Descrizione del progetto
Modelli di fondazione per una previsione affidabile del cancro
La diagnostica molecolare svolge un ruolo cruciale nella medicina personalizzata. Tuttavia gli attuali modelli di IA richiedono assistenza per l’apprendimento dei profili molecolari dei pazienti e per la formulazione di previsioni, a causa della natura complessa della biologia molecolare delle malattie e dei dati di addestramento limitati. Il progetto FoundationDX, finanziato dal CER, affronta questa lacuna sviluppando modelli di fondazione utilizzando i dati biomolecolari disponibili per i tessuti sani e malati. Utilizzando l’apprendimento auto-supervisionato, un motore fondamentale dell’IA, il progetto cerca di creare una rappresentazione completa della biologia cellulare senza bisogno di dati ben annotati dei pazienti. Questo approccio consentirà di prevedere in modo affidabile i sottotipi di cancro e la relativa prognosi. Il progetto si propone di offrire potenti soluzioni di apprendimento automatico a problemi di diagnostica molecolare finora difficili.
Obiettivo
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.
Campo scientifico
- 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
Parole chiave
Programma(i)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Argomento(i)
Meccanismo di finanziamento
HORIZON-ERC - HORIZON ERC GrantsIstituzione ospitante
3584 CX Utrecht
Paesi Bassi