FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282570892> ?p ?o ?g. }

• W4282570892 endingPage "104120" @default.
• W4282570892 startingPage "104120" @default.
• W4282570892 abstract "Develop a novel methodology to create a comprehensive knowledge graph (SuppKG) to represent a domain with limited coverage in the Unified Medical Language System (UMLS), specifically dietary supplement (DS) information for discovering drug-supplement interactions (DSI), by leveraging biomedical natural language processing (NLP) technologies and a DS domain terminology. We created SemRepDS (an extension of an NLP tool, SemRep), capable of extracting semantic relations from abstracts by leveraging a DS-specific terminology (iDISK) containing 28,884 DS terms not found in the UMLS. PubMed abstracts were processed using SemRepDS to generate semantic relations, which were then filtered using a PubMedBERT model to remove incorrect relations before generating SuppKG. Two discovery pathways were applied to SuppKG to identify potential DSIs, which are then compared with an existing DSI database and also evaluated by medical professionals for mechanistic plausibility. SemRepDS returned 158.5% more DS entities and 206.9% more DS relations than SemRep. The fine-tuned PubMedBERT model (significantly outperformed other machine learning and BERT models) obtained an F1 score of 0.8605 and removed 43.86% of semantic relations, improving the precision of the relations by 26.4% over pre-filtering. SuppKG consists of 56,635 nodes and 595,222 directed edges with 2,928 DS-specific nodes and 164,738 edges. Manual review of findings identified 182 of 250 (72.8%) proposed DS-Gene-Drug and 77 of 100 (77%) proposed DS-Gene1-Function-Gene2-Drug pathways to be mechanistically plausible. With added DS terminology to the UMLS, SemRepDS has the capability to find more DS-specific semantic relationships from PubMed than SemRep. The utility of the resulting SuppKG was demonstrated using discovery patterns to find novel DSIs. For the domain with limited coverage in the traditional terminology (e.g., UMLS), we demonstrated an approach to leverage domain terminology and improve existing NLP tools to generate a more comprehensive knowledge graph for the downstream task. Even this study focuses on DSI, the method may be adapted to other domains." @default.
• W4282570892 created "2022-06-14" @default.
• W4282570892 creator A5013038150 @default.
• W4282570892 creator A5016571803 @default.
• W4282570892 creator A5025296346 @default.
• W4282570892 creator A5032913460 @default.
• W4282570892 creator A5033047276 @default.
• W4282570892 creator A5052103895 @default.
• W4282570892 creator A5062552700 @default.
• W4282570892 creator A5065037360 @default.
• W4282570892 creator A5084072550 @default.
• W4282570892 creator A5089264212 @default.
• W4282570892 date "2022-07-01" @default.
• W4282570892 modified "2023-10-15" @default.
• W4282570892 title "Discovering novel drug-supplement interactions using SuppKG generated from the biomedical literature" @default.
• W4282570892 cites W1194922867 @default.
• W4282570892 cites W1550258693 @default.
• W4282570892 cites W1599615952 @default.
• W4282570892 cites W1972409985 @default.
• W4282570892 cites W2005311637 @default.
• W4282570892 cites W2029592334 @default.
• W4282570892 cites W2085860988 @default.
• W4282570892 cites W2098201295 @default.
• W4282570892 cites W2117446654 @default.
• W4282570892 cites W2122402213 @default.
• W4282570892 cites W2131046557 @default.
• W4282570892 cites W2141243519 @default.
• W4282570892 cites W2159873510 @default.
• W4282570892 cites W2160331326 @default.
• W4282570892 cites W2169540564 @default.
• W4282570892 cites W2340441220 @default.
• W4282570892 cites W2418634846 @default.
• W4282570892 cites W2522835094 @default.
• W4282570892 cites W2548017804 @default.
• W4282570892 cites W2582146834 @default.
• W4282570892 cites W2753199411 @default.
• W4282570892 cites W2810228672 @default.
• W4282570892 cites W2911489562 @default.
• W4282570892 cites W2963716420 @default.
• W4282570892 cites W2971258845 @default.
• W4282570892 cites W2998639251 @default.
• W4282570892 cites W3007352422 @default.
• W4282570892 cites W3020759564 @default.
• W4282570892 cites W3026298482 @default.
• W4282570892 cites W3087321790 @default.
• W4282570892 cites W3093150592 @default.
• W4282570892 cites W3116099552 @default.
• W4282570892 cites W3135884540 @default.
• W4282570892 cites W4233525735 @default.
• W4282570892 doi "https://doi.org/10.1016/j.jbi.2022.104120" @default.
• W4282570892 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35709900" @default.
• W4282570892 hasPublicationYear "2022" @default.
• W4282570892 type Work @default.
• W4282570892 citedByCount "6" @default.
• W4282570892 countsByYear W42825708922023 @default.
• W4282570892 crossrefType "journal-article" @default.
• W4282570892 hasAuthorship W4282570892A5013038150 @default.
• W4282570892 hasAuthorship W4282570892A5016571803 @default.
• W4282570892 hasAuthorship W4282570892A5025296346 @default.
• W4282570892 hasAuthorship W4282570892A5032913460 @default.
• W4282570892 hasAuthorship W4282570892A5033047276 @default.
• W4282570892 hasAuthorship W4282570892A5052103895 @default.
• W4282570892 hasAuthorship W4282570892A5062552700 @default.
• W4282570892 hasAuthorship W4282570892A5065037360 @default.
• W4282570892 hasAuthorship W4282570892A5084072550 @default.
• W4282570892 hasAuthorship W4282570892A5089264212 @default.
• W4282570892 hasBestOaLocation W42825708921 @default.
• W4282570892 hasConcept C110615152 @default.
• W4282570892 hasConcept C132525143 @default.
• W4282570892 hasConcept C134306372 @default.
• W4282570892 hasConcept C138885662 @default.
• W4282570892 hasConcept C154945302 @default.
• W4282570892 hasConcept C165141518 @default.
• W4282570892 hasConcept C204321447 @default.
• W4282570892 hasConcept C23123220 @default.
• W4282570892 hasConcept C33923547 @default.
• W4282570892 hasConcept C36503486 @default.
• W4282570892 hasConcept C41008148 @default.
• W4282570892 hasConcept C41895202 @default.
• W4282570892 hasConcept C511227900 @default.
• W4282570892 hasConcept C547195049 @default.
• W4282570892 hasConcept C69505689 @default.
• W4282570892 hasConcept C71472368 @default.
• W4282570892 hasConcept C80444323 @default.
• W4282570892 hasConceptScore W4282570892C110615152 @default.
• W4282570892 hasConceptScore W4282570892C132525143 @default.
• W4282570892 hasConceptScore W4282570892C134306372 @default.
• W4282570892 hasConceptScore W4282570892C138885662 @default.
• W4282570892 hasConceptScore W4282570892C154945302 @default.
• W4282570892 hasConceptScore W4282570892C165141518 @default.
• W4282570892 hasConceptScore W4282570892C204321447 @default.
• W4282570892 hasConceptScore W4282570892C23123220 @default.
• W4282570892 hasConceptScore W4282570892C33923547 @default.
• W4282570892 hasConceptScore W4282570892C36503486 @default.
• W4282570892 hasConceptScore W4282570892C41008148 @default.
• W4282570892 hasConceptScore W4282570892C41895202 @default.
• W4282570892 hasConceptScore W4282570892C511227900 @default.
• W4282570892 hasConceptScore W4282570892C547195049 @default.

• next