Most patients do not respond to immune checkpoint inhibitors (ICIs), and existing biomarkers often fail to generalize across cancer types and treatments. Researchers developed COMPASS, a pan-cancer foundation model that predicts ICI response directly from bulk tumor transcriptomes using a concept bottleneck transformer.

COMPASS encodes gene expression through 44 biologically grounded immune concepts (cell states, tumor-microenvironment interactions, and signaling pathways). Trained on over 10,000 tumors, it significantly outperforms 22 existing methods across 16 external clinical cohorts spanning multiple cancers and different ICIs. It also generalizes well to previously unseen cancer types and therapies.

A new agentic framework called SPARK uses language as a universal interface to autonomously generate biologically meaningful hypotheses and convert them into analytical tools directly from routine H&E pathology slides.

No hand-crafted features or task-specific retraining are required. The multi-agent system handles the full pipeline: