Background: Prostate cancer stemness (PCS) cells have been reported to drive tumor progression, recurrence and drug resistance. However, there is lacking systematical assessment of stemness traits and associations with immunological properties in prostate adenocarcinoma (PRAD). Methods We collected 7 PRAD cohorts with 1465 men and calculated the stemness indices for each sample using the innovative one-class logistic regression (OCLR) machine learning algorithm. We selected the mRNAsi to quantify the stemness traits that correlated significantly with prognosis and accordingly identified 21 PCS-related CpG loci and 13 pivotal signature. Meanwhile, we conducted consensus clustering and classified the total cohorts into 5 PCS clusters with distinct outcomes based on the 13-gene panel. Additionally, we implemented the CIBERSORT algorithm to infer the differential abundance across 5 PCS clusters. Lastly, we used the Connectivity Map (CMap) resource to screen potential compounds for targeting PRAD stemness. Results: The 13-gene based PCS model possessed high predictive significance for progression-free survival (PFS) that was trained and validated in 7 independent cohorts. We found that PCScluster5 possessed the highest stemness fractions and suffered from the worst prognosis. Immune infiltration analysis shows that the activated immune cells (CD8+ T cell and dendritic cells) infiltrated significantly less in PCScluster5 than other clusters, especially PCScluster1, supporting the negative regulations between stemness and anticancer immunity. High mRNAsi was also found to be associated with up-regulation of immunosuppressive checkpoints, like PDL1. Finally, several potential compounds, including the top hits of cell cycle inhibitor and FOXM1 inhibitor, were identified for targeting PRAD stemness. Conclusion: Our study comprehensively evaluated the PRAD stemness traits based on large cohorts and established a 13-gene based classifier for predicting prognosis or potential strategies for stemness treatment.