Back

Translating clinical gene sequencing into a foundational representation of tumor subtype

Kong, J.; Lee, I.; Boecher, D.; Singhal, A.; Kelly, M.; Moon, J.; Ahn, C. H.; Ock, C.-Y.; Kumar, T.; Sears, T. J.; Laub, D.; Wright, S.; Wall, P.; Carter, H.; Wang, Z.; Ideker, T.

2025-09-09 systems biology
10.1101/2025.09.08.674723 bioRxiv
Show abstract

While gene sequencing is routine in cancer care, translating sequences into treatment decisions remains a challenge. Here we introduce MutationProjector, an AI foundation model that transforms tumor mutation profiles into a compact representation of cancer subtype, with broad implications for diagnosis and therapy. MutationProjector is pre-trained by integrating genomic alterations from >30,000 tumors with extensive molecular knowledge, yielding a model that accurately reconstructs held-out genetic profiles (demonstrating strong generalization) and determines subtype representations from altered molecular pathways (enabling model interpretability). We evaluate MutationProjector in independent tasks related to prediction of immunotherapy response, prediction of chemotherapy response, and classification of metastasis, recording leading performance in all areas. Each task identifies key biomarkers of interest, including KMT2A and KRAS-STK11 alterations which govern immunotherapy response.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.