Finding melanoma drugs through a probabilistic knowledge graph

Metastatic cutaneous melanoma is an aggressive skin cancer with some progressionslowing treatments but no known cure. The omics data explosion has created many possible drug candidates; however, filtering criteria remain challenging, and systems biology approaches have become fragmented with many disconnected databases. Using drug, protein and disease interactions, we built an evidence-weighted knowledge graph of integrated interactions. Our knowledge graph-based system, ReDrugS, can be used via an application programming interface or web interface, and has generated 25 high-quality melanoma drug candidates. We show that probabilistic analysis of systems biology graphs increases drug candidate quality compared to non-probabilistic methods. Four of the 25 candidates are novel therapies, three of which have been tested with other cancers. All other candidates have current or completed clinical trials, or have been studied in in vivo or in vitro. This approach can be used to identify candidate therapies for use in research or personalized medicine.

Associated Projects

We aim to find new effective treatments for disease using existing drugs. Our approach is to gather and integrate existing data using semantic technologies to help discover promising drug repurposing.

Many diseases are based on genetic or epigenetic changes that can be targeted indirectly via upstream regulatory pathways. Targets need to have a high likelihood of affecting all possible changes, and so need to have upstream interactions that cover multiple genotypes/epigenotypes that might drive the same phenotype.