PhD in AI-Powered Multimodal Data Fusion for Rare Diseases

KU Leuven; Vlaams-Brabant; Sur place; EUR 29 000 - 36 000; Plein temps

Avantages offerts par ce poste

Holiday pay

Hospitalization insurance

Commuting cost reimbursement

Sports and childcare facilities

Résumé du poste

KU Leuven, Department of Human Genetics, Leuven, Belgium, invites applications for a 48-month full-time PhD fellowship. The project focuses on zero-shot multimodal fusion models for rare disease prediction, integrating spatial and single-cell multi-omics with histopathology and clinical data.

Based in the MSCA SPACE-MEL network, you will develop machine-learning strategies for multimodal representation learning, access to high-performance computing, and secondments in international partner labs;

Qualifications

• Master's degree in Bioinformatics, Computer Science, AI, Bioscience Engineering or related field, obtained by start date.
• Applicants must be doctoral candidates, not holding a doctoral degree.
• Mobility rule: no residence or main activity in Belgium >12 months in 36 months before recruitment.

Responsabilités

• Develop and benchmark zero-shot multimodal fusion models for rare disease prediction.
• Integrate spatial and single-cell multi-omics data with histopathology and clinical information.
• Develop ML strategies for multimodal representation learning.
• Participate in secondments to partner labs and collaborate across institutions.

Connaissances

Python

PyTorch

Machine learning

Linux

HPC/GPU

Git

Conda/Containers

Snakemake/Nextflow

English

Formation

Master's degree in Bioinformatics, Computer Science, Artificial Intelligence, Bioscience Engineering or related field

Outils

Docker

Snakemake

Nextflow

Conda

Description du poste

KU Leuven, Department of Human Genetics, Leuven, Belgium, invites applications for a 48-month full-time PhD fellowship. The project focuses on zero-shot multimodal fusion models for rare disease prediction, integrating spatial and single-cell multi-omics with histopathology and clinical data.

Based in the MSCA SPACE-MEL network, you will develop machine-learning strategies for multimodal representation learning, access to high-performance computing, and secondments in international partner labs;