CMM PI Jeroen de Ridder receives an ERC consolidator grant

Jeroen de Ridder says: “In personalized medicine it is all about tailoring treatment decisions to the individual patient. For cancer patients, for instance, these decisions can be based on a thorough characterization of the tumor at a molecular level. However, recent artificial intelligence (AI) models, that work so well on images and text, struggle in dealing with the complexity of these molecular data. When it comes to patient-derived molecular profiles, there is simply not enough patient data to use within modern AI models. To fix this, the FoundationDX project is trying a new approach. Instead of immediately training on patient data, we first want to teach an AI about molecular disease biology by creating so-called foundation models based on massive amounts of biomolecular data from single cells, molecular profiles of healthy and sick tissues and networks that show how different biological pieces connect. We're using a special kind of learning called self-supervised learning (SSL), an important driver of AI. Once the AI has some ‘common sense’ about molecular disease biology, we can finally train it to make predictions such as “what drug should this patient receive?” or “what tumor subtype does this patient have?” In this way we can benefit from the enormous progress in AI and thereby bring truly personalized medicine one step closer.”