Hypergraph Link Prediction: Learning Drug Interaction Networks Embeddings

Vaida, Maria; Purcell, Kevin M.

doi:10.1109/icmla.2019.00299

Cited by 12 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypergraph, as a generalization of the regular graph data, is ubiquitous in various domains, and has drawn increasing attention recently [26,36,37]. Different from traditional regular graphs, which consist of nodes and edges to represent pairwise relations between nodes, the hyperedges in the hypergraphs contain a collection of nodes, which represent high-order relations.…”

Section: Introductionmentioning

confidence: 99%

“…Different from traditional regular graphs, which consist of nodes and edges to represent pairwise relations between nodes, the hyperedges in the hypergraphs contain a collection of nodes, which represent high-order relations. For example, in the clinical studies of the pharmacological mechanism [24,26], the effects of medical treatment is often the result of the combined interactions of a set of drugs. Here the combination of drugs for one disease could consist of one hyperedge.…”

Section: Introductionmentioning

confidence: 99%

“…To date, relatively few works on hypergraph representation learning exist, most of which primarily focus on hyperlink prediction (e.g. [25], [37], [26], [31]). The major difficulties of representation learning on hypergraph are two-fold.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hypergraph Pre-training with Graph Neural Networks

Du¹,

Yuan²,

Barton³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite the prevalence of hypergraphs in a variety of high-impact applications, there are relatively few works on hypergraph representation learning, most of which primarily focus on hyperlink prediction, and often restricted to the transductive learning setting. Among others, a major hurdle for effective hypergraph representation learning lies in the label scarcity of nodes and/or hyperedges. To address this issue, this paper presents an end-to-end, bi-level pre-training strategy with Graph Neural Networks for hypergraphs. The proposed framework named HyperGene bears three distinctive advantages. First, it is capable of ingesting the labeling information when available, but more importantly, it is mainly designed in the self-supervised fashion which significantly broadens its applicability. Second, at the heart of the proposed HyperGene are two carefully designed pretexts, one on the node level and the other on the hyperedge level, which enable us to encode both the local and the global context in a mutually complementary way. Third, the proposed framework can work in both transductive and inductive settings. When applying the two proposed pretexts in tandem, it can accelerate the adaptation of the knowledge from the pre-trained model to downstream applications in the transductive setting, thanks to the bi-level nature of the proposed method. The extensive experimental results demonstrate that: (1) HyperGene achieves up to 5.69% improvements in hyperedge classification, and (2) improves pre-training efficiency by up to 42.80% on average.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hypergraph Pre-training with Graph Neural Networks

Du¹,

Yuan²,

Barton³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There are precedents for modeling biological networks using hypergraphs, but they have not been used to predict DTIs. Vaida et al 24 modeled relations between pairs of drugs as a hypergraph and used a two-layer graph convolution neural network as an encoder to predict drug interactions. Niu et al 25 used diseases as hyperedges, connected microbes associated with them, and developed a hypergraph-based random walk model for microbe-disease association prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Vaida et al. 24 modeled relations between pairs of drugs as a hypergraph and used a two-layer graph convolution neural network as an encoder to predict drug interactions. Niu et al.…”

Section: Introductionmentioning

confidence: 99%

Exploring complex and heterogeneous correlations on hypergraph for the prediction of drug-target interactions

Ruan

Ji²,

Yan³

et al. 2021

Patterns

View full text Add to dashboard Cite

Summary The continuous emergence of drug-target interaction data provides an opportunity to construct a biological network for systematically discovering unknown interactions. However, this is challenging due to complex and heterogeneous correlations between drug and target. Here, we describe a heterogeneous hypergraph-based framework for drug-target interaction (HHDTI) predictions by modeling biological networks through a hypergraph, where each vertex represents a drug or a target and a hyperedge indicates existing similar interactions or associations between the connected vertices. The hypergraph is then trained to generate suitably structured embeddings for discovering unknown interactions. Comprehensive experiments performed on four public datasets demonstrate that HHDTI achieves significant and consistently improved predictions compared with state-of-the-art methods. Our analysis indicates that this superior performance is due to the ability to integrate heterogeneous high-order information from the hypergraph learning. These results suggest that HHDTI is a scalable and practical tool for uncovering novel drug-target interactions.

show abstract