Health Data Science Sandbox

We are building a health data science sandbox that supports training and research using advanced computing resources and non-person-sensitive health data.

With focus areas ranging from electronic health records to single-cell RNA-Seq data to data carpentry skills, Sandbox modules will support trainees, researchers, and educators in exploring key health domains. Training modules package large biomedical datasets, state-of-the-art tools and analysis approaches, and high performance computing resources. The Sandbox is a national project coordinated by the Center for Health Data Science at the University of Copenhagen with advisors and project scientists located at five Danish universities.

Our initial aim is to support university courses and programs in health data science and personal medicine, with broader environment access for researchers and university students provided on a rolling basis. Our sandbox for exploring health data science techniques will allow guided learning and development in an open environment using non-sensitive data followed by a smooth transition to a secure environment where users’ knowledge and tools can be applied to sensitive data. 

Sandbox datasets are currently sourced from public databases or studies while we explore privacy-preserving approaches to generating synthetic health data that resembles Danish datasets. We are building modules that pair topical datasets with recommended analysis tools, pipelines, and learning materials/tutorials in a portable, containerized format.

The sandbox environment is hosted on Danish supercomputers Computerome and UCloud with open-source module materials hosted on GitHub (organization: hds-sandbox). 

We thank the Novo Nordisk Foundation for their generous support via the Data Science Research Infrastructure funding initiative.

Please visit our website for much more information about the project.