Pan-cancer predictive model
Pan-cancer predictive model
We developed an XGBoost-based prediction model for pan-cancer immunotherapy response using ceRNA network features. The XGBoost model was trained on the training set and evaluated using 5-Fold Stratified Cross-Validation. We identified 14 best-performing ImmCeRNAs as predictive signatures, including OIP5-AS1-OSMR, MSC-AS1-AVPR1A, AGAP2-AS1-SEMA4C, KCNQ1OT1-IGF1R, and MAPKAPK5-AS1-TMSB10.
Features importance analysis of ImmCeRNA
ROC Curve: ImmCeRNA vs PD-L1 biomarker
