Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387583841> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4387583841 abstract "In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can generate molecular structures with desired properties effectively. In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence. The model's efficacy is demonstrated across numerous tasks, including generating analogues to a query structure and producing compounds with particular attributes, outperforming the baseline RNN-based methods. Our approach can be used for scaffold hopping, library expansion starting from a single molecule, and generating compounds with high predicted activity against biological targets." @default.
- W4387583841 created "2023-10-13" @default.
- W4387583841 creator A5000442596 @default.
- W4387583841 creator A5003226543 @default.
- W4387583841 creator A5049184232 @default.
- W4387583841 creator A5061746697 @default.
- W4387583841 creator A5080389605 @default.
- W4387583841 date "2023-10-08" @default.
- W4387583841 modified "2023-10-14" @default.
- W4387583841 title "Molecular De Novo Design through Transformer-based Reinforcement Learning" @default.
- W4387583841 doi "https://doi.org/10.48550/arxiv.2310.05365" @default.
- W4387583841 hasPublicationYear "2023" @default.
- W4387583841 type Work @default.
- W4387583841 citedByCount "0" @default.
- W4387583841 crossrefType "posted-content" @default.
- W4387583841 hasAuthorship W4387583841A5000442596 @default.
- W4387583841 hasAuthorship W4387583841A5003226543 @default.
- W4387583841 hasAuthorship W4387583841A5049184232 @default.
- W4387583841 hasAuthorship W4387583841A5061746697 @default.
- W4387583841 hasAuthorship W4387583841A5080389605 @default.
- W4387583841 hasBestOaLocation W43875838411 @default.
- W4387583841 hasConcept C119599485 @default.
- W4387583841 hasConcept C127413603 @default.
- W4387583841 hasConcept C147168706 @default.
- W4387583841 hasConcept C154945302 @default.
- W4387583841 hasConcept C165801399 @default.
- W4387583841 hasConcept C185592680 @default.
- W4387583841 hasConcept C2778112365 @default.
- W4387583841 hasConcept C39890363 @default.
- W4387583841 hasConcept C40506919 @default.
- W4387583841 hasConcept C41008148 @default.
- W4387583841 hasConcept C50644808 @default.
- W4387583841 hasConcept C55493867 @default.
- W4387583841 hasConcept C66322947 @default.
- W4387583841 hasConcept C97541855 @default.
- W4387583841 hasConceptScore W4387583841C119599485 @default.
- W4387583841 hasConceptScore W4387583841C127413603 @default.
- W4387583841 hasConceptScore W4387583841C147168706 @default.
- W4387583841 hasConceptScore W4387583841C154945302 @default.
- W4387583841 hasConceptScore W4387583841C165801399 @default.
- W4387583841 hasConceptScore W4387583841C185592680 @default.
- W4387583841 hasConceptScore W4387583841C2778112365 @default.
- W4387583841 hasConceptScore W4387583841C39890363 @default.
- W4387583841 hasConceptScore W4387583841C40506919 @default.
- W4387583841 hasConceptScore W4387583841C41008148 @default.
- W4387583841 hasConceptScore W4387583841C50644808 @default.
- W4387583841 hasConceptScore W4387583841C55493867 @default.
- W4387583841 hasConceptScore W4387583841C66322947 @default.
- W4387583841 hasConceptScore W4387583841C97541855 @default.
- W4387583841 hasLocation W43875838411 @default.
- W4387583841 hasOpenAccess W4387583841 @default.
- W4387583841 hasPrimaryLocation W43875838411 @default.
- W4387583841 hasRelatedWork W1847088711 @default.
- W4387583841 hasRelatedWork W2428505524 @default.
- W4387583841 hasRelatedWork W2597948870 @default.
- W4387583841 hasRelatedWork W2953061907 @default.
- W4387583841 hasRelatedWork W2962722950 @default.
- W4387583841 hasRelatedWork W3032952384 @default.
- W4387583841 hasRelatedWork W3034302643 @default.
- W4387583841 hasRelatedWork W4225394202 @default.
- W4387583841 hasRelatedWork W4298043863 @default.
- W4387583841 hasRelatedWork W4298287631 @default.
- W4387583841 isParatext "false" @default.
- W4387583841 isRetracted "false" @default.
- W4387583841 workType "article" @default.