Development and pan-cancer validation of an epigenetics-based random survival forest model for prognosis prediction and drug response in OS
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study developed an epigenetics-based model to predict osteosarcoma (OS) patient outcomes and guide treatment. The model accurately stratifies patients, improving personalized therapy selection for better clinical outcomes.
Area Of Science
- Oncology
- Epigenetics
- Genomics
Background
- Osteosarcoma (OS) displays significant epigenetic heterogeneity, necessitating systematic characterization for clinical application.
- Current understanding of OS epigenetic landscape and its clinical implications is limited.
Purpose Of The Study
- To systematically characterize epigenetic features in osteosarcoma.
- To develop and validate an epigenetics-based predictive model for patient prognosis and treatment stratification.
Main Methods
- Single-cell transcriptomic analysis of primary OS samples.
- Construction and validation of a Random Survival Forest (RSF) model using 801 epigenetic factors.
- Analysis of epigenetic states in the OS microenvironment and identification of key predictive genes.
Main Results
- Distinct epigenetic states identified in OS cells and the tumor microenvironment.
- RSF model identified OLFML2B, ACTB, and C1QB as key predictive genes with broad applicability across cancers.
- Risk stratification revealed differential responses to chemotherapy and targeted therapies.
Conclusions
- The epigenetics-based RSF model shows high prognostic accuracy (AUC > 0.83 in external cohorts).
- The model serves as a practical tool for treatment stratification in osteosarcoma.
- Findings establish a framework for personalized therapy selection in OS patients.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
