PhD: Foundation Models for Clinical Bioinformatics

DTU Sundhedsteknologi (Kgs. Lyngby); Kongens Lyngby; On-site; DKK 336,000 - 408,000; Full time

Job summary

DTU Sundhedsteknologi (Kgs. Lyngby) invites applications for a PhD scholarship in foundation models for clinical bioinformatics and cancer prevention.

The project is a collaboration between DTU Health Tech and CSS at University Hospital Zealand, focusing on integrating nationwide health data with omics data to predict postoperative recurrence in colorectal cancer. You will develop AI and ML models, work with clinical and computational researchers, and contribute to representations of patient

Qualifications

• A master's degree in bioinformatics, computer science, computational biology, data science, biomedical engineering, statistics, or a related quantitative field.
• Experience with statistical analysis and machine learning.
• Experience handling and analyzing large-scale biological or health-related datasets.

Responsibilities

• Develop and apply machine learning and foundation-model approaches for large-scale longitudinal health data and large-scale genomic data.
• Integrate clinical, microbiome, and genomic data to uncover factors associated with adenoma progression and colorectal cancer development.
• Develop computational representations of patient trajectories and microbial communities using modern AI and bioinformatics methodologies.

Skills

Statistical analysis

Machine learning

Large-scale data handling

Education

Two-year master's degree (120 ECTS) or equivalent

Job description

DTU Sundhedsteknologi (Kgs. Lyngby) invites applications for a PhD scholarship in foundation models for clinical bioinformatics and cancer prevention.

The project is a collaboration between DTU Health Tech and CSS at University Hospital Zealand, focusing on integrating nationwide health data with omics data to predict postoperative recurrence in colorectal cancer. You will develop AI and ML models, work with clinical and computational researchers, and contribute to representations of patient