Current Status of Methods for Defining the Applicability Domain of (Quantitative) Structure-Activity Relationships
By T. Netzeva, Andrew Paul Worth, T. Aldenberg, R. Benigni, Mark T. D. Cronin, Paola Gramatica, Joanna Jaworska, Scott D. Kahn, G. Klopman, C. Marchant and 11 more. Alternatives to laboratory animals : ATLA, 2005
797 citations recorded by the source corpus.
Subfields: Computational Theory and Mathematics, Food Science, Small Animals
View Paper: https://www.semanticscholar.org/paper/55f4a0fd6f17d14f0a9f0080113728eaa75230ef
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Igor V. Tetko
- Gennadiy Poda
- Kamel Mansouri
- Roberto Todeschini
- Viviana Consonni
- Davide Ballabio
- Pierre Bruneau
- K. Müller
In Food Science
Citations in the corpus
- Applied Predictive Modeling (2013, background): “The applicability domain of a model is the region of predictor space where “the model makes predictions with a given reliability” (Netzeva et al. 2005).”
- Comparison of Different Approaches to Define the Applicability Domain of QSAR Models (2012, methodology): “Predictions from all the combined DTs are averaged in order to determine the prediction confidence for a given compound while domain extrapolation provides the prediction accuracy for that compound outside the training space [1,20,21].”
- In Silico Tools for Sharing Data and Knowledge on Toxicity and Metabolism: Derek for Windows, Meteor, and Vitic (2008, methodology): “Application of these principles (or the Set´ubal principles that preceded them) to Derek for Windows has been described (OECD 2004; Hulzebos et al. 2005; Ma´slankiewicz et al. 2005; Netzeva et al. 2005; Benigni et al. 2007).”
- Predicting into unknown space? Estimating the area of applicability of spatial prediction models (2020, methodology): “…point (in the pre-70 dictor space) which allows accounting for values outside the range or hull of predictors, as well as significant gaps in71 the predictor space, something that cannot be accounted for by methods like hulls (Netzeva et al. 2005, Montgomery72 et al. 2012) or average distances.”
- Can we estimate the accuracy of ADME-Tox predictions? (2006, methodology): “The more complex probability density distribution-based methods (Figure 1C) can also be used to detect dense and low populated regions of the structural space [ 16 ].”
- Estimating the domain of applicability for machine learning QSAR models: a study on aqueous solubility of drug discovery molecules (2007, methodology): “When applying any kind of model, it is therefore essential to know the reliability of each individual prediction [7, 8, 9, 10].”