COMPASS Beats 22 Immunotherapy Prediction Methods in Leave-One-Out Evaluation
marinkazitnik · x · 2026-07-03
In leave-one-out cross-validation, COMPASS improved average accuracy by 8.5% and precision-recall AUC by 15.7%, outperforming 22 commonly used biomarkers and predictive models while achieving the highest cross-cohort transfer generalization rate. Even when completely excluding a specific cancer type, drug class, or checkpoint target during training, the model maintained its performance on the excluded categories, indicating its ability to capture anti-tumor immune biological patterns transferable across cancer types.
More from Research
- Alibaba says RecGPT-V3 cuts serving cost 52.4% while lifting Taobao GMV 3.97% — burny_tech · 2026-07-27
- Google says 86% of Gemini chats in a 14.65M-conversation study were non-work related — xiaohu · 2026-07-27
- Developers weigh the hardest LLM app security problems: injection, leakage, MCP — PRINCE9553 · 2026-07-27
- RoboDojo benchmarks 30 robot manipulation policies across 42 sim and 18 real tasks — jiqizhixin · 2026-07-27
- Researchers show fact-storing MLPs can be viewed as Hebbian memories — CatAstro_Piyush · 2026-07-27
- A measure-zero reminder: Transformers can be almost surely injective — CatAstro_Piyush · 2026-07-27