Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205328831> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4205328831 abstract "Drug-target interaction (DTI) prediction is important in drug discovery and chemogenomics studies. Machine learning, particularly deep learning, has advanced this area significantly over the past few years. However, a significant gap between the performance reported in academic papers and that in practical drug discovery settings, e.g. the random-split-based evaluation strategy tends to be too optimistic in estimating the prediction performance in real-world settings. Such performance gap is largely due to hidden data bias in experimental datasets and inappropriate data split. In this paper, we construct a low-bias DTI dataset and study more challenging data split strategies to improve performance evaluation for real-world settings. Specifically, we study the data bias in a popular DTI dataset, BindingDB, and re-evaluate the prediction performance of three state-of-the-art deep learning models using five different data split strategies: random split, cold drug split, scaffold split, and two hierarchical-clustering-based splits. In addition, we comprehensively examine six performance metrics. Our experimental results confirm the overoptimism of the popular random split and show that hierarchical-clustering-based splits are far more challenging and can provide potentially more useful assessment of model generalizability in real-world DTI prediction settings." @default.
- W4205328831 created "2022-01-25" @default.
- W4205328831 creator A5002566778 @default.
- W4205328831 creator A5009807039 @default.
- W4205328831 creator A5021895953 @default.
- W4205328831 creator A5027847171 @default.
- W4205328831 creator A5031183535 @default.
- W4205328831 creator A5089864495 @default.
- W4205328831 date "2021-12-09" @default.
- W4205328831 modified "2023-10-16" @default.
- W4205328831 title "Hierarchical Clustering Split for Low-Bias Evaluation of Drug-Target Interaction Prediction" @default.
- W4205328831 cites W1988037271 @default.
- W4205328831 cites W2080642200 @default.
- W4205328831 cites W2148145769 @default.
- W4205328831 cites W2204695023 @default.
- W4205328831 cites W2601243251 @default.
- W4205328831 cites W2767891136 @default.
- W4205328831 cites W2785947426 @default.
- W4205328831 cites W2806547269 @default.
- W4205328831 cites W2807792492 @default.
- W4205328831 cites W2809216727 @default.
- W4205328831 cites W2899070097 @default.
- W4205328831 cites W2899788782 @default.
- W4205328831 cites W2966848807 @default.
- W4205328831 cites W3018980093 @default.
- W4205328831 cites W3028589594 @default.
- W4205328831 cites W3104508774 @default.
- W4205328831 doi "https://doi.org/10.1109/bibm52615.2021.9669515" @default.
- W4205328831 hasPublicationYear "2021" @default.
- W4205328831 type Work @default.
- W4205328831 citedByCount "3" @default.
- W4205328831 countsByYear W42053288312023 @default.
- W4205328831 crossrefType "proceedings-article" @default.
- W4205328831 hasAuthorship W4205328831A5002566778 @default.
- W4205328831 hasAuthorship W4205328831A5009807039 @default.
- W4205328831 hasAuthorship W4205328831A5021895953 @default.
- W4205328831 hasAuthorship W4205328831A5027847171 @default.
- W4205328831 hasAuthorship W4205328831A5031183535 @default.
- W4205328831 hasAuthorship W4205328831A5089864495 @default.
- W4205328831 hasBestOaLocation W42053288312 @default.
- W4205328831 hasConcept C105795698 @default.
- W4205328831 hasConcept C108583219 @default.
- W4205328831 hasConcept C119857082 @default.
- W4205328831 hasConcept C124101348 @default.
- W4205328831 hasConcept C154945302 @default.
- W4205328831 hasConcept C169258074 @default.
- W4205328831 hasConcept C27158222 @default.
- W4205328831 hasConcept C33923547 @default.
- W4205328831 hasConcept C41008148 @default.
- W4205328831 hasConcept C73555534 @default.
- W4205328831 hasConceptScore W4205328831C105795698 @default.
- W4205328831 hasConceptScore W4205328831C108583219 @default.
- W4205328831 hasConceptScore W4205328831C119857082 @default.
- W4205328831 hasConceptScore W4205328831C124101348 @default.
- W4205328831 hasConceptScore W4205328831C154945302 @default.
- W4205328831 hasConceptScore W4205328831C169258074 @default.
- W4205328831 hasConceptScore W4205328831C27158222 @default.
- W4205328831 hasConceptScore W4205328831C33923547 @default.
- W4205328831 hasConceptScore W4205328831C41008148 @default.
- W4205328831 hasConceptScore W4205328831C73555534 @default.
- W4205328831 hasLocation W42053288311 @default.
- W4205328831 hasLocation W42053288312 @default.
- W4205328831 hasOpenAccess W4205328831 @default.
- W4205328831 hasPrimaryLocation W42053288311 @default.
- W4205328831 hasRelatedWork W2968586400 @default.
- W4205328831 hasRelatedWork W3211546796 @default.
- W4205328831 hasRelatedWork W4223564025 @default.
- W4205328831 hasRelatedWork W4223943233 @default.
- W4205328831 hasRelatedWork W4281616679 @default.
- W4205328831 hasRelatedWork W4312200629 @default.
- W4205328831 hasRelatedWork W4360585206 @default.
- W4205328831 hasRelatedWork W4364306694 @default.
- W4205328831 hasRelatedWork W4380075502 @default.
- W4205328831 hasRelatedWork W4380086463 @default.
- W4205328831 isParatext "false" @default.
- W4205328831 isRetracted "false" @default.
- W4205328831 workType "article" @default.