Matches in SemOpenAlex for { <https://semopenalex.org/work/W4245372219> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4245372219 abstract "In recent years, deep molecular generative models have emerged as novel methods for de novo molecular design. Thanks to the rapid advance of deep learning techniques, deep learning architectures such as recurrent neural networks, generative autoencoders, and adversarial networks, to give a few examples, have been employed for constructing generative models. However, so far the metrics used to evaluate these deep generative models are not discriminative enough to separate the performance of various state-of-the-art generative models. This work presents a novel metric for evaluating deep molecular generative models; this new metric is based on the chemical space coverage of a reference database, and compares not only the molecular structures, but also the ring systems and functional groups, reproduced from a reference dataset of 1M structures. In this study, the performance of 7 different molecular generative models was compared by calculating their structure and substructure coverage of the GDB-13 database while using a 1M subset of GDB-13 for training. Our study shows that the performance of various generative models varies significantly using the benchmarking metrics introduced herein, such that generalization capability of the generative model can be clearly differentiated. Additionally, the coverage of ring systems and functional groups existing in GDB-13 was also compared between the models. Our study provides a useful new metric that can be used for evaluating and comparing generative models." @default.
- W4245372219 created "2022-05-12" @default.
- W4245372219 creator A5022033626 @default.
- W4245372219 creator A5063816637 @default.
- W4245372219 creator A5076975589 @default.
- W4245372219 creator A5090993508 @default.
- W4245372219 date "2020-11-16" @default.
- W4245372219 modified "2023-09-23" @default.
- W4245372219 title "Comparative Study of Deep Generative Models on Chemical Space Coverage" @default.
- W4245372219 doi "https://doi.org/10.26434/chemrxiv.13234289.v1" @default.
- W4245372219 hasPublicationYear "2020" @default.
- W4245372219 type Work @default.
- W4245372219 citedByCount "5" @default.
- W4245372219 countsByYear W42453722192020 @default.
- W4245372219 countsByYear W42453722192021 @default.
- W4245372219 countsByYear W42453722192022 @default.
- W4245372219 crossrefType "posted-content" @default.
- W4245372219 hasAuthorship W4245372219A5022033626 @default.
- W4245372219 hasAuthorship W4245372219A5063816637 @default.
- W4245372219 hasAuthorship W4245372219A5076975589 @default.
- W4245372219 hasAuthorship W4245372219A5090993508 @default.
- W4245372219 hasBestOaLocation W42453722191 @default.
- W4245372219 hasConcept C108583219 @default.
- W4245372219 hasConcept C119857082 @default.
- W4245372219 hasConcept C127413603 @default.
- W4245372219 hasConcept C13280743 @default.
- W4245372219 hasConcept C134306372 @default.
- W4245372219 hasConcept C154945302 @default.
- W4245372219 hasConcept C167966045 @default.
- W4245372219 hasConcept C176217482 @default.
- W4245372219 hasConcept C177148314 @default.
- W4245372219 hasConcept C184408114 @default.
- W4245372219 hasConcept C185798385 @default.
- W4245372219 hasConcept C205649164 @default.
- W4245372219 hasConcept C21547014 @default.
- W4245372219 hasConcept C33923547 @default.
- W4245372219 hasConcept C39890363 @default.
- W4245372219 hasConcept C41008148 @default.
- W4245372219 hasConcept C60644358 @default.
- W4245372219 hasConcept C74187038 @default.
- W4245372219 hasConcept C86803240 @default.
- W4245372219 hasConcept C97931131 @default.
- W4245372219 hasConcept C99726746 @default.
- W4245372219 hasConceptScore W4245372219C108583219 @default.
- W4245372219 hasConceptScore W4245372219C119857082 @default.
- W4245372219 hasConceptScore W4245372219C127413603 @default.
- W4245372219 hasConceptScore W4245372219C13280743 @default.
- W4245372219 hasConceptScore W4245372219C134306372 @default.
- W4245372219 hasConceptScore W4245372219C154945302 @default.
- W4245372219 hasConceptScore W4245372219C167966045 @default.
- W4245372219 hasConceptScore W4245372219C176217482 @default.
- W4245372219 hasConceptScore W4245372219C177148314 @default.
- W4245372219 hasConceptScore W4245372219C184408114 @default.
- W4245372219 hasConceptScore W4245372219C185798385 @default.
- W4245372219 hasConceptScore W4245372219C205649164 @default.
- W4245372219 hasConceptScore W4245372219C21547014 @default.
- W4245372219 hasConceptScore W4245372219C33923547 @default.
- W4245372219 hasConceptScore W4245372219C39890363 @default.
- W4245372219 hasConceptScore W4245372219C41008148 @default.
- W4245372219 hasConceptScore W4245372219C60644358 @default.
- W4245372219 hasConceptScore W4245372219C74187038 @default.
- W4245372219 hasConceptScore W4245372219C86803240 @default.
- W4245372219 hasConceptScore W4245372219C97931131 @default.
- W4245372219 hasConceptScore W4245372219C99726746 @default.
- W4245372219 hasLocation W42453722191 @default.
- W4245372219 hasLocation W42453722192 @default.
- W4245372219 hasOpenAccess W4245372219 @default.
- W4245372219 hasPrimaryLocation W42453722191 @default.
- W4245372219 hasRelatedWork W2353457699 @default.
- W4245372219 hasRelatedWork W2462891905 @default.
- W4245372219 hasRelatedWork W2475221136 @default.
- W4245372219 hasRelatedWork W2560791808 @default.
- W4245372219 hasRelatedWork W2944874434 @default.
- W4245372219 hasRelatedWork W3020939278 @default.
- W4245372219 hasRelatedWork W3110370715 @default.
- W4245372219 hasRelatedWork W4287811065 @default.
- W4245372219 hasRelatedWork W4311430276 @default.
- W4245372219 hasRelatedWork W4319994054 @default.
- W4245372219 isParatext "false" @default.
- W4245372219 isRetracted "false" @default.
- W4245372219 workType "article" @default.