A public-private consortium, including Euretos, recently won a very competitive grant (with about 10% success rate) from the E-Rare European Research Area Programme. The grant was awarded for a drug repurposing project for Myotonic dystrophy type 1 (DM1); the most common adult form of muscular dystrophy. DM1 affects virtually all tissues and is an incurable condition that carries significant morbidity and mortality impacting patient and family quality of life.
The consortium is lead by the Centre for Molecular and Biomolecular Informatics of the Radboud University (The Netherlands) and includes the University of Gent (Belgium), Centre de Recherche en Myologie (France), University of Ottawa (Canada), Centre d’Etude des Cellules Souches (France) and the Institute of Microbiology (Czech Republic).
In the project, a network-based bioinformatics approach shall be used to identify drug targets in DM1 molecular signatures. The project will repurpose clinically approved drugs measuring impact on molecular profiles of patients cells and the behaviour of DM1 mouse models. The drug repurposing strategy based on the reverse engineering of a positive response to a behavioural intervention may set the scene for future drug development trajectories for rare diseases.
Euretos will support a key element of the drug repurposing strategy by enabling machine learning using feature sets based on the relationships present in the Euretos AI Platform. In a recent Nature publication, this classifier model has already demonstrated that it can successfully predict drug:disease relationships with a prediction level (area under the curve) with over 90% accuracy.
In addition, Euretos will provides access to its artificial intelligence platform to the project partners. The rich knowledge base underlying the platform circumvents the need to mine individual databases and therefore accelerates the drug discovery process. Moreover, Euretos will advice on knowledge discovery and data integration strategies, which will help the consortium partners to derive actionable knowledge from large and distributed datasets
.svg)
