Identification and experimental validation of core genes associated with breast cancer brain metastasis via machine learning

• Identified four core genes (B3GNT9, SERPINF1, LUM, CILP) associated with breast cancer brain metastasis using machine learning. • The three-gene model (SERPINF1, LUM, CILP) demonstrated excellent diagnostic performance with AUC 0.984 in external validation. • Experimental validation in zebrafish and mouse models confirmed the role of these genes in brain metastasis. • These genes may serve as novel biomarkers and therapeutic targets for breast cancer brain metastasis.