our hospital. In addition, we used four immune infiltration methods (MCP-counter, ssGSEA, ImmuCellAI, and CIBERSORT) to analyze immune cell composition in sepsis. We also explored the correlation between the prognostic biomarker and immune cells.

Results: First, 140 genes were identified as prognostic-related immune genes from the intersection of DEGs and IRGs. We screened 18 candidate prognostic genes in the discovery cohort with the lasso regression model. Second, in the first validation cohort, we identified 4 genes (CFHR2, FCGR2C, GFI1, and TICAM1) as prognostic immune genes. Subsequently, we found that FCGR2C was the only gene differentially expressed between survivors and non-survivors in 81 septic patients. In the discovery and first validation cohorts, the AUC values of FCGR2C were 0.73 and 0.67, respectively. FCGR2C (AUC=0.84) had more value than SOFA (AUC=0.80) and APACHE II (AUC=0.69) in evaluating the prognosis of septic patients in our recruitment cohort. Moreover, FCGR2C may be closely related to many immune cells and functions, such as B cells, NK cells, neutrophils, cytolytic activity, and inflammatory promotion. Finally, enrichment analysis showed that FCGR2C was enriched in the phagosome signaling pathway.

Conclusion: FCGR2C could be an immune biomarker associated with prognosis, which may be a new direction of immunotherapy to reduce sepsis mortality.

Keywords: FCGR2C; immune genes; prognosis; prognostic biomarker; sepsis.

Figure 1

Flowchart of the study.

Figure 2

Identification and verification of prognostic genes. (A) The intersecting genes of DEGs and IRGs. (B, C) The Lasso coefficient values of 18 candidate prognostic genes were identified from the intersected genes in the discovery dataset. The vertical dashed lines are at the optimal log (λ) value. (D) The 18 candidate prognostic genes are shown in the box plot. (E–H) Identification of prognostic genes in the first validation cohort (GSE95233). Only 4 genes (CFHR2 (E), FCGR2C (F), GFI1 (G), and TICAM1 (H)) had the same expression differences as those in the discovery cohort. (I) Verification of FCGR2C in the second validation cohort (our recruitment cohort). The expression difference of FCGR2C was the same as that in the discovery and first validation cohorts. (*:P< 0.05, **:P< 0.01, ***:P < 0.001).

Figure 3

Validation of the qRT-PCR products of FCGR2C. (A) Matching the forward and reverse strand product plots with the primer sequences specific to FCGR2C. (B) Details of the complementary base pairing of the forward and reverse strand products with the FCGR2C primer sequence. (C) Agarose electrophoresis plot of qRT-PCR amplification products of FCGR2C. (D) The 168 base sequence is specific to FCGR2C. First-generation sequencing is a double-end sequencing of the product based on the forward and reverse strand sequences of the primer. The forward strand sequencing results of the products are indicated by 1. The reverse strand sequencing results of the products are indicated by 2. The primers of FCGR2C were designed with a length of 168 bp. The agarose electropherogram showed only one band consistent with the primer sequence’s size, indicating the primer’s specificity. In this study, we performed generation sequencing and agarose electrophoresis of qRT-PCR products from septic patients. Some of the patients’ results are shown in the pictures. The sequencing results of the forward and reverse sequences of qRT-PCR products and the sequence files after double-end splicing are shown in Table S6 .

Figure 4

Clinical role of FCGR2C. Correlation analysis of FCGR2C with the SOFA score (A), the GCS score (B), neutrophils (C), CD3+ T cells (D), and CD8+ T cells (E). (C-E): The x-axis represents the absolute value of neutrophils, the percentage of CD3+ T cells, and CD8+ T cells, respectively. (F) The prognostic evaluation ability of FCGR2C in the discovery dataset (GSE54514+GSE33118). (G) The prognostic evaluation ability of FCGR2C in the first validation dataset (GSE95233). The prognostic evaluation ability of FCGR2C (H), the SOFA score (I), and the APACHE II score (J) in the second validation cohort (our recruitment cohort).

Figure 5

Immune cell analysis with MCP-counter and ssGSEA in the discovery cohort. (A) The MCP-counter algorithm was used to analyze the immune cell relative abundance in septic survivors and non-survivors. The MCP-counter analyzes 8 immune cell populations(T cells, CD8 T cells, cytotoxic lymphocytes, B lineage cells, NK cells, monocytic lineage cells, myeloid dendritic cells, and neutrophils) and 2 stromal cell populations (endothelial cells and fibroblasts). (B) Correlation analysis of FCGR2C with immune cells and stromal cells. ssGSEA was used to analyze the 16 immune cells (C) and 13 immune functions (D) between septic survivors and non-survivors. (E) Heatmap of the correlation between immune functions and immune cells by ssGSEA. Color changes show the correlation intensity; red indicates a positive correlation, and blue indicates a negative correlation. (F) Correlation analysis of FCGR2C with immune functions and immune cells. Dots indicate the power of the correlation, and different colors indicate the P-value. (*P< 0.05, **P< 0.01, ***P < 0.001, ns:no significant).

Figure 6

Immune cell analysis with ImmuCellAI in the discovery cohort. (A) The ImmuCellAI algorithm was used to analyze the immune cells other than T cells between septic survivors and non-survivors. (B) The ImmuCellAI algorithm was used to compare T-cell subsets between septic survivors and non-survivors. (C) Correlation analysis of FCGR2C with immune cells. Dots indicate the intensity of the correlation, and different colors indicate the P-value. (*P< 0.05, **P< 0.01, ***P < 0.001, ns:no significant).

Figure 7

Immune cell analysis with CIBERSORT in the discovery cohort. (A) The relative percentages of 22 subpopulations of immune cells in septic patients. (B) The difference in immune cells between septic survivors and non-survivors. (C) Correlation analysis of FCGR2C with 22 immune cells. Dots indicate the intensity of the correlation, and different colors indicate the P-value. (*P< 0.05, ns: no significant.)

Figure 8

Functional enrichment analysis of DEGs in the discovery cohort. (A) The top 10 results of the cellular component (CC), molecular function (MF), and biological process (BP) categories in GO enrichment analysis are shown. (B) The top 30 KEGG enrichment results with the most significant P-values are displayed. (C) Genes enriched in the B-cell receptor signaling pathway, Fc gamma R-mediated phagocytosis, lysosome, and phagosome in the KEGG results are shown.