Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938282337> ?p ?o ?g. }
- W2938282337 endingPage "3339" @default.
- W2938282337 startingPage "3330" @default.
- W2938282337 abstract "While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we present a framework to compute reliable errors in prediction for Neural Networks using Test-Time Dropout and Conformal Prediction. Specifically, the algorithm consists of training a single Neural Network using dropout, and then applying it N times to both the validation and test sets, also employing dropout in this step. Therefore, for each instance in the validation and test sets an ensemble of predictions were generated. The residuals and absolute errors in prediction for the validation set were then used to compute prediction errors for test set instances using Conformal Prediction. We show using 24 bioactivity data sets from ChEMBL 23 that dropout Conformal Predictors are valid (i.e., the fraction of instances whose true value lies within the predicted interval strongly correlates with the confidence level) and efficient, as the predicted confidence intervals span a narrower set of values than those computed with Conformal Predictors generated using Random Forest (RF) models. Lastly, we show in retrospective virtual screening experiments that dropout and RF-based Conformal Predictors lead to comparable retrieval rates of active compounds. Overall, we propose a computationally efficient framework (as only N extra forward passes are required in addition to training a single network) to harness Test-Time Dropout and the Conformal Prediction framework, and to thereby generate reliable prediction errors for deep Neural Networks." @default.
- W2938282337 created "2019-04-25" @default.
- W2938282337 creator A5026643759 @default.
- W2938282337 creator A5091416834 @default.
- W2938282337 date "2019-06-17" @default.
- W2938282337 modified "2023-09-30" @default.
- W2938282337 title "Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout" @default.
- W2938282337 cites W1967042264 @default.
- W2938282337 cites W1983393839 @default.
- W2938282337 cites W1988037271 @default.
- W2938282337 cites W1994249991 @default.
- W2938282337 cites W2009842403 @default.
- W2938282337 cites W2043990744 @default.
- W2938282337 cites W2048611698 @default.
- W2938282337 cites W2051790677 @default.
- W2938282337 cites W2054111413 @default.
- W2938282337 cites W2057069496 @default.
- W2938282337 cites W2079444823 @default.
- W2938282337 cites W2088970363 @default.
- W2938282337 cites W2096541451 @default.
- W2938282337 cites W2104709519 @default.
- W2938282337 cites W2118689184 @default.
- W2938282337 cites W2137356002 @default.
- W2938282337 cites W2144377773 @default.
- W2938282337 cites W2146038212 @default.
- W2938282337 cites W2155478691 @default.
- W2938282337 cites W2162610241 @default.
- W2938282337 cites W2407586185 @default.
- W2938282337 cites W2472085920 @default.
- W2938282337 cites W2558999090 @default.
- W2938282337 cites W2567439748 @default.
- W2938282337 cites W2587942483 @default.
- W2938282337 cites W2731161895 @default.
- W2938282337 cites W2740946158 @default.
- W2938282337 cites W2760946358 @default.
- W2938282337 cites W2769322745 @default.
- W2938282337 cites W2777974480 @default.
- W2938282337 cites W2784213390 @default.
- W2938282337 cites W2789547262 @default.
- W2938282337 cites W2790808809 @default.
- W2938282337 cites W2794301983 @default.
- W2938282337 cites W2802404464 @default.
- W2938282337 cites W2888526648 @default.
- W2938282337 cites W2890097032 @default.
- W2938282337 cites W2895763047 @default.
- W2938282337 cites W2900415334 @default.
- W2938282337 cites W2906627336 @default.
- W2938282337 cites W2909055772 @default.
- W2938282337 cites W2911789160 @default.
- W2938282337 cites W2911964244 @default.
- W2938282337 cites W2913930293 @default.
- W2938282337 cites W2919115771 @default.
- W2938282337 cites W2922305141 @default.
- W2938282337 cites W2950238754 @default.
- W2938282337 cites W2964054038 @default.
- W2938282337 cites W4231944115 @default.
- W2938282337 cites W851307856 @default.
- W2938282337 doi "https://doi.org/10.1021/acs.jcim.9b00297" @default.
- W2938282337 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31241929" @default.
- W2938282337 hasPublicationYear "2019" @default.
- W2938282337 type Work @default.
- W2938282337 sameAs 2938282337 @default.
- W2938282337 citedByCount "28" @default.
- W2938282337 countsByYear W29382823372019 @default.
- W2938282337 countsByYear W29382823372020 @default.
- W2938282337 countsByYear W29382823372021 @default.
- W2938282337 countsByYear W29382823372022 @default.
- W2938282337 countsByYear W29382823372023 @default.
- W2938282337 crossrefType "journal-article" @default.
- W2938282337 hasAuthorship W2938282337A5026643759 @default.
- W2938282337 hasAuthorship W2938282337A5091416834 @default.
- W2938282337 hasBestOaLocation W29382823372 @default.
- W2938282337 hasConcept C103402496 @default.
- W2938282337 hasConcept C105795698 @default.
- W2938282337 hasConcept C11413529 @default.
- W2938282337 hasConcept C119857082 @default.
- W2938282337 hasConcept C124101348 @default.
- W2938282337 hasConcept C134306372 @default.
- W2938282337 hasConcept C154945302 @default.
- W2938282337 hasConcept C169258074 @default.
- W2938282337 hasConcept C169903167 @default.
- W2938282337 hasConcept C177264268 @default.
- W2938282337 hasConcept C199360897 @default.
- W2938282337 hasConcept C2776145597 @default.
- W2938282337 hasConcept C33923547 @default.
- W2938282337 hasConcept C41008148 @default.
- W2938282337 hasConcept C44249647 @default.
- W2938282337 hasConcept C50644808 @default.
- W2938282337 hasConcept C58489278 @default.
- W2938282337 hasConcept C60644358 @default.
- W2938282337 hasConcept C63222358 @default.
- W2938282337 hasConcept C74187038 @default.
- W2938282337 hasConcept C86803240 @default.
- W2938282337 hasConcept C98214594 @default.
- W2938282337 hasConceptScore W2938282337C103402496 @default.
- W2938282337 hasConceptScore W2938282337C105795698 @default.
- W2938282337 hasConceptScore W2938282337C11413529 @default.
- W2938282337 hasConceptScore W2938282337C119857082 @default.