English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Learning accurate drug representation is essential for tasks such ascomputational drug repositioning and prediction of drug side-effects. A drughierarchy is a valuable source that encodes human knowledge of drug relationsin a tree-like structure where drugs that act on the same organs, treat thesame disease, or bind to the same biological target are grouped together.However, its utility in learning drug representations has not yet beenexplored, and currently described drug representations cannot place novelmolecules in a drug hierarchy. Here, we develop a semi-supervised drugembedding that incorporates two sources of information: (1) underlying chemicalgrammar that is inferred from molecular structures of drugs and drug-likemolecules (unsupervised), and (2) hierarchical relations that are encoded in anexpert-crafted hierarchy of approved drugs (supervised). We use the VariationalAuto-Encoder (VAE) framework to encode the chemical structures of molecules anduse the knowledge-based drug-drug similarity to induce the clustering of drugsin hyperbolic space. The hyperbolic space is amenable for encoding hierarchicalconcepts. Both quantitative and qualitative results support that the learneddrug embedding can accurately reproduce the chemical structure and induce thehierarchical relations among drugs. Furthermore, our approach can infer thepharmacological properties of novel molecules by retrieving similar drugs fromthe embedding space. We demonstrate that the learned drug embedding can be usedto find new uses for existing drugs and to discover side-effects. We show thatit significantly outperforms baselines in both tasks.

Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space