Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793371569> ?p ?o ?g. }
- W2793371569 endingPage "2836" @default.
- W2793371569 startingPage "2825" @default.
- W2793371569 abstract "This article describes an unsupervised machine learning method for computing distributed vector representation of molecular fragments. These vectors encode fragment features in a continuous high-dimensional space and enable similarity computation between individual fragments, even for small fragments with only two heavy atoms. The method is based on a word embedding algorithm borrowed from natural language processing field, and approximately 6 million unlabeled PubChem chemicals were used for training. The resulting dense fragment vectors are in contrast to the traditional sparse “one-hot” fragment representation and capture rich relational structure in the fragment space. The vectors of small linear fragments were averaged to yield distributed vectors of bigger fragments and molecules, which were used for different tasks, e.g., clustering, ligand recall, and quantitative structure–activity relationship modeling. The distributed vectors were found to be better at clustering ring systems and recall of kinase ligands as compared to standard binary fingerprints. This work demonstrates unsupervised learning of fragment chemistry from large sets of unlabeled chemical structures and subsequent application to supervised training on relatively small data sets of labeled chemicals." @default.
- W2793371569 created "2018-03-29" @default.
- W2793371569 creator A5006751935 @default.
- W2793371569 date "2018-03-08" @default.
- W2793371569 modified "2023-09-26" @default.
- W2793371569 title "Distributed Representation of Chemical Fragments" @default.
- W2793371569 cites W1501531009 @default.
- W2793371569 cites W1964981516 @default.
- W2793371569 cites W1968319881 @default.
- W2793371569 cites W1975147762 @default.
- W2793371569 cites W1977340881 @default.
- W2793371569 cites W1988037271 @default.
- W2793371569 cites W2002653560 @default.
- W2793371569 cites W2024057175 @default.
- W2793371569 cites W2032008870 @default.
- W2793371569 cites W2034998435 @default.
- W2793371569 cites W2038702914 @default.
- W2793371569 cites W2048312836 @default.
- W2793371569 cites W2066532920 @default.
- W2793371569 cites W2117130368 @default.
- W2793371569 cites W2119512897 @default.
- W2793371569 cites W2150593711 @default.
- W2793371569 cites W2412446857 @default.
- W2793371569 cites W2414870557 @default.
- W2793371569 cites W2777416523 @default.
- W2793371569 doi "https://doi.org/10.1021/acsomega.7b02045" @default.
- W2793371569 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6044751" @default.
- W2793371569 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30023852" @default.
- W2793371569 hasPublicationYear "2018" @default.
- W2793371569 type Work @default.
- W2793371569 sameAs 2793371569 @default.
- W2793371569 citedByCount "23" @default.
- W2793371569 countsByYear W27933715692018 @default.
- W2793371569 countsByYear W27933715692019 @default.
- W2793371569 countsByYear W27933715692020 @default.
- W2793371569 countsByYear W27933715692021 @default.
- W2793371569 countsByYear W27933715692022 @default.
- W2793371569 countsByYear W27933715692023 @default.
- W2793371569 crossrefType "journal-article" @default.
- W2793371569 hasAuthorship W2793371569A5006751935 @default.
- W2793371569 hasBestOaLocation W27933715691 @default.
- W2793371569 hasConcept C103278499 @default.
- W2793371569 hasConcept C11413529 @default.
- W2793371569 hasConcept C115961682 @default.
- W2793371569 hasConcept C153180895 @default.
- W2793371569 hasConcept C154945302 @default.
- W2793371569 hasConcept C158180186 @default.
- W2793371569 hasConcept C17744445 @default.
- W2793371569 hasConcept C199539241 @default.
- W2793371569 hasConcept C2776235265 @default.
- W2793371569 hasConcept C2776359362 @default.
- W2793371569 hasConcept C41008148 @default.
- W2793371569 hasConcept C41608201 @default.
- W2793371569 hasConcept C60644358 @default.
- W2793371569 hasConcept C70721500 @default.
- W2793371569 hasConcept C73555534 @default.
- W2793371569 hasConcept C74187038 @default.
- W2793371569 hasConcept C86803240 @default.
- W2793371569 hasConcept C94625758 @default.
- W2793371569 hasConcept C99726746 @default.
- W2793371569 hasConceptScore W2793371569C103278499 @default.
- W2793371569 hasConceptScore W2793371569C11413529 @default.
- W2793371569 hasConceptScore W2793371569C115961682 @default.
- W2793371569 hasConceptScore W2793371569C153180895 @default.
- W2793371569 hasConceptScore W2793371569C154945302 @default.
- W2793371569 hasConceptScore W2793371569C158180186 @default.
- W2793371569 hasConceptScore W2793371569C17744445 @default.
- W2793371569 hasConceptScore W2793371569C199539241 @default.
- W2793371569 hasConceptScore W2793371569C2776235265 @default.
- W2793371569 hasConceptScore W2793371569C2776359362 @default.
- W2793371569 hasConceptScore W2793371569C41008148 @default.
- W2793371569 hasConceptScore W2793371569C41608201 @default.
- W2793371569 hasConceptScore W2793371569C60644358 @default.
- W2793371569 hasConceptScore W2793371569C70721500 @default.
- W2793371569 hasConceptScore W2793371569C73555534 @default.
- W2793371569 hasConceptScore W2793371569C74187038 @default.
- W2793371569 hasConceptScore W2793371569C86803240 @default.
- W2793371569 hasConceptScore W2793371569C94625758 @default.
- W2793371569 hasConceptScore W2793371569C99726746 @default.
- W2793371569 hasIssue "3" @default.
- W2793371569 hasLocation W27933715691 @default.
- W2793371569 hasLocation W27933715692 @default.
- W2793371569 hasLocation W27933715693 @default.
- W2793371569 hasLocation W27933715694 @default.
- W2793371569 hasOpenAccess W2793371569 @default.
- W2793371569 hasPrimaryLocation W27933715691 @default.
- W2793371569 hasRelatedWork W1457719682 @default.
- W2793371569 hasRelatedWork W1998200301 @default.
- W2793371569 hasRelatedWork W2076606819 @default.
- W2793371569 hasRelatedWork W2150220167 @default.
- W2793371569 hasRelatedWork W2151971404 @default.
- W2793371569 hasRelatedWork W2770765812 @default.
- W2793371569 hasRelatedWork W2793371569 @default.
- W2793371569 hasRelatedWork W2912933387 @default.
- W2793371569 hasRelatedWork W2997669297 @default.
- W2793371569 hasRelatedWork W4291624975 @default.
- W2793371569 hasVolume "3" @default.
- W2793371569 isParatext "false" @default.