Multi-omic machine learning predictor of breast cancer therapy response

This study investigated the prediction of breast cancer therapy response using multi-omic data and machine learning. Researchers collected clinical, digital pathology, genomic, and transcriptomic profiles from pre-treatment biopsies of 168 breast cancer patients undergoing chemotherapy with or without HER2-targeted therapy. They found that treatment response is influenced by the pre-treatment tumor ecosystem and developed machine learning models to predict response based on this multi-omic landscape. The models, validated on an independent cohort, showed good accuracy in predicting the degree of residual disease after therapy.

Stephen-John Sammut, Mireia Crispin-Ortuzar, Suet-Feng Chin, Elena Provenzano, Helen A Bardwell, Wenxin Ma, Veil Cope, Ali Dariush, Sarah-Jane Dawson, Jean E Abraham, Janet Dunn, Louise Hitel, Jeremy Thomas, David A Cameron, John M S Bartlet, Larry Hayward, Paul D Paroha, Florian Markowetz, Oscar M Rueda, Helena M Earl, Carlos Calderon