FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165163721> ?p ?o ?g. }

• W3165163721 endingPage "2657" @default.
• W3165163721 startingPage "2648" @default.
• W3165163721 abstract "Predictive modeling for toxicity can help reduce risks in a range of applications and potentially serve as the basis for regulatory decisions. However, the utility of these predictions can be limited if the associated uncertainty is not adequately quantified. With recent studies showing great promise for deep learning-based models also for toxicity predictions, we investigate the combination of deep learning-based predictors with the conformal prediction framework to generate highly predictive models with well-defined uncertainties. We use a range of deep feedforward neural networks and graph neural networks in a conformal prediction setting and evaluate their performance on data from the Tox21 challenge. We also compare the results from the conformal predictors to those of the underlying machine learning models. The results indicate that highly predictive models can be obtained that result in very efficient conformal predictors even at high confidence levels. Taken together, our results highlight the utility of conformal predictors as a convenient way to deliver toxicity predictions with confidence, adding both statistical guarantees on the model performance as well as better predictions of the minority class compared to the underlying models." @default.
• W3165163721 created "2021-06-07" @default.
• W3165163721 creator A5055587467 @default.
• W3165163721 creator A5067014994 @default.
• W3165163721 creator A5087233240 @default.
• W3165163721 date "2021-05-27" @default.
• W3165163721 modified "2023-10-16" @default.
• W3165163721 title "Deep Learning-Based Conformal Prediction of Toxicity" @default.
• W3165163721 cites W1786598644 @default.
• W3165163721 cites W1967434540 @default.
• W3165163721 cites W1988037271 @default.
• W3165163721 cites W1994249991 @default.
• W3165163721 cites W2009842403 @default.
• W3165163721 cites W2059847559 @default.
• W3165163721 cites W2189911347 @default.
• W3165163721 cites W2234529989 @default.
• W3165163721 cites W2276859037 @default.
• W3165163721 cites W2541855169 @default.
• W3165163721 cites W2563115000 @default.
• W3165163721 cites W2568027568 @default.
• W3165163721 cites W2594183968 @default.
• W3165163721 cites W2604268533 @default.
• W3165163721 cites W2790282224 @default.
• W3165163721 cites W2790808809 @default.
• W3165163721 cites W2795068716 @default.
• W3165163721 cites W2801088198 @default.
• W3165163721 cites W2860192827 @default.
• W3165163721 cites W2890097032 @default.
• W3165163721 cites W2911612351 @default.
• W3165163721 cites W2911964244 @default.
• W3165163721 cites W2920702708 @default.
• W3165163721 cites W2936503027 @default.
• W3165163721 cites W2938282337 @default.
• W3165163721 cites W2966357564 @default.
• W3165163721 cites W2976332861 @default.
• W3165163721 cites W3000732582 @default.
• W3165163721 cites W3008349664 @default.
• W3165163721 cites W3011921139 @default.
• W3165163721 cites W3014339631 @default.
• W3165163721 cites W3048410462 @default.
• W3165163721 cites W3136947284 @default.
• W3165163721 doi "https://doi.org/10.1021/acs.jcim.1c00208" @default.
• W3165163721 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34043352" @default.
• W3165163721 hasPublicationYear "2021" @default.
• W3165163721 type Work @default.
• W3165163721 sameAs 3165163721 @default.
• W3165163721 citedByCount "22" @default.
• W3165163721 countsByYear W31651637212021 @default.
• W3165163721 countsByYear W31651637212022 @default.
• W3165163721 countsByYear W31651637212023 @default.
• W3165163721 crossrefType "journal-article" @default.
• W3165163721 hasAuthorship W3165163721A5055587467 @default.
• W3165163721 hasAuthorship W3165163721A5067014994 @default.
• W3165163721 hasAuthorship W3165163721A5087233240 @default.
• W3165163721 hasBestOaLocation W31651637212 @default.
• W3165163721 hasConcept C105795698 @default.
• W3165163721 hasConcept C108583219 @default.
• W3165163721 hasConcept C119857082 @default.
• W3165163721 hasConcept C127413603 @default.
• W3165163721 hasConcept C134306372 @default.
• W3165163721 hasConcept C146978453 @default.
• W3165163721 hasConcept C154945302 @default.
• W3165163721 hasConcept C204323151 @default.
• W3165163721 hasConcept C33923547 @default.
• W3165163721 hasConcept C41008148 @default.
• W3165163721 hasConcept C44249647 @default.
• W3165163721 hasConcept C45804977 @default.
• W3165163721 hasConcept C50644808 @default.
• W3165163721 hasConcept C98214594 @default.
• W3165163721 hasConceptScore W3165163721C105795698 @default.
• W3165163721 hasConceptScore W3165163721C108583219 @default.
• W3165163721 hasConceptScore W3165163721C119857082 @default.
• W3165163721 hasConceptScore W3165163721C127413603 @default.
• W3165163721 hasConceptScore W3165163721C134306372 @default.
• W3165163721 hasConceptScore W3165163721C146978453 @default.
• W3165163721 hasConceptScore W3165163721C154945302 @default.
• W3165163721 hasConceptScore W3165163721C204323151 @default.
• W3165163721 hasConceptScore W3165163721C33923547 @default.
• W3165163721 hasConceptScore W3165163721C41008148 @default.
• W3165163721 hasConceptScore W3165163721C44249647 @default.
• W3165163721 hasConceptScore W3165163721C45804977 @default.
• W3165163721 hasConceptScore W3165163721C50644808 @default.
• W3165163721 hasConceptScore W3165163721C98214594 @default.
• W3165163721 hasIssue "6" @default.
• W3165163721 hasLocation W31651637211 @default.
• W3165163721 hasLocation W31651637212 @default.
• W3165163721 hasLocation W31651637213 @default.
• W3165163721 hasOpenAccess W3165163721 @default.
• W3165163721 hasPrimaryLocation W31651637211 @default.
• W3165163721 hasRelatedWork W1971223889 @default.
• W3165163721 hasRelatedWork W2011016219 @default.
• W3165163721 hasRelatedWork W2044486817 @default.
• W3165163721 hasRelatedWork W2046055149 @default.
• W3165163721 hasRelatedWork W2392707140 @default.
• W3165163721 hasRelatedWork W2611989081 @default.
• W3165163721 hasRelatedWork W2731899572 @default.
• W3165163721 hasRelatedWork W2747077871 @default.
• W3165163721 hasRelatedWork W4375867731 @default.

• next