Identification of potential biomarkers for lung cancer using integrated bioinformatics and machine learning...

Lung cancer is one of the most common cancer and the leading cause of cancer-related death worldwide. Early detection of lung cancer can help reduce the death rate; therefore, the identification of potential biomarkers is crucial. Thus, this study aimed to identify potential biomarkers for lung cancer by integrating bioinformatics analysis and machine learning (ML)-based approaches. Data were normalized using the robust multiarray average method and batch effect were corrected using the ComBat method. Differentially expressed genes were identified by the LIMMA approach and carcinoma-associated genes were selected using Enrichr, based on the DisGeNET database. Protein-protein interaction (PPI) network analysis was performed using STRING, and the PPI network was visualized using Cytoscape. The core hub genes were identified by overlapping genes obtained from degree, betweenness, closeness, and MNC. Moreover, the MCODE plugin for Cytoscape was used to perform module analysis, and optimal modules were selected based on MCODE scores along with their associated genes. Subsequently, Boruta-based ML approach was utilized to identify the important genes. Consequently, the core genes were identified by the overlapping genes obtained from PPI networks, module analysis, and ML-based approach. The prognostic and discriminative power analysis of the core genes was assessed through survival and ROC analysis. We extracted five datasets from USA cohort and three datasets from Taiwan cohort and performed same experimental protocols to determine potential biomarkers. Four genes (LPL, CLDN18, EDNRB, MME) were identified from USA cohort, while three genes (DNRB, MME, ROBO4) were from Taiwan cohort. Finally, two biomarkers (EDNRB and MME) were identified by intersecting genes, obtained from USA and Taiwan cohorts. The proposed biomarkers can significantly improve patient outcomes by enabling earlier detection, precise diagnosis, and tailored treatment, ultimately contributing to better survival rates and quality of life for patients.