Our most recent publication is about using molecular network information like from protein interaction networks, and graph neural network based deep learning to identify core genes directly involved in the mechanisms of complex disease.

Ratajczak F, Joblin M, Hildebrandt M, Ringsquandl M, Falter-Braun P*, Heinig M*, Speos: An ensemble graph representation learning framework to predict core genes for complex diseases, Nat. Commun. 2023 Nov 08, doi 10.1038/s41467-023-42975-z  Our most recent publication is about using molecular network information like from protein interaction networks, and graph neural network based deep learning to identifycore genes directlyinvolved in themechanisms of complex disease. In validationsacrossmouseknockouts, wesee a multiple enrichment of relevant phenotypescomparedto GWAS genes. Importantly, thesecore genes aresuitabledrugtargets.