After a patient is diagnosed with cancer, modern cancer care increasingly turns to genetic testing to get more information about the tumor and guide treatment options. When there’s a strong link between a genetic signature and a type of cancer, this approach can be invaluable. But only eight percent of cancer cases are paired to an approved therapy via genetic testing approaches. “Genetic sequencing is already routine in cancer care, but we still struggle to fully interpret the many mutations found in a patient’s tumor,” said Trey Ideker, a geneticist at the University of California, San Diego (UCSD), and coauthor of a new study that aims to enhance how we handle genetic data in cancer care, in a statement. Ideker and his team have developed MutationProjector, an AI model that analyzes a tumor’s genetic landscape and predicts how it will respond to a range of treatment options.

Full report : An AI model trained on over 30,000 tumors from 10 different solid cancer types aims to turn complex mutation information into more effective treatment plans.