Gene Anonymisation and Synthetisation for Privacy
GASTRIC will investigate three aspects of microbiome sharing and analysis. First, an analysis on privacy threats in the presence of microbiome data will be conducted. Secondly, anonymization approaches will be adapted for genetic and, in particular, microbiome data. Finally, methods for the generation of synthetic data, which can be used as a means to enable privacy-preserving data mining, will be developed for microbiome data.
The human microbiome and its relations to health, diet, exercise and illness is subject to extensive research; it is studied for prediction, diagnosis and therapy of diseases, and new results about certain correlations and interactions are published on a daily basis. At the same time, the human microbiome is personal, sensitive medical data, and thus should be treated with the same care and standards as other types of medical data.
Solutions for these challenges are vital for the business development of the industrial partner, myBioma, for their current operations, as well as for new products and services.
The GASTRIC project addresses the challenge to preserve the privacy of individuals taking part in microbiome studies and microbiome sequencing projects.
- This project will thus consist of three different research strands. First, we will perform an analysis on privacy threats in the presence of microbiome data.
- Secondly, we will investigate how genetic and, in particular, microbiome data can be anonymized.
- Thirdly, synthetic data is a recently emerging trend to enable privacy-preserving data mining and analysis endeavours. In this setting, instead of anonymizing data, a new data set is generated. This greatly reduces the risk for data breaches for individuals, while at the same time retaining a high utility of the data in many application scenarios.
- The project is led by SBA Research.
This project is funded by the FFG.