Comprehensive analysis of the progression mechanisms of CRPC and its inhibitor discovery based on machine learning algorithms

Background: Almost all patients treated with androgen deprivation therapy (ADT) eventually develop castration-resistant prostate cancer (CRPC). Our research aims to elucidate the potential biomarkers and molecular mechanisms that underlie transformation of primary into CRPC. Methods: We collected three microarray datasets (GSE32269, GSE74367, GSE66187) from Gene Expression Omnibus (GEO) database for Differentially expressed genes (DEGs) in CRPC were identified further analyses, including Ontology (GO), Kyoto Encyclopedia Genes Genomes (KEGG), gene set enrichment analysis (GSEA). Weighted coexpression network (WGCNA) two machine learning algorithms employed identify The diagnostic efficiency selected was evaluated based on expression level receiver operating characteristic (ROC) curve analyses. conducted virtual screening drugs using AutoDock Vina. In vitro experiments performed Cell Counting Kit-8 (CCK-8) assay evaluate inhibitory effects cell viability. Scratch transwell invasion assays assess migration abilities cells. Results: Overall, a total 719 DEGs, consisting 513 upregulated 206 downregulated genes, identified. biological functional indicated DEGs mainly enriched pathways related cycle metabolism. CCNA2 CKS2 as promising combination WGCNA, LASSO logistic regression, SVM-RFE, Venn diagram These validated exhibited strong predictive ability. results revealed Aprepitant Dolutegravir optimal targeted CKS2, respectively. demonstrated both exerted significant cells ( p < 0.05), displaying superior effect compared Dolutegravir. Discussion: increases progression cancer, which may be one driving factors can serve therapeutic targets Additionally, show anti-tumor