Built on the concept of knowledge-driven ecosystems, the TrustKG framework represents a data ecosystem of heterogeneous data sources. Knowledge extracted from heterogeneous sources, e.g., clinical records, scientific publications, and pharmacologic data, is integrated into knowledge graphs. Ontologies describe the meaning of the combined data, and mapping rules enable the declarative definition of the transformation and integration processes. Moreover, the TrustKG framework is assessed in terms of the methods followed for data quality assessment and curation. Lastly, the role of controlled vocabularies and ontologies in data management is discussed and their impact on transparent knowledge extraction and analytics. The following figure illustrates the main components of the TrustKG framework.

The TrustKG framework is applied in the context of the lung cancer pilots in the EU H2020 funded project BigMedilytics, the ERA PerMed funded project P4-LUCAT, the EU H2020 projects IASIS and CLARIFY, and ImProVIT. Moreover, TrustKG has been used in the implementation of the Knowledge4COVID-19 knowledge graph.

The TrustKG framework is also applied in the industry domain.

The TrustKG framework provides the basis to create an intelligent platform built on industry-wide value and supply chains in the context of CoyPU, a project funded by the German Federal Ministry for Economic Affairs and Climate Protection in the artificial intelligence innovation competition (BMWK). Lastly, TrustKG provides the basis for building the PLATOON knowledge graph in the context of the EU-funded H2020 project PLATOON with the aim to digitalize the energy sector, ad enable data exchange while ensuring privacy and sovereignty.

The following components compose the TrustKG framework platform,