FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183194627> ?p ?o ?g. }

• W3183194627 endingPage "100178" @default.
• W3183194627 startingPage "100178" @default.
• W3183194627 abstract "Machine learning and deep learning approaches have been increasingly used in the field of toxicology through prediction models developed using various toxicity data. However, toxicity data are often class-imbalanced, which hinders the development of machine learning models with good performance. Therefore, in this study, we identified effective data-balancing methods for class-imbalanced genotoxicity datasets using machine learning algorithms and molecular fingerprints. Data-balancing methods, such as random undersampling (RUS), sample weight (SW), synthetic minority oversampling technique (SMOTE), and random oversampling (ROS) were applied to the datasets. Model performance was evaluated using the F1 score on five machine learning algorithms: gradient boosting tree (GBT), random forest (RF), support vector machine (SVM), multi-layer perceptron (MLP) network, and k-nearest neighbors (kNN) in combination with five molecular fingerprints (Morgan, MACCS, RDKit, Pattern, and Layered). The performance was evaluated for each combination of molecular fingerprints, machine learning algorithms, and data-balancing methods. The MACCS-GBT-SMOTE combination model achieved the best F1 score, followed by RDKit-GBT-SW. Thus, this study demonstrated that data balancing conducted using oversampling methods improved the performance of models. The systematic approach used in this study can also be applied to other toxicity datasets, which may facilitate the development of an improved classification model for toxicity screening." @default.
• W3183194627 created "2021-08-02" @default.
• W3183194627 creator A5019846022 @default.
• W3183194627 creator A5031975117 @default.
• W3183194627 creator A5033852440 @default.
• W3183194627 creator A5047491479 @default.
• W3183194627 creator A5088937607 @default.
• W3183194627 date "2021-11-01" @default.
• W3183194627 modified "2023-10-16" @default.
• W3183194627 title "Effective data-balancing methods for class-imbalanced genotoxicity datasets using machine learning algorithms and molecular fingerprints" @default.
• W3183194627 cites W1964940342 @default.
• W3183194627 cites W1970101098 @default.
• W3183194627 cites W1987882653 @default.
• W3183194627 cites W1988195734 @default.
• W3183194627 cites W1990990050 @default.
• W3183194627 cites W2027105714 @default.
• W3183194627 cites W2072462334 @default.
• W3183194627 cites W2087398486 @default.
• W3183194627 cites W2121780366 @default.
• W3183194627 cites W2189911347 @default.
• W3183194627 cites W2403746960 @default.
• W3183194627 cites W2541855169 @default.
• W3183194627 cites W2556851635 @default.
• W3183194627 cites W2773131117 @default.
• W3183194627 cites W2792093157 @default.
• W3183194627 cites W2800112443 @default.
• W3183194627 cites W2887896328 @default.
• W3183194627 cites W2922333374 @default.
• W3183194627 cites W2944040221 @default.
• W3183194627 cites W2984379065 @default.
• W3183194627 cites W2990257819 @default.
• W3183194627 cites W3037682562 @default.
• W3183194627 cites W3097920362 @default.
• W3183194627 doi "https://doi.org/10.1016/j.comtox.2021.100178" @default.
• W3183194627 hasPublicationYear "2021" @default.
• W3183194627 type Work @default.
• W3183194627 sameAs 3183194627 @default.
• W3183194627 citedByCount "12" @default.
• W3183194627 countsByYear W31831946272022 @default.
• W3183194627 countsByYear W31831946272023 @default.
• W3183194627 crossrefType "journal-article" @default.
• W3183194627 hasAuthorship W3183194627A5019846022 @default.
• W3183194627 hasAuthorship W3183194627A5031975117 @default.
• W3183194627 hasAuthorship W3183194627A5033852440 @default.
• W3183194627 hasAuthorship W3183194627A5047491479 @default.
• W3183194627 hasAuthorship W3183194627A5088937607 @default.
• W3183194627 hasConcept C11413529 @default.
• W3183194627 hasConcept C119857082 @default.
• W3183194627 hasConcept C12267149 @default.
• W3183194627 hasConcept C124101348 @default.
• W3183194627 hasConcept C136536468 @default.
• W3183194627 hasConcept C154945302 @default.
• W3183194627 hasConcept C169258074 @default.
• W3183194627 hasConcept C179717631 @default.
• W3183194627 hasConcept C197323446 @default.
• W3183194627 hasConcept C2776257435 @default.
• W3183194627 hasConcept C31258907 @default.
• W3183194627 hasConcept C41008148 @default.
• W3183194627 hasConcept C45942800 @default.
• W3183194627 hasConcept C46686674 @default.
• W3183194627 hasConcept C50644808 @default.
• W3183194627 hasConceptScore W3183194627C11413529 @default.
• W3183194627 hasConceptScore W3183194627C119857082 @default.
• W3183194627 hasConceptScore W3183194627C12267149 @default.
• W3183194627 hasConceptScore W3183194627C124101348 @default.
• W3183194627 hasConceptScore W3183194627C136536468 @default.
• W3183194627 hasConceptScore W3183194627C154945302 @default.
• W3183194627 hasConceptScore W3183194627C169258074 @default.
• W3183194627 hasConceptScore W3183194627C179717631 @default.
• W3183194627 hasConceptScore W3183194627C197323446 @default.
• W3183194627 hasConceptScore W3183194627C2776257435 @default.
• W3183194627 hasConceptScore W3183194627C31258907 @default.
• W3183194627 hasConceptScore W3183194627C41008148 @default.
• W3183194627 hasConceptScore W3183194627C45942800 @default.
• W3183194627 hasConceptScore W3183194627C46686674 @default.
• W3183194627 hasConceptScore W3183194627C50644808 @default.
• W3183194627 hasFunder F4320322030 @default.
• W3183194627 hasFunder F4320322120 @default.
• W3183194627 hasLocation W31831946271 @default.
• W3183194627 hasOpenAccess W3183194627 @default.
• W3183194627 hasPrimaryLocation W31831946271 @default.
• W3183194627 hasRelatedWork W2979979539 @default.
• W3183194627 hasRelatedWork W3175748729 @default.
• W3183194627 hasRelatedWork W3193372619 @default.
• W3183194627 hasRelatedWork W3195168932 @default.
• W3183194627 hasRelatedWork W4200525072 @default.
• W3183194627 hasRelatedWork W4206325870 @default.
• W3183194627 hasRelatedWork W4206558443 @default.
• W3183194627 hasRelatedWork W4293069612 @default.
• W3183194627 hasRelatedWork W4319777965 @default.
• W3183194627 hasRelatedWork W4322743207 @default.
• W3183194627 hasVolume "20" @default.
• W3183194627 isParatext "false" @default.
• W3183194627 isRetracted "false" @default.
• W3183194627 magId "3183194627" @default.
• W3183194627 workType "article" @default.