DOUBLER: Unified Representation Learning of Biological Entities and Documents for Predicting Protein-Disease Relationships

Abstract

MotivationWe propose a system that learns consistent representations of biological entities, such as proteins and diseases, based on a knowledge graph and additional data modalities, like structured annotations and free text describing the entities. In contrast to similar approaches, we explicitly incorporate the consistency of the representations into the learning process. In particular, we use these representations to identify novel proteins associated with diseases; these novel relationships could be used to prioritize protein targets for new drugs. ResultsWe show that our approach outperforms state-of-the-art link prediction algorithms for predicting unknown protein-disease associations. Detailed analysis demonstrates that our approach is most beneficial when additional data modalities, such as free text, are informative. AvailabilityCode and data are available at: https://github.com/nle-sztyler/research-doubler Contacttimo.sztyler@neclab.eu