This work package will provide the expertise and the computing infrastructure required to support all aspects of the ens@t-ht project. This includes creation of the ens@t-ht virtual research environment and linkage with the ENS@T-CANCER patient data registries. This work package will also ensure multi-dimensional bioinformatics modelling of omics data for the identification of omics-derived biomarkers. The specific objectives of this WP are:

1. Definition of the ENSAT-HT schema utilizing structures and information from the ENS@T-CANCER systems.
2. Establishment and population of the ENSAT-HT registry including patients recruited from the ENS@T systems (and the on-going linkage of the two).
3. Develop the governance and data sharing protocols and security processes to support the other WPs.
4. Load, link, and transform the omics data from the ENSAT-HT study cohort from WP2 and WP3 into the HIC system and provide security-oriented linkages with the ENSAT-HT phenotypic database hosted at MEG.
5. Support for the clinical trials (eCRFs) and databases in WP4 and their linkages with the ENS@T and ENSAT-HT registries;
6. Create user interfaces to allow data annotation from both local and standard ‘omics’ reference sources.
7. Configure the infrastructure and hardware to host the ENSAT-HT study ‘omics’ data sets within a Safe Haven environment.
8. Systematic review of literature to understand the current state of knowledge about machine learning algorithms on ‘omics’ datasets
9. Develop bioinformatics tools and modelling for data analysis including support for advanced machine learning-driven data analytics;
10. Apply data-driven bioinformatics modelling approaches to biomarker identification and discovery
11. Supply molecular signatures for validation by WP4.