Exploring the potential link between MitoEVs and the immune microenvironment of periodontitis based on machine learning and bioinformatics methods

Abstract

Background: Periodontitis is a chronic inflammatory condition triggered by immune system malfunction. Mitochondrial extracellular vesicles (MitoEVs) are a group of highly heterogeneous extracellular vesicles (EVs) enriched in mitochondrial fractions. The objective of this research was to examine the correlation between MitoEVs and the immune microenvironment of periodontitis.

Methods: Data from MitoCarta 3.0, GeneCards, and GEO databases were utilized to identify differentially expressed MitoEV-related genes (MERGs) and conduct functional enrichment and pathway analyses. The random forest and LASSO algorithms were employed to identify hub MERGs. Infiltration levels of immune cells in periodontitis and healthy groups were estimated using the CIBERSORT algorithm, and phenotypic subgroups of periodontitis based on hub MERG expression levels were explored using a consensus clustering method.

Results: A total of 44 differentially expressed MERGs were identified. The random forest and LASSO algorithms identified 9 hub MERGs (BCL2L11, GLDC, CYP24A1, COQ2, MTPAP, NIPSNAP3A, FAM162A, MYO19, and NDUFS1). ROC curve analysis showed that the hub gene and logistic regression model presented excellent diagnostic and discriminating abilities. Immune infiltration and consensus clustering analysis indicated that hub MERGs were highly correlated with various types of immune cells, and there were significant differences in immune cells and hub MERGs among different periodontitis subtypes.

Conclusion: The periodontitis classification model based on MERGs shows excellent performance and can offer novel perspectives into the pathogenesis of periodontitis. The high correlation between MERGs and various immune cells and the significant differences between immune cells and MERGs in different periodontitis subtypes can clarify the regulatory roles of MitoEVs in the immune microenvironment of periodontitis. Future research should focus on elucidating the functional mechanisms of hub MERGs and exploring potential therapeutic interventions based on these findings.

Keywords: Bioinformatics; Extracellular vesicles; Immune microenvironment; Machine learning; Mitochondria; Periodontitis.

Fig. 1

Occurrence and characterization of MitoEVs: an example of mitochondria-rich exosomes. Mitochondria-derived exosomes are formed through the accumulation of proteins, nucleic acids, and lipids synthesized by the endoplasmic reticulum, where the Golgi apparatus mediates the formation of outgrowth structures characterized by vesicles. Subsequently, these vesicles merge with the plasma membrane and are then liberated into the extracellular milieu, culminating in the formation of MitoEVs

Fig. 2

Flowchart of this study

Fig. 3

Identification of differentially expressed MERGs. A The petal plot identifies 44 MERGs. B Volcano plot showing differentially expressed MERGs between periodontitis and healthy gingival tissues. C Expression levels of 44 MERGs in gingival samples. Rows and columns denote MERGs and samples, respectively. D Correlation heatmap showing correlations among 44 MERGs, where “×” indicates no correlation

Fig. 4

Violin plot showing all 44 MERGs with significantly different expression levels. MERGs, MERGs; ***P < 0.001

Fig. 5

Results of GO and KEGG pathway analyses of MERGs. A GO enrichment results. B KEGG pathway enrichment results

Fig. 6

Screening for hub MERGs. A LASSO coefficient profiles of the 44 MERGs. B Tenfold cross-validation was performed to identify the optimal tuning parameter (λ). C Graphical representation depicting the impact of the decision tree count on the model error. D The Gini coefficient method random forest classifier was used to filter results. E Venn diagram of the shared genes between the random forest and LASSO algorithm datasets

Fig. 7

A Nomogram. B Calibration curve. C Decision curve

Fig. 8

A ROC curves of MERGs in the GSE10334 dataset. B ROC curves of classification models in the GSE10334 dataset. C ROC curves of MERGs in the GSE16134 dataset. D ROC curves of classification models in the GSE16134 dataset

Fig. 9

Differential immune cell infiltration in periodontitis and its correlation with hub MERGs. A Pearson correlation analysis between periodontitis immune cells. All correlation coefficients not indicating correlations are marked with “×”. B Infiltration ratio of immune cells for each periodontitis sample. C Pearson correlation analysis between hub MERGs and immune cells. All correlation coefficients not indicating correlations are marked with “×”

Fig. 10

Violin plot showing all 12 types of immune cells with significantly different expression levels in periodontitis; *P < 0.05, **P < 0.01, ***P < 0.001

Fig. 11

Identification of two distinct subtypes of hub MERG expression patterns in periodontitis. A Consensus clustering cumulative distribution function (CDF) for k = 2–9. B Relative change in the area under the CDF curve for k = 2–9. C Heatmap of the cooccurrence ratio matrix of periodontitis samples. D Principal component analysis of MERGs in subtype 1 and subtype 2. E Differences in the expression of hub MERGs between subtype 2 and subtype 1; ***P < 0.001

Fig. 12

A LASSO coefficient profiles of 22 immune cell types. B Tenfold cross-validation was performed to identify the optimal tuning parameter (λ). C Expression differences in the filtered immune cells between subtype 2 and subtype 1; *P < 0.05, **P < 0.01, ***P < 0.001

Fig. 13

Pearson correlation analysis between hub MERG expression levels and probing depth. All correlation coefficients not indicating correlations are marked with “×”