Hyperbolic Molecular Representation Learning for Drug Repositioning

TL;DR

This paper introduces a semi-supervised hyperbolic embedding method for drugs that combines chemical structure analysis with hierarchical drug relations, improving drug repositioning capabilities.

Contribution

It develops a novel hyperbolic embedding framework that integrates chemical grammar and hierarchical drug knowledge for better drug representation.

Findings

Embeddings effectively encode hierarchical drug relations.

The method improves drug repositioning accuracy.

Qualitative analysis shows meaningful drug clustering.

Abstract

Learning accurate drug representations is essential for task such as computational drug repositioning. A drug hierarchy is a valuable source that encodes knowledge of relations among drugs in a tree-like structure where drugs that act on the same organs, treat the same disease, or bind to the same biological target are grouped together. However, its utility in learning drug representations has not yet been explored, and currently described drug representations cannot place novel molecules in a drug hierarchy. Here, we develop a semi-supervised drug embedding that incorporates two sources of information: (1) underlying chemical grammar that is inferred from chemical structures of drugs and drug-like molecules (unsupervised), and (2) hierarchical relations that are encoded in an expert-crafted hierarchy of approved drugs (supervised). We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the drug-drug similarity information obtained from the hierarchy to induce the clustering of drugs in hyperbolic space. The hyperbolic space is amenable for encoding hierarchical relations. Our qualitative results support that the learned drug embedding can induce the hierarchical relations among drugs. We demonstrate that the learned drug embedding can be used for drug repositioning.