Matches in SemOpenAlex for { <https://semopenalex.org/work/W2784252267> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2784252267 abstract "Molecular activity prediction is critical in drug design. Machine learning techniques such as kernel methods and random forests have been successful for this task. These models require fixed-size feature vectors as input while the molecules are variable in size and structure. As a result, fixed-size fingerprint representation is poor in handling substructures for large molecules. In addition, molecular activity tests, or a so-called BioAssays, are relatively small in the number of tested molecules due to its complexity. Here we approach the problem through deep neural networks as they are flexible in modeling structured data such as grids, sequences and graphs. We train multiple BioAssays using a multi-task learning framework, which combines information from multiple sources to improve the performance of prediction, especially on small datasets. We propose Graph Memory Network (GraphMem), a memory-augmented neural network to model the graph structure in molecules. GraphMem consists of a recurrent controller coupled with an external memory whose cells dynamically interact and change through a multi-hop reasoning process. Applied to the molecules, the dynamic interactions enable an iterative refinement of the representation of molecular graphs with multiple bond types. GraphMem is capable of jointly training on multiple datasets by using a specific-task query fed to the controller as an input. We demonstrate the effectiveness of the proposed model for separately and jointly training on more than 100K measurements, spanning across 9 BioAssay activity tests." @default.
- W2784252267 created "2018-01-26" @default.
- W2784252267 creator A5037705861 @default.
- W2784252267 creator A5045540854 @default.
- W2784252267 creator A5085471517 @default.
- W2784252267 date "2018-01-08" @default.
- W2784252267 modified "2023-09-26" @default.
- W2784252267 title "Graph Memory Networks for Molecular Activity Prediction" @default.
- W2784252267 cites W1655274992 @default.
- W2784252267 cites W1793121960 @default.
- W2784252267 cites W1974166884 @default.
- W2784252267 cites W1977405994 @default.
- W2784252267 cites W2033757486 @default.
- W2784252267 cites W2116341502 @default.
- W2784252267 cites W2131744502 @default.
- W2784252267 cites W2177508090 @default.
- W2784252267 cites W2919115771 @default.
- W2784252267 cites W2950621961 @default.
- W2784252267 cites W2963984147 @default.
- W2784252267 hasPublicationYear "2018" @default.
- W2784252267 type Work @default.
- W2784252267 sameAs 2784252267 @default.
- W2784252267 citedByCount "6" @default.
- W2784252267 countsByYear W27842522672018 @default.
- W2784252267 countsByYear W27842522672019 @default.
- W2784252267 crossrefType "posted-content" @default.
- W2784252267 hasAuthorship W2784252267A5037705861 @default.
- W2784252267 hasAuthorship W2784252267A5045540854 @default.
- W2784252267 hasAuthorship W2784252267A5085471517 @default.
- W2784252267 hasConcept C119857082 @default.
- W2784252267 hasConcept C124101348 @default.
- W2784252267 hasConcept C132525143 @default.
- W2784252267 hasConcept C154945302 @default.
- W2784252267 hasConcept C17744445 @default.
- W2784252267 hasConcept C199539241 @default.
- W2784252267 hasConcept C2776359362 @default.
- W2784252267 hasConcept C41008148 @default.
- W2784252267 hasConcept C50644808 @default.
- W2784252267 hasConcept C80444323 @default.
- W2784252267 hasConcept C94625758 @default.
- W2784252267 hasConceptScore W2784252267C119857082 @default.
- W2784252267 hasConceptScore W2784252267C124101348 @default.
- W2784252267 hasConceptScore W2784252267C132525143 @default.
- W2784252267 hasConceptScore W2784252267C154945302 @default.
- W2784252267 hasConceptScore W2784252267C17744445 @default.
- W2784252267 hasConceptScore W2784252267C199539241 @default.
- W2784252267 hasConceptScore W2784252267C2776359362 @default.
- W2784252267 hasConceptScore W2784252267C41008148 @default.
- W2784252267 hasConceptScore W2784252267C50644808 @default.
- W2784252267 hasConceptScore W2784252267C80444323 @default.
- W2784252267 hasConceptScore W2784252267C94625758 @default.
- W2784252267 hasLocation W27842522671 @default.
- W2784252267 hasOpenAccess W2784252267 @default.
- W2784252267 hasPrimaryLocation W27842522671 @default.
- W2784252267 hasRelatedWork W1278276328 @default.
- W2784252267 hasRelatedWork W13840495 @default.
- W2784252267 hasRelatedWork W2007477772 @default.
- W2784252267 hasRelatedWork W2035593643 @default.
- W2784252267 hasRelatedWork W2134499763 @default.
- W2784252267 hasRelatedWork W2557260587 @default.
- W2784252267 hasRelatedWork W2810172011 @default.
- W2784252267 hasRelatedWork W2810631159 @default.
- W2784252267 hasRelatedWork W2895788438 @default.
- W2784252267 hasRelatedWork W2901287800 @default.
- W2784252267 hasRelatedWork W2952475472 @default.
- W2784252267 hasRelatedWork W3000308450 @default.
- W2784252267 hasRelatedWork W3089084887 @default.
- W2784252267 hasRelatedWork W3092472376 @default.
- W2784252267 hasRelatedWork W3128327402 @default.
- W2784252267 hasRelatedWork W3157142061 @default.
- W2784252267 hasRelatedWork W3158246141 @default.
- W2784252267 hasRelatedWork W3185204125 @default.
- W2784252267 hasRelatedWork W3208667955 @default.
- W2784252267 hasRelatedWork W3214213376 @default.
- W2784252267 isParatext "false" @default.
- W2784252267 isRetracted "false" @default.
- W2784252267 magId "2784252267" @default.
- W2784252267 workType "article" @default.