Machine Learning and Mendelian Randomization Reveal Molecular Mechanisms and Causal Relationships of Immune-Related Biomarkers in Periodontitis

Abstract

This study aimed to investigate the molecular mechanisms of periodontitis and identify key immune-related biomarkers using machine learning and Mendelian randomization (MR). Differentially expressed gene (DEG) analysis was performed on periodontitis datasets GSE16134 and GSE10334 from the Gene Expression Omnibus (GEO) database, followed by weighted gene co-expression network analysis (WGCNA) to identify relevant gene modules. Various machine learning algorithms were utilized to construct predictive models, highlighting core genes, while MR assessed the causal relationships between these genes and periodontitis. Additionally, immune infiltration analysis and single-cell sequencing were employed to explore the roles of key genes in immunity and their expression across different cell types. The integration of machine learning, MR, and single-cell sequencing represents a novel approach that significantly enhances our understanding of the immune dynamics and gene interactions in periodontitis. The study identified 682 significant DEGs, with WGCNA revealing seven gene modules associated with periodontitis and 471 core candidate genes. Among the 113 machine learning algorithms tested, XGBoost was the most effective in identifying periodontitis samples, leading to the selection of 19 core genes. MR confirmed significant causal relationships between CD93, CD69, and CXCL6 and periodontitis. Further analysis showed that these genes were correlated with various immune cells and exhibited specific expression patterns in periodontitis tissues. The findings suggest that CD93, CD69, and CXCL6 are closely related to the progression of periodontitis, with MR confirming their causal links to the disease. These genes have potential applications in the diagnosis and treatment of periodontitis, offering new insights into the disease's molecular mechanisms and providing valuable resources for precision medicine approaches in periodontitis management. Limitations of this study include the demographic and sample size constraints of the datasets, which may impact the generalizability of the findings. Future research is needed to validate these biomarkers in larger, diverse cohorts and to investigate their functional roles in the pathogenesis of periodontitis.

Keywords: Mendelian randomization; biomarkers; machine learning; periodontitis; single-cell sequencing.

Figure 1

Workflow of this study. MR, Mendelian randomization; WGCNA, weighted gene co-expression network analysis.

Figure 2

Screening of periodontitis-related genes. (A) Heatmap of differential expression analysis for GSE16134 and GSE10334. (B) Volcano plot of differential expression analysis for GSE16134 and GSE10334. Green represents downregulated genes and red represents upregulated genes. (C) Module–trait heatmap showing the correlation between clustered gene modules and periodontitis, with corresponding correlation coefficients and p-values for each module. (D) Venn diagram revealing 471 overlapping candidate hub genes. (E, F) GO enrichment analysis of the candidate hub genes. (G) KEGG pathway analysis of the candidate hub genes. WGCNA, weighted gene co-expression network analysis.

Figure 3

Refining the core gene characteristics associated with periodontitis through machine learning. (A) Performance comparison of prediction models based on different machine learning methods. (B–D) Receiver operating characteristic (ROC) curves and confusion matrices for the GSE16134, GSE10334, and GSE223924 datasets. (E) Volcano plot showing the differential analysis of the 19 candidate genes identified by XGBoost.

Figure 4

Mendelian randomization (MR) analysis revealing the causal relationships between periodontitis and key genes. (A–C) Scatter plots, forest plots, and funnel plots for CD93, CD69, and CXCL6, respectively, showing the causal effects on periodontitis risk, evaluating the causal effects of individual Single nucleotide polymorphisms (SNPs), and assessing overall heterogeneity. Leave-one-out analysis further visualizes the independent impact of each gene on periodontitis risk.

Figure 5

Molecular characteristics of CD93, CD69, and CXCL6 in periodontitis. (A) Expression analysis of CD93, CD69, and CXCL6 in normal and periodontitis tissues. (B) Correlation analysis of the three genes, CD93, CD69, and CXCL6. (C) Receiver operating characteristic (ROC) curves of CD93, CD69, and CXCL6 in the periodontitis datasets. (D–F) Gene set enrichment analysis (GSEA) analysis of CD93, CD69, and CXCL6 in the periodontitis datasets. (G–I) Gene set variation analysis (GSVA) analysis of CD93, CD69, and CXCL6 in the periodontitis datasets.

Figure 6

Analysis of immune cell infiltration and inflammatory marker genes in periodontitis. (A) Relative distribution of 22 immune cell types in normal and periodontitis samples. (B) Differential analysis of 22 immune cell types in normal and periodontitis samples. (C) Analysis of the relationships between CD93, CD69, CXCL6, and immune cells. (D) Analysis of immune cells associated with CD93 in periodontitis. (E) Analysis of immune cells associated with CD93 in periodontitis. (F) Analysis of immune cells associated with CXCL6 in periodontitis.

Figure 7

Single-cell analysis revealing the cell-specific expression of periodontitis-related genes. (A) UMAP plot of single cells from the GSE171213 cohort of periodontitis. (B) Relative expression of CD93, CD69, and CXCL6 genes across different cell types. (C) Violin plot showing the expression of CD93, CD69, and CXCL6 genes in different cell types.