Efficiency of different measures for defining the applicability domain of classification models
Abstract The goal of defining an applicability domain for a predictive classification model is to identify the region in chemical space where the model’s predictions are reliable. The boundary of the applicability domain is defined with the help of a measure that shall reflect the reliability of an...
Main Authors: | Waldemar Klingspohn, Miriam Mathea, Antonius ter Laak, Nikolaus Heinrich, Knut Baumann |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2017-08-01
|
Series: | Journal of Cheminformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13321-017-0230-2 |
Similar Items
-
Confidence Measures for Deep Learning in Domain Adaptation
by: Simone Bonechi, et al.
Published: (2019-05-01) -
Comparison of Different Approaches to Define the Applicability Domain of QSAR Models
by: Roberto Todeschini, et al.
Published: (2012-04-01) -
A comparative study of a class of direct estimators for domain mean with a direct ratio estimator for domain mean using auxiliary character
by: Brij Behari Khare, et al.
Published: (2021-06-01) -
Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty
by: Lewis H. Mervin, et al.
Published: (2021-08-01) -
Estimations de dispersion et de Strichartz dans un domaine cylindrique convexe
by: Meas, Len
Published: (2017)