An AI model decodes tumor mutations to predict treatment response Trained on more than 30,000 tumor genomes, MutationProjector offers drug developers a broader framework for connecting cancer genetics to therapy outcomes. Written byAndrea Corona

https://www.drugdiscoverynews.com/an-ai-model-decodes-tumor-mutations-to-predict-treatment-response-17197 Genetic sequencing has become a routine part of cancer care, but making clinical sense of the thousands of mutations found in a given tumor remains a stubborn challenge. A new AI model from researchers at University of California, San Diego (UC San Diego) is designed to close that gap — and it could have meaningful implications for how drug developers think about patient stratification and biomarker discovery.