Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113037061> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3113037061 endingPage "5498" @default.
- W3113037061 startingPage "5492" @default.
- W3113037061 abstract "Abstract Motivation Quantitative structure-activity relationship (QSAR) analysis is commonly used in drug discovery. Collaborations among pharmaceutical institutions can lead to a better performance in QSAR prediction, however, intellectual property and related financial interests remain substantially hindering inter-institutional collaborations in QSAR modeling for drug discovery. Results For the first time, we verified the feasibility of applying the horizontal federated learning (HFL), which is a recently developed collaborative and privacy-preserving learning framework to perform QSAR analysis. A prototype platform of federated-learning-based QSAR modeling for collaborative drug discovery, i.e. FL-QSAR, is presented accordingly. We first compared the HFL framework with a classic privacy-preserving computation framework, i.e. secure multiparty computation to indicate its difference from various perspective. Then we compared FL-QSAR with the public collaboration in terms of QSAR modeling. Our extensive experiments demonstrated that (i) collaboration by FL-QSAR outperforms a single client using only its private data, and (ii) collaboration by FL-QSAR achieves almost the same performance as that of collaboration via cleartext learning algorithms using all shared information. Taking together, our results indicate that FL-QSAR under the HFL framework provides an efficient solution to break the barriers between pharmaceutical institutions in QSAR modeling, therefore promote the development of collaborative and privacy-preserving drug discovery with extendable ability to other privacy-related biomedical areas. Availability and implementation The source codes of FL-QSAR are available on the GitHub: https://github.com/bm2-lab/FL-QSAR. Supplementary information Supplementary data are available at Bioinformatics online." @default.
- W3113037061 created "2020-12-21" @default.
- W3113037061 creator A5018143257 @default.
- W3113037061 creator A5032083590 @default.
- W3113037061 creator A5054707442 @default.
- W3113037061 creator A5085028455 @default.
- W3113037061 creator A5089940875 @default.
- W3113037061 date "2020-12-01" @default.
- W3113037061 modified "2023-10-16" @default.
- W3113037061 title "FL-QSAR: a federated learning-based QSAR prototype for collaborative drug discovery" @default.
- W3113037061 cites W1999798000 @default.
- W3113037061 cites W2593870237 @default.
- W3113037061 cites W2607075141 @default.
- W3113037061 cites W2747433492 @default.
- W3113037061 cites W2798456213 @default.
- W3113037061 cites W2800679800 @default.
- W3113037061 cites W2887447356 @default.
- W3113037061 cites W2896757914 @default.
- W3113037061 cites W2937307539 @default.
- W3113037061 cites W2949272108 @default.
- W3113037061 cites W2952016241 @default.
- W3113037061 cites W2995191368 @default.
- W3113037061 cites W2999351157 @default.
- W3113037061 cites W3141585064 @default.
- W3113037061 doi "https://doi.org/10.1093/bioinformatics/btaa1006" @default.
- W3113037061 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33289524" @default.
- W3113037061 hasPublicationYear "2020" @default.
- W3113037061 type Work @default.
- W3113037061 sameAs 3113037061 @default.
- W3113037061 citedByCount "31" @default.
- W3113037061 countsByYear W31130370612021 @default.
- W3113037061 countsByYear W31130370612022 @default.
- W3113037061 countsByYear W31130370612023 @default.
- W3113037061 crossrefType "journal-article" @default.
- W3113037061 hasAuthorship W3113037061A5018143257 @default.
- W3113037061 hasAuthorship W3113037061A5032083590 @default.
- W3113037061 hasAuthorship W3113037061A5054707442 @default.
- W3113037061 hasAuthorship W3113037061A5085028455 @default.
- W3113037061 hasAuthorship W3113037061A5089940875 @default.
- W3113037061 hasBestOaLocation W31130370612 @default.
- W3113037061 hasConcept C118552586 @default.
- W3113037061 hasConcept C119857082 @default.
- W3113037061 hasConcept C154945302 @default.
- W3113037061 hasConcept C164126121 @default.
- W3113037061 hasConcept C185592680 @default.
- W3113037061 hasConcept C2780035454 @default.
- W3113037061 hasConcept C3018146709 @default.
- W3113037061 hasConcept C41008148 @default.
- W3113037061 hasConcept C55493867 @default.
- W3113037061 hasConcept C71924100 @default.
- W3113037061 hasConcept C74187038 @default.
- W3113037061 hasConceptScore W3113037061C118552586 @default.
- W3113037061 hasConceptScore W3113037061C119857082 @default.
- W3113037061 hasConceptScore W3113037061C154945302 @default.
- W3113037061 hasConceptScore W3113037061C164126121 @default.
- W3113037061 hasConceptScore W3113037061C185592680 @default.
- W3113037061 hasConceptScore W3113037061C2780035454 @default.
- W3113037061 hasConceptScore W3113037061C3018146709 @default.
- W3113037061 hasConceptScore W3113037061C41008148 @default.
- W3113037061 hasConceptScore W3113037061C55493867 @default.
- W3113037061 hasConceptScore W3113037061C71924100 @default.
- W3113037061 hasConceptScore W3113037061C74187038 @default.
- W3113037061 hasFunder F4320321001 @default.
- W3113037061 hasFunder F4320335777 @default.
- W3113037061 hasFunder F4320335787 @default.
- W3113037061 hasIssue "22-23" @default.
- W3113037061 hasLocation W31130370611 @default.
- W3113037061 hasLocation W31130370612 @default.
- W3113037061 hasOpenAccess W3113037061 @default.
- W3113037061 hasPrimaryLocation W31130370611 @default.
- W3113037061 hasRelatedWork W2045517587 @default.
- W3113037061 hasRelatedWork W2150555232 @default.
- W3113037061 hasRelatedWork W2951530177 @default.
- W3113037061 hasRelatedWork W2978058147 @default.
- W3113037061 hasRelatedWork W3040907557 @default.
- W3113037061 hasRelatedWork W3092524006 @default.
- W3113037061 hasRelatedWork W3117501106 @default.
- W3113037061 hasRelatedWork W4210854019 @default.
- W3113037061 hasRelatedWork W4223889031 @default.
- W3113037061 hasRelatedWork W4309710797 @default.
- W3113037061 hasVolume "36" @default.
- W3113037061 isParatext "false" @default.
- W3113037061 isRetracted "false" @default.
- W3113037061 magId "3113037061" @default.
- W3113037061 workType "article" @default.