Back

A Rapid Gene Expression Profiler Classifies AML Tumor Responsiveness to Standard Therapies

Kurtz, S. E.; Eide, C. A.; Kaempf, A.; Long, N.; Miller, A.; Bottomly, D.; McWeeney, S.; Anand, S.; Ng, S. W.; Wang, J. C.; Dick, J. E.; Tyner, J. W.

2025-10-09 cancer biology
10.1101/2025.10.08.681215 bioRxiv
Show abstract

The emergence of transcriptional signatures that define cell types and pathways has made it possible to guide cancer therapy selection through gene expression profiling. We developed a rapid qPCR-based platform to profile cell state, stemness, and BCL2 family gene expression as a companion diagnostic test for acute myeloid leukemia (AML). We validated the stability and utility of the signatures across multiple measurement platforms and using patient samples from two centers. Integrating these signatures with clinical features enables an expedient means to predict the likelihood of patient responses to two standard-of-care therapies: intensive chemotherapy and hypomethylating agent plus venetoclax (HMA+Ven). For patients treated with HMA+Ven, expression levels of the promonocyte-like signature and BCL2 add predictive value for response and overall survival in multivariable models that include genetic features. The incorporation of the rapid profiler into the prospective evaluation of newly diagnosed AML patients may enhance treatment stratification and improve outcomes.

Matching journals

The top 5 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.