Matches in SemOpenAlex for { <https://semopenalex.org/work/W4236108512> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4236108512 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.
- W4236108512 created "2022-05-12" @default.
- W4236108512 creator A5022033626 @default.
- W4236108512 creator A5063816637 @default.
- W4236108512 creator A5076975589 @default.
- W4236108512 creator A5090993508 @default.
- W4236108512 date "2020-12-18" @default.
- W4236108512 modified "2023-10-16" @default.
- W4236108512 title "Comparative Study of Deep Generative Models on Chemical Space Coverage" @default.
- W4236108512 doi "https://doi.org/10.26434/chemrxiv.13234289.v2" @default.
- W4236108512 hasPublicationYear "2020" @default.
- W4236108512 type Work @default.
- W4236108512 citedByCount "1" @default.
- W4236108512 countsByYear W42361085122021 @default.
- W4236108512 crossrefType "posted-content" @default.
- W4236108512 hasAuthorship W4236108512A5022033626 @default.
- W4236108512 hasAuthorship W4236108512A5063816637 @default.
- W4236108512 hasAuthorship W4236108512A5076975589 @default.
- W4236108512 hasAuthorship W4236108512A5090993508 @default.
- W4236108512 hasBestOaLocation W42361085121 @default.
- W4236108512 hasConcept C108583219 @default.
- W4236108512 hasConcept C119857082 @default.
- W4236108512 hasConcept C127413603 @default.
- W4236108512 hasConcept C13280743 @default.
- W4236108512 hasConcept C134306372 @default.
- W4236108512 hasConcept C154945302 @default.
- W4236108512 hasConcept C167966045 @default.
- W4236108512 hasConcept C176217482 @default.
- W4236108512 hasConcept C177148314 @default.
- W4236108512 hasConcept C184408114 @default.
- W4236108512 hasConcept C185798385 @default.
- W4236108512 hasConcept C205649164 @default.
- W4236108512 hasConcept C21547014 @default.
- W4236108512 hasConcept C33923547 @default.
- W4236108512 hasConcept C39890363 @default.
- W4236108512 hasConcept C41008148 @default.
- W4236108512 hasConcept C60644358 @default.
- W4236108512 hasConcept C74187038 @default.
- W4236108512 hasConcept C86803240 @default.
- W4236108512 hasConcept C97931131 @default.
- W4236108512 hasConcept C99726746 @default.
- W4236108512 hasConceptScore W4236108512C108583219 @default.
- W4236108512 hasConceptScore W4236108512C119857082 @default.
- W4236108512 hasConceptScore W4236108512C127413603 @default.
- W4236108512 hasConceptScore W4236108512C13280743 @default.
- W4236108512 hasConceptScore W4236108512C134306372 @default.
- W4236108512 hasConceptScore W4236108512C154945302 @default.
- W4236108512 hasConceptScore W4236108512C167966045 @default.
- W4236108512 hasConceptScore W4236108512C176217482 @default.
- W4236108512 hasConceptScore W4236108512C177148314 @default.
- W4236108512 hasConceptScore W4236108512C184408114 @default.
- W4236108512 hasConceptScore W4236108512C185798385 @default.
- W4236108512 hasConceptScore W4236108512C205649164 @default.
- W4236108512 hasConceptScore W4236108512C21547014 @default.
- W4236108512 hasConceptScore W4236108512C33923547 @default.
- W4236108512 hasConceptScore W4236108512C39890363 @default.
- W4236108512 hasConceptScore W4236108512C41008148 @default.
- W4236108512 hasConceptScore W4236108512C60644358 @default.
- W4236108512 hasConceptScore W4236108512C74187038 @default.
- W4236108512 hasConceptScore W4236108512C86803240 @default.
- W4236108512 hasConceptScore W4236108512C97931131 @default.
- W4236108512 hasConceptScore W4236108512C99726746 @default.
- W4236108512 hasLocation W42361085121 @default.
- W4236108512 hasLocation W42361085122 @default.
- W4236108512 hasOpenAccess W4236108512 @default.
- W4236108512 hasPrimaryLocation W42361085121 @default.
- W4236108512 hasRelatedWork W2066921324 @default.
- W4236108512 hasRelatedWork W2128027845 @default.
- W4236108512 hasRelatedWork W2137705650 @default.
- W4236108512 hasRelatedWork W2294985537 @default.
- W4236108512 hasRelatedWork W2560791808 @default.
- W4236108512 hasRelatedWork W2770426046 @default.
- W4236108512 hasRelatedWork W2921547035 @default.
- W4236108512 hasRelatedWork W3108004614 @default.
- W4236108512 hasRelatedWork W4283820830 @default.
- W4236108512 hasRelatedWork W4378711654 @default.
- W4236108512 isParatext "false" @default.
- W4236108512 isRetracted "false" @default.
- W4236108512 workType "article" @default.