Identification of Age-Related Genes in Skeletal Muscle Using Ensemble Machine Learning

Sarcopenia, the age-related decline in skeletal muscle mass and function, was a major contributor to frailty and reduced quality of life in older adults. Understanding the genetic factors that influenced muscle aging was essential for improving early detection and potential interventions. In this study, we leveraged transcriptomic data from the Genotype-Tissue Expression (GTEx) project and employed an ensemble machine learning approach, specifically Extreme Gradient Boosting (XGBoost), to identify key genes associated with skeletal muscle aging. Our model demonstrated improved predictive performance over traditional regression methods, capturing complex, non-linear relationships in gene expression patterns. The analysis identified six influential genes—{EDA2R} (ENSG00000131080), {OPRD1} (ENSG00000116329), {H2BC11} (ENSG00000124635), {FAM171A1} (ENSG00000148468), {GALNTL6} (ENSG00000174473), and {DMRT2} (ENSG00000173253)—implicated in neuromuscular signaling, chromatin remodeling, and muscle structure maintenance. These findings contributed to a better understanding of the molecular processes underlying skeletal muscle aging and supported further research into potential biomarkers for age-related muscle decline.