Integrative Transcriptomic and Machine Learning Analysis Identifies Key Senescence‐Associated Secretory Phenotype Genes Associated With Immune Dysregulation in Periodontitis

Abstract

Periodontitis (PD) is a chronic inflammatory disorder marked by immune dysregulation and progressive tissue destruction. Cellular senescence and the senescence‐associated secretory phenotype (SASP) have been increasingly recognized as pivotal drivers of chronic inflammation. However, their specific contributions to PD remain insufficiently clarified. In this study, integrative bioinformatic analyses were conducted across transcriptomic datasets, employing least absolute shrinkage and selection operator, support vector machine–recursive feature elimination, and eXtreme gradient boosting algorithms to identify SASP‐related genes of significance. ICAM1, CXCL12, and MMP3 were found to be markedly upregulated in PD and demonstrated strong diagnostic potential through receiver operating characteristic and artificial neural network models. Functional enrichment analysis indicated their involvement in immune cell adhesion, migration, and infection‐associated pathways. Immune infiltration profiling revealed disrupted immune landscapes, with ICAM1 exhibiting a negative correlation with resting mast cells. Experimental validation using real‐time quantitative polymerase chain reaction and immunohistochemistry on clinical samples confirmed elevated expression of these genes at both the mRNA and protein levels. Moreover, dexamethasone was identified via molecular docking as a potential therapeutic compound targeting ICAM1 and CXCL12. Collectively, these findings advance the understanding of SASP associated with immune regulation in PD and suggest potential biomarkers and therapeutic targets for early diagnosis and intervention.