Identification of Aging-related Genes in Diagnosing Idiopathic Pulmonary Fibrosis via Integrating Bioinformatics Analysis and Machine Learning

Data Acquisition, Processing, and Differential Expression Analysis3435363738Differential Expression Analysis of Age-Related GenesDEARGs between normal and IPF samples were identified using the "venn" and "limma" packages. DEARGs were defined by an adjusted p-value < 0.05 and |log2-fold-change| > 0.5. Heatmaps were generated using the "heatmap" function in R.Gene Ontology, Pathway Enrichment, and PPI Network AnalysisDisease ontology (DO) analysis, Gene ontology (GO) functional enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses of DEARGs were performed using the "ClusterProfiler" R package. The STRING database (https://string-db.org/) was used to visualize the protein-protein interaction (PPI) network among DEARGs.Identification of Potential Biomarkers in Normal and IPF SamplesBiomarkers for IPF were identified using machine learning algorithms: LASSO, SVM-RFE, and RF. The "glmnet" package in R was used for LASSO, the "e1071" package for SVM-RFE, and the "randomForest" package for RF. Overlapping genes identified by these algorithms were considered as hub age-related genes for IPF diagnosis.Identification and Validation of Hub Age-Related GenesThe expression levels of hub genes were evaluated using box plots to compare normal and IPF individuals. Receiver Operating Characteristic (ROC) curves were plotted using the "pROC" package in R to assess the diagnostic accuracy of hub age-related genes in both training and test datasets, with GSE24206 serving as an external validation dataset.