There has long been a pressing need to exploit efficiently research results in patient care. One of the key problems has been in linking clinically relevant information to the knowledge obtained across multiple disciplines, experimental platforms, and biological systems.
The megNet enables integrative mining of e.g., molecular interactions, genomes, gene expression profiles, metabolic profiles, medical images and clinical data. VTT is currently applying the megNet to combine medical image and metabolomic data in search of new biomarkers for various diseases. The objective is also to link preclinical and clinical data in pharmaceutical development and health care with the megNet tool.
VTT has applied in the development work of megNet conceptual space theory for mining and visualizing life science and medical data. This includes state-of-the-art 3D techniques, mathematical modelling and contextualization. The theory of conceptual spaces combines elements from other theories in cognitive science, psychology and linguistics. It is based on the topological analysis of the information space that enables similarity to be modelled and computed in a natural way. It suits well for integration of complex clinical data such as medical images with molecular level information.
VTT has already applied the megNet software tool in its research projects. In the VISUBIOMED project the researchers analysed cardiac magnetic resonance images and will do the same in other future clinical data related to cardiac diseases. Metabolomics analyses can be performed from serum samples of the same patients. The data was complemented with molecular network information and with information on molecular interactions related to the disease. In the TRANSCENDO project VTT applied the megNet in order to elucidate molecular pathways in the early stages of type 1 diabetes. The work has been done in collaboration with hospitals.