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

Link prediction in biomedical knowledge graphs (KGs) aims at predictingunknown interactions between entities, including drug-target interaction (DTI)and drug-drug interaction (DDI), which is critical for drug discovery andtherapeutics. Previous methods prefer to utilize the rich semantic relationsand topological structure of the KG to predict missing links, yieldingpromising outcomes. However, all these works only focus on improving thepredictive performance without considering the inevitable noise and unreliableinteractions existing in the KGs, which limits the development of KG-basedcomputational methods. To address these limitations, we propose a Denoised LinkPrediction framework, called DenoisedLP. DenoisedLP obtains reliableinteractions based on the local subgraph by denoising noisy links in alearnable way, providing a universal module for mining underlying task-relevantrelations. To collaborate with the smoothed semantic information, DenoisedLPintroduces the semantic subgraph by blurring conflict relations around thepredicted link. By maximizing the mutual information between the reliablestructure and smoothed semantic relations, DenoisedLP emphasizes theinformative interactions for predicting relation-specific links. Experimentalresults on real-world datasets demonstrate that DenoisedLP outperformsstate-of-the-art methods on DTI and DDI prediction tasks, and verify theeffectiveness and robustness of denoising unreliable interactions on thecontaminated KGs.

Learning to Denoise Unreliable Interactions for Link Prediction on Biomedical Knowledge Graph