Machine Learning-Based Identification of Biomarkers for Early-Stage Non-Small Cell Lung Cancer Through Gene Expression Analysis

Tumor progression is primarily driven by DNA mutations; however, this mechanism alone does not fully account for all aspects of tumor development. Beyond genetic alterations, epigenetic changes also significantly influence the mutational landscape and affect gene expression without altering the DNA sequence. To gain a more comprehensive understanding of these regulatory mechanisms, it is essential to analyze gene expression at the transcriptional level. In this study, we examined non-small cell lung cancer (NSCLC) samples to identify specific gene expression changes, particularly in early-stage tumors. We conducted a bioinformatic analysis of RNA-sequencing data, followed by validation using an independent dataset from The Cancer Genome Atlas. Our analysis revealed a set of differentially expressed genes, seven of which were validated in patient-derived samples. Among these genes, EFNA4 and TEDC2 were significantly upregulated, whereas CDC42EP2, STX11, THBD, TMEM88, and GPM6A were notably downregulated in tumor tissues compared with adjacent normal tissues. Our findings highlight a distinct gene expression signature that differentiates NSCLC samples from normal lung tissues at the transcriptional level. These results underscore the potential of transcriptomic profiling as a promising tool for early-stage cancer detection and biomarker discovery.