“The challenge of precision medicine is to improve the diagnosis and treatment of diseases”
Working on genomic data sharing and AI for precision medicine
NASERTIC, together with the Foundation for Applied Medical Research, Clínica Universidad de Navarra and the company Data Value Management are working together genomic data sharing. This type of data is special because of its large size and the need to maintain its privacy.
The main objective is to prove that the data can be shared, and that AI techniques can be used with them. This initiative, called MARGA (Advanced Genomic Architecture Model) uses technology required for the creation of a shared, secure and reliable genomic data space. The challenge is to move towards medicine that improves diagnosis and treatment of diseases.
The MARGA initiative has the technical support of TECNALIA
- TECNALIA integrates the components of the data space to solve some problems that arose in its development and that had not been foreseen, which means that it has also contributed to the software development community for these components.
- TECNALIA trains the participants’ IT departments in the installation and integration of the connectors (these are responsible for enabling the exercise of data sovereignty; the owners of the data determine at all times under which conditions it can be operated), and so they know how to configure them.
Sharing genomic data
Genomic data spaces allow healthcare professionals to access genomic information (which involves the study of the entire genetic material of an organism) more quickly and efficiently.
These genomic data spaces are secure platforms where large volumes of patient genetic sequencing data are stored and shared, integrating this information with other clinical data, such as medical history, environmental factors and general health data.
Integration of components in the data space
Data space technology opens up the opportunity for data that is not available, due to lack of trust or lack of exploitation models, to be brought out and used to devise more complex exploitation models.
It is a pioneering project that enables public and private entities that have genomic data to make it available to actors that develop applications that work on this data, so that collaboration increases and it is possible to have a larger amount of data for research and clinical applications.
