Research article
Estimation of the applicability domain of kernel-based machine learning models for virtual screening
-
* Corresponding author: Nikolas Fechner nikolas.fechner@uni-tuebingen.de
Center for Bioinformatics Tübingen (ZBIT), University of Tübingen, Sand 1, 72076 Tübingen, Germany
Journal of Cheminformatics 2010, 2:2 doi:10.1186/1758-2946-2-2
Published: 11 March 2010Additional files
Additional file 1:
List of atom and bond descriptors used by the structured kernels. A complete enumeration of the atom and bond descriptors including their respective references (if applicable) is given in the file.
Format: PDF Size: 58KB Download file
This file can be viewed with: Adobe Acrobat Reader
Additional file 2:
Effect of the AD on the VS performance of all combinations of AD, Kernel and Target. All figures for the AD evaluation of the different experiments are presented in the file. The values for the threshold retaining less than 50 compounds in the respective AD are omitted.
Format: PDF Size: 161KB Download file
This file can be viewed with: Adobe Acrobat Reader