Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS

Background: Osteosarcoma (OS) exhibits significant epigenetic heterogeneity, yet its systematic characterization and clinical implications remain largely unexplored. Methods: We analyzed single-cell transcriptomes of five primary OS samples, identifying cell type-specific epigenetic features and their evolutionary trajectories. An epigenetics-based Random Survival Forest (RSF) model was constructed using 801 curated epigenetic factors and validated in multiple independent cohorts. Results: Our analysis revealed distinct epigenetic states in the OS microenvironment, with particular activity in OS cells and osteoclasts. The RSF model identified key predictive genes including OLFML2B, ACTB, and C1QB, and demonstrated broad applicability across multiple cancer types. Risk stratification analysis revealed distinct therapeutic response patterns, with low-risk groups showing enhanced sensitivity to traditional chemotherapy drugs while high-risk groups responded better to targeted therapies. Conclusion: Our epigenetics-based model demonstrates excellent prognostic accuracy (AUC>0.997 in internal validation, 0.832-0.929 in external cohorts) and provides a practical tool for treatment stratification. These findings establish a clinically applicable framework for personalized therapy selection in OS patients.