DNA methylation and a biomarker panel to predict asthma development

A Methylation Diagnostic Model Based on Random Forests and Neural Networks for Asthma Identification

Background

Asthma significantly impacts human life and health as a chronic disease. Traditional treatments for asthma have several limitations. Artificial intelligence aids in cancer treatment and may also accelerate our understanding of asthma mechanisms. We aimed to develop a new clinical diagnosis model for asthma using artificial neural networks (ANN).

Methods

Datasets (GSE85566, GSE40576, and GSE13716) were downloaded from Gene Expression Omnibus (GEO) and identified differentially expressed CpGs (DECs) enriched by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis. Random forest (RF) and ANN algorithms further identified gene characteristics and built clinical models. In addition, two external validation datasets (GSE40576 and GSE137716) were used to validate the diagnostic ability of the model.

Results

The methylation analysis tool (ChAMP) considered DECs that were up-regulated (n =121) and down-regulated (n =20). GO results showed enrichment of actin cytoskeleton organization and cell-substrate adhesion, shigellosis, and serotonergic synapses. RF (random forest) analysis identified 10 crucial DECs (cg05075579, cg20434422, cg03907390, cg00712106, cg05696969, cg22862094, cg11733958, cg00328720, and cg13570822). ANN constructed the clinical model according to 10 DECs. In two external validation datasets (GSE40576 and GSE137716), the Area Under Curve (AUC) for GSE137716 was 1.000, and AUC for GSE40576 was 0.950, confirming the reliability of the model.

Conclusion

Our findings provide new methylation markers and clinical diagnostic models for asthma diagnosis and treatment.

The landscape of DNA methylation in asthma: a data mining and validation

Human asthma is caused by interactions between a range of genetic and environmental factors. However, the specific pathogenesis of asthma remains controversial. This study explored the contribution of DNA methylation to asthma using computer learning methods. Relevant datasets and information related to patients with asthma were collected from the Gene Expression Omnibus (GEO) database. A multivariate linear regression model was established. Differentially expressed genes and DNA methylation sites were identified. The results showed that the expression of 169 genes was significantly different between the two groups. Through differential analysis of methylation and differential analysis of gene expression, 44 differentially expressed genes that may be affected by DNA methylation modification were identified. The results of the multiple linear regression model showed that DNA methylation could explain 9.81% of the variation in gene expression. Gene ontology and Kyoto Encyclopedia of Genes and Genomes analyses showed that the differentially expressed genes, HLA-DMB, IL4, HLA-DPB1, and CD40LG, were related to the occurrence of asthma, and HLA-DMB expression was significantly reduced in allergic asthma. There was a positive correlation between cg04933135 and HLA-DMB expression, and cg04933135 was a differential site for DNA methylation. Using blood samples from asthma patients, we confirmed that HLA-DMB expression is down-regulated, which may be affected by abnormal DNA methylation. DNA methylation plays an important role in the development of asthma, and HLA-DMB which modified by abnormal DNA methylation can be regarded as a new biomarker of asthma.