The fourth HEAP Bring Your Own Data (BYOD#4) workshop, held in Helsinki from 20th to 22nd November 2024, enabled hands-on collaboration between HEAP exposome researchers, software developers, IT infrastructure specialists and legal experts to test and demonstrate the HEAP platform in practical exposome research.
During the workshop, researchers uploaded and analysed datasets from the Swedish cervical screening cohort, comprising over 3 million anonymised data points. From a data governance viewpoint, this cohort also tested Digital Use Conditions (DUCs) which along with Common Conditions of Use Elements (CCEs), can be used to catalogue resources and define access permissions and conditions of data reuse.
Researchers also used environmental data, comprising deep-sequenced metagenomic samples of microbes from sewage samples from 19 Swedish cities that were originally used to identify the presence of the COVID virus during the pandemic.
During hands-on sessions, these datasets were used to train Machine Learning (ML) prediction models for cervical cancer incidence, and to monitor SARS-CoV-2 presence in sewage samples. The demonstrated tools and pipelines, as well as the ML models, stimulated collaboration among the participants to find solutions for improvements and reuse.