Descripción del proyecto
Modelos fundacionales para una predicción fiable del cáncer
El diagnóstico molecular desempeña un papel crucial en la medicina personalizada. Sin embargo, los modelos de inteligencia artificial (IA) actuales necesitan ayuda para aprender de los perfiles moleculares de los pacientes y hacer predicciones debido a la compleja naturaleza de la biología molecular de las enfermedades y a los limitados datos de entrenamiento. El equipo del proyecto FoundationDX, financiado por el Consejo Europeo de Investigación, aborda esta carencia desarrollando modelos fundacionales a partir de los datos biomoleculares disponibles para tejidos sanos y enfermos. Mediante el aprendizaje autosupervisado, uno de los pilares de la IA, en el proyecto se pretende crear una representación completa de la biología celular sin necesidad de disponer de datos de pacientes bien anotados. Este método permitirá predecir con fiabilidad los subtipos de cáncer y su pronóstico. El objetivo del proyecto es ofrecer soluciones potentes de aprendizaje automático a problemas de diagnóstico molecular que hasta ahora suponían un reto.
Objetivo
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.
Ámbito científico
- 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
Palabras clave
Programa(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Régimen de financiación
HORIZON-ERC - HORIZON ERC GrantsInstitución de acogida
3584 CX Utrecht
Países Bajos