Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

TL;DR

This paper introduces an inductive RGCN model for few-shot link prediction in heterogeneous graphs, applied to Covid-19 drug repurposing, outperforming existing models and identifying potential drug candidates.

Contribution

The paper presents a novel inductive RGCN approach that effectively learns relation embeddings in few-shot scenarios, specifically applied to drug discovery for Covid-19.

Findings

The inductive RGCN outperforms state-of-the-art models in few-shot link prediction.

Applied to DRKG, the method identified drugs in clinical trials as potential candidates.

Initial results show promising drug discovery insights for Covid-19.

Abstract

Predicting interactions among heterogenous graph structured data has numerous applications such as knowledge graph completion, recommendation systems and drug discovery. Often times, the links to be predicted belong to rare types such as the case in repurposing drugs for novel diseases. This motivates the task of few-shot link prediction. Typically, GCNs are ill-equipped in learning such rare link types since the relation embedding is not learned in an inductive fashion. This paper proposes an inductive RGCN for learning informative relation embeddings even in the few-shot learning regime. The proposed inductive model significantly outperforms the RGCN and state-of-the-art KGE models in few-shot learning tasks. Furthermore, we apply our method on the drug-repurposing knowledge graph (DRKG) for discovering drugs for Covid-19. We pose the drug discovery task as link prediction and learn embeddings for the biological entities that partake in the DRKG. Our initial results corroborate that several drugs used in clinical trials were identified as possible drug candidates. The method in this paper are implemented using the efficient deep graph learning (DGL)