FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216996162> ?p ?o ?g. }

• W3216996162 abstract "In this work, we benchmark a variety of single- and multi-task graph neural network (GNN) models against lower-bar and higher-bar traditional machine learning approaches employing human engineered molecular features. We consider four GNN variants -- Graph Convolutional Network (GCN), Graph Attention Network (GAT), Message Passing Neural Network (MPNN), and Attentive Fingerprint (AttentiveFP). So far deep learning models have been primarily benchmarked using lower-bar traditional models solely based on fingerprints, while more realistic benchmarks employing fingerprints, whole-molecule descriptors and predictions from other related endpoints (e.g., LogD7.4) appear to be scarce for industrial ADME datasets. In addition to time-split test sets based on Genentech data, this study benefits from the availability of measurements from an external chemical space (Roche data). We identify GAT as a promising approach to implementing deep learning models. While all GNN models significantly outperform lower-bar benchmark traditional models solely based on fingerprints, only GATs seem to offer a small but consistent improvement over higher-bar benchmark traditional models. Finally, the accuracy of in vitro assays from different laboratories predicting the same experimental endpoints appears to be comparable with the accuracy of GAT single-task models, suggesting that most of the observed error from the models is a function of the experimental error propagation." @default.
• W3216996162 created "2021-12-06" @default.
• W3216996162 creator A5014873370 @default.
• W3216996162 creator A5047272417 @default.
• W3216996162 creator A5065751221 @default.
• W3216996162 creator A5078010996 @default.
• W3216996162 creator A5082384108 @default.
• W3216996162 date "2022-02-23" @default.
• W3216996162 modified "2023-10-01" @default.
• W3216996162 title "Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical Spaces" @default.
• W3216996162 cites W2019678805 @default.
• W3216996162 cites W2064176611 @default.
• W3216996162 cites W2076301458 @default.
• W3216996162 cites W2095032418 @default.
• W3216996162 cites W2126466225 @default.
• W3216996162 cites W2139694010 @default.
• W3216996162 cites W2237850791 @default.
• W3216996162 cites W2290847742 @default.
• W3216996162 cites W2323400728 @default.
• W3216996162 cites W2626276175 @default.
• W3216996162 cites W2734982589 @default.
• W3216996162 cites W2740946158 @default.
• W3216996162 cites W2799892685 @default.
• W3216996162 cites W2968734407 @default.
• W3216996162 cites W3015208165 @default.
• W3216996162 cites W3202227570 @default.
• W3216996162 doi "https://doi.org/10.1002/minf.202100321" @default.
• W3216996162 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35156325" @default.
• W3216996162 hasPublicationYear "2022" @default.
• W3216996162 type Work @default.
• W3216996162 sameAs 3216996162 @default.
• W3216996162 citedByCount "6" @default.
• W3216996162 countsByYear W32169961622022 @default.
• W3216996162 countsByYear W32169961622023 @default.
• W3216996162 crossrefType "journal-article" @default.
• W3216996162 hasAuthorship W3216996162A5014873370 @default.
• W3216996162 hasAuthorship W3216996162A5047272417 @default.
• W3216996162 hasAuthorship W3216996162A5065751221 @default.
• W3216996162 hasAuthorship W3216996162A5078010996 @default.
• W3216996162 hasAuthorship W3216996162A5082384108 @default.
• W3216996162 hasBestOaLocation W32169961622 @default.
• W3216996162 hasConcept C105795698 @default.
• W3216996162 hasConcept C108583219 @default.
• W3216996162 hasConcept C112705442 @default.
• W3216996162 hasConcept C119857082 @default.
• W3216996162 hasConcept C124101348 @default.
• W3216996162 hasConcept C132525143 @default.
• W3216996162 hasConcept C13280743 @default.
• W3216996162 hasConcept C144133560 @default.
• W3216996162 hasConcept C154945302 @default.
• W3216996162 hasConcept C162853370 @default.
• W3216996162 hasConcept C185798385 @default.
• W3216996162 hasConcept C205649164 @default.
• W3216996162 hasConcept C27158222 @default.
• W3216996162 hasConcept C33923547 @default.
• W3216996162 hasConcept C41008148 @default.
• W3216996162 hasConcept C50644808 @default.
• W3216996162 hasConcept C60644358 @default.
• W3216996162 hasConcept C69366308 @default.
• W3216996162 hasConcept C74187038 @default.
• W3216996162 hasConcept C80444323 @default.
• W3216996162 hasConcept C81363708 @default.
• W3216996162 hasConcept C86251818 @default.
• W3216996162 hasConcept C86803240 @default.
• W3216996162 hasConcept C99726746 @default.
• W3216996162 hasConceptScore W3216996162C105795698 @default.
• W3216996162 hasConceptScore W3216996162C108583219 @default.
• W3216996162 hasConceptScore W3216996162C112705442 @default.
• W3216996162 hasConceptScore W3216996162C119857082 @default.
• W3216996162 hasConceptScore W3216996162C124101348 @default.
• W3216996162 hasConceptScore W3216996162C132525143 @default.
• W3216996162 hasConceptScore W3216996162C13280743 @default.
• W3216996162 hasConceptScore W3216996162C144133560 @default.
• W3216996162 hasConceptScore W3216996162C154945302 @default.
• W3216996162 hasConceptScore W3216996162C162853370 @default.
• W3216996162 hasConceptScore W3216996162C185798385 @default.
• W3216996162 hasConceptScore W3216996162C205649164 @default.
• W3216996162 hasConceptScore W3216996162C27158222 @default.
• W3216996162 hasConceptScore W3216996162C33923547 @default.
• W3216996162 hasConceptScore W3216996162C41008148 @default.
• W3216996162 hasConceptScore W3216996162C50644808 @default.
• W3216996162 hasConceptScore W3216996162C60644358 @default.
• W3216996162 hasConceptScore W3216996162C69366308 @default.
• W3216996162 hasConceptScore W3216996162C74187038 @default.
• W3216996162 hasConceptScore W3216996162C80444323 @default.
• W3216996162 hasConceptScore W3216996162C81363708 @default.
• W3216996162 hasConceptScore W3216996162C86251818 @default.
• W3216996162 hasConceptScore W3216996162C86803240 @default.
• W3216996162 hasConceptScore W3216996162C99726746 @default.
• W3216996162 hasIssue "8" @default.
• W3216996162 hasLocation W32169961621 @default.
• W3216996162 hasLocation W32169961622 @default.
• W3216996162 hasLocation W32169961623 @default.
• W3216996162 hasOpenAccess W3216996162 @default.
• W3216996162 hasPrimaryLocation W32169961621 @default.
• W3216996162 hasRelatedWork W2519019522 @default.
• W3216996162 hasRelatedWork W2593649365 @default.
• W3216996162 hasRelatedWork W2731899572 @default.
• W3216996162 hasRelatedWork W2950577464 @default.
• W3216996162 hasRelatedWork W2962391030 @default.

• next