Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313260052> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4313260052 endingPage "217" @default.
- W4313260052 startingPage "217" @default.
- W4313260052 abstract "Molecular structure property modeling is an increasingly important tool for predicting compounds with desired properties due to the expensive and resource-intensive nature and the problem of toxicity-related attrition in late phases during drug discovery and development. Lately, the interest for applying deep learning techniques has increased considerably. This investigation compares the traditional physico-chemical descriptor and machine learning-based approaches through autoencoder generated descriptors to two different descriptor-free, Simplified Molecular Input Line Entry System (SMILES) based, deep learning architectures of Bidirectional Encoder Representations from Transformers (BERT) type using the Mondrian aggregated conformal prediction method as overarching framework. The results show for the binary CATMoS non-toxic and very-toxic datasets that for the former, almost equally balanced, dataset all methods perform equally well while for the latter dataset, with an 11-fold difference between the two classes, the MolBERT model based on a large pre-trained network performs somewhat better compared to the rest with high efficiency for both classes (0.93-0.94) as well as high values for sensitivity, specificity and balanced accuracy (0.86-0.87). The descriptor-free, SMILES-based, deep learning BERT architectures seem capable of producing well-balanced predictive models with defined applicability domains. This work also demonstrates that the class imbalance problem is gracefully handled through the use of Mondrian conformal prediction without the use of over- and/or under-sampling, weighting of classes or cost-sensitive methods." @default.
- W4313260052 created "2023-01-06" @default.
- W4313260052 creator A5067014994 @default.
- W4313260052 date "2022-12-26" @default.
- W4313260052 modified "2023-10-14" @default.
- W4313260052 title "Traditional Machine and Deep Learning for Predicting Toxicity Endpoints" @default.
- W4313260052 cites W1975147762 @default.
- W4313260052 cites W2015452969 @default.
- W4313260052 cites W2273267066 @default.
- W4313260052 cites W2531470489 @default.
- W4313260052 cites W2790808809 @default.
- W4313260052 cites W2884001105 @default.
- W4313260052 cites W2888802689 @default.
- W4313260052 cites W2901476322 @default.
- W4313260052 cites W2910248242 @default.
- W4313260052 cites W2936503027 @default.
- W4313260052 cites W2962764460 @default.
- W4313260052 cites W2966357564 @default.
- W4313260052 cites W2973114758 @default.
- W4313260052 cites W3010761615 @default.
- W4313260052 cites W3013954280 @default.
- W4313260052 cites W3023042104 @default.
- W4313260052 cites W3032781902 @default.
- W4313260052 cites W3037682562 @default.
- W4313260052 cites W3048065091 @default.
- W4313260052 cites W3157265962 @default.
- W4313260052 cites W3158507782 @default.
- W4313260052 cites W3182055317 @default.
- W4313260052 cites W3189831819 @default.
- W4313260052 cites W4281732955 @default.
- W4313260052 cites W4294310143 @default.
- W4313260052 cites W4309013036 @default.
- W4313260052 doi "https://doi.org/10.3390/molecules28010217" @default.
- W4313260052 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36615411" @default.
- W4313260052 hasPublicationYear "2022" @default.
- W4313260052 type Work @default.
- W4313260052 citedByCount "0" @default.
- W4313260052 crossrefType "journal-article" @default.
- W4313260052 hasAuthorship W4313260052A5067014994 @default.
- W4313260052 hasBestOaLocation W43132600521 @default.
- W4313260052 hasConcept C101738243 @default.
- W4313260052 hasConcept C108583219 @default.
- W4313260052 hasConcept C111919701 @default.
- W4313260052 hasConcept C118505674 @default.
- W4313260052 hasConcept C119857082 @default.
- W4313260052 hasConcept C126838900 @default.
- W4313260052 hasConcept C154945302 @default.
- W4313260052 hasConcept C183115368 @default.
- W4313260052 hasConcept C41008148 @default.
- W4313260052 hasConcept C71924100 @default.
- W4313260052 hasConceptScore W4313260052C101738243 @default.
- W4313260052 hasConceptScore W4313260052C108583219 @default.
- W4313260052 hasConceptScore W4313260052C111919701 @default.
- W4313260052 hasConceptScore W4313260052C118505674 @default.
- W4313260052 hasConceptScore W4313260052C119857082 @default.
- W4313260052 hasConceptScore W4313260052C126838900 @default.
- W4313260052 hasConceptScore W4313260052C154945302 @default.
- W4313260052 hasConceptScore W4313260052C183115368 @default.
- W4313260052 hasConceptScore W4313260052C41008148 @default.
- W4313260052 hasConceptScore W4313260052C71924100 @default.
- W4313260052 hasFunder F4320309951 @default.
- W4313260052 hasIssue "1" @default.
- W4313260052 hasLocation W43132600521 @default.
- W4313260052 hasLocation W43132600522 @default.
- W4313260052 hasLocation W43132600523 @default.
- W4313260052 hasLocation W43132600524 @default.
- W4313260052 hasOpenAccess W4313260052 @default.
- W4313260052 hasPrimaryLocation W43132600521 @default.
- W4313260052 hasRelatedWork W2567271240 @default.
- W4313260052 hasRelatedWork W2788487394 @default.
- W4313260052 hasRelatedWork W2922457425 @default.
- W4313260052 hasRelatedWork W2989980351 @default.
- W4313260052 hasRelatedWork W3002526821 @default.
- W4313260052 hasRelatedWork W3044458868 @default.
- W4313260052 hasRelatedWork W3196183652 @default.
- W4313260052 hasRelatedWork W4213225422 @default.
- W4313260052 hasRelatedWork W4250304930 @default.
- W4313260052 hasRelatedWork W4289656111 @default.
- W4313260052 hasVolume "28" @default.
- W4313260052 isParatext "false" @default.
- W4313260052 isRetracted "false" @default.
- W4313260052 workType "article" @default.