Projektbeschreibung
Basismodelle für eine zuverlässige Krebsvorhersage
Die Molekulardiagnostik spielt eine entscheidende Rolle in der personalisierten Medizin. Aktuelle KI-Modelle benötigen jedoch aufgrund der komplexen Natur der molekularen Krankheitsbiologie und der begrenzten Trainingsdaten Unterstützung beim Lernen aus molekularen Patientenprofilen und bei der Erstellung von Vorhersagen. Das vom Europäischen Forschungsrat finanzierte Projekt FoundationDX schließt diese Lücke durch die Entwicklung von Basismodellen unter Verwendung biomolekularer Daten, die für gesundes und krankes Gewebe verfügbar sind. Mithilfe des selbstüberwachten Lernens, einer der wichtigsten Triebkräfte der KI, soll eine umfassende Darstellung der Zellbiologie erstellt werden, ohne dass dafür gut annotierte Patientendaten erforderlich sind. Dieser Ansatz wird eine zuverlässige Vorhersage von Krebs-Subtypen und -Prognosen ermöglichen. Das Projekt zielt darauf ab, leistungsfähige Lösungen maschinellen Lernens für bisher schwierige molekulardiagnostische Probleme anzubieten.
Ziel
Molecular diagnostics is crucial in fulfilling the promise of personalized medicine. While we are amidst an AI revolution, current machine learning models (ML) struggle to effectively learn from molecular (‘omics’) patient profiles and fail to make robust predictions. Perhaps this is not a surprise. After all, molecular disease biology is immensely complex, and we ask ML models to predict such complicated things as patient prognosis, without them ‘knowing’ anything about molecular biology and based on limited training data.
To address this, I will create foundation models on top of the vast troves of available biomolecular data, such as multi-omics profiles in healthy and diseased tissues, high-resolution single-cell data and biological knowledge graphs. This unique approach is driven by self-supervised learning (SSL), an important driver of AI, which offers the opportunity to learn a comprehensive representation of the multimodal biology of the cell – without the need for well-annotated patient data.
Starting from this strong basis, the FoundationDX model can then reliably predict cancer subtype or prognosis as it no longer needs to start from scratch on too high-dimensional, too low sample-size datasets. Effectively, we give our systems biological ‘common sense’, foregoing the need for millions of labeled training samples. This uniquely enables us to address one of the most clinically relevant questions: which treatment is best for the patient?
The FoundationDX research program is designed to deliver key insights into how the SSL revolution can be used to drive progress in the field of molecular diagnostics. It contains a ‘clinical-grade’ benchmarking module and solves three urgent diagnostic challenges, including noninvasive subtyping of pediatric brain cancer. The time for powerful, robust and generalizable, knowledge-aware machine learning solutions to previously intractable molecular diagnostics problems has come. FoundationDX aims to deliver this.
Wissenschaftliches Gebiet
- natural sciencescomputer and information sciencesknowledge engineering
- social sciencespolitical sciencespolitical transitionsrevolutions
- medical and health scienceshealth sciencespersonalized medicine
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencesbiological sciencesmolecular biology
Schlüsselbegriffe
Programm/Programme
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thema/Themen
Finanzierungsplan
HORIZON-ERC - HORIZON ERC GrantsGastgebende Einrichtung
3584 CX Utrecht
Niederlande