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

OBJECTIVE: Leverage existing biomedical NLP tools and DS domain terminologyto produce a novel and comprehensive knowledge graph containing dietarysupplement (DS) information for discovering interactions between DS and drugs,or Drug-Supplement Interactions (DSI). MATERIALS AND METHODS: We createdSemRepDS (an extension of SemRep), capable of extracting semantic relationsfrom abstracts by leveraging a DS-specific terminology (iDISK) containing28,884 DS terms not found in the UMLS. PubMed abstracts were processed usingSemRepDS to generate semantic relations, which were then filtered using aPubMedBERT-based model to remove incorrect relations before generating ourknowledge graph (SuppKG). Two pathways are used to identify potential DS-Druginteractions which are then evaluated by medical professionals for mechanisticplausibility. RESULTS: Comparison analysis found that SemRepDS returned 206.9%more DS relations and 158.5% more DS entities than SemRep. The fine-tuned BERTmodel obtained an F1 score of 0.8605 and removed 43.86% of the relations,improving the precision of the relations by 26.4% compared to pre-filtering.SuppKG consists of 2,928 DS-specific nodes. Manual review of findingsidentified 44 (88%) proposed DS-Gene-Drug and 32 (64%) proposedDS-Gene1-Function-Gene2-Drug pathways to be mechanistically plausible.DISCUSSION: The additional relations extracted using SemRepDS generated SuppKGthat was used to find plausible DSI not found in the current literature. By thenature of the SuppKG, these interactions are unlikely to have been found usingSemRep without the expanded DS terminology. CONCLUSION: We successfully extendSemRep to include DS information and produce SuppKG which can be used to findpotential DS-Drug interactions.

Discovering novel drug-supplement interactions using a dietary supplements knowledge graph generated from the biomedical literature