1868-1751/asset/2022_left.gif?v=1&s=55861aec609bfeb0bc3c0534a51214d53d9fdc7d)
1868-1751/asset/olbannerright.gif?v=1&s=ecd199dedfd0b2cddec070f1d2c6b8962951f728)
Full Paper
Estimation of Acid Dissociation Constants Using Graph Kernels
Article first published online: 22 OCT 2010
DOI: 10.1002/minf.201000072
Copyright © 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim
Additional Information
How to Cite
Rupp, M., Körner, R. and Tetko, I. V. (2010), Estimation of Acid Dissociation Constants Using Graph Kernels. Molecular Informatics, 29: 731–740. doi: 10.1002/minf.201000072
Publication History
- Issue published online: 22 OCT 2010
- Article first published online: 22 OCT 2010
- Manuscript Accepted: 30 SEP 2010
- Manuscript Received: 5 JUL 2010
Funded by
- GO-Bio BMBF. Grant Number: 0313883
Keywords:
- pKa;
- Acid dissociation constant;
- Graph kernel;
- Kernel ridge regression;
- QSPR
Graphical Abstract
Abstract
The biopharmaceutical profile of a compound depends directly on the dissociation constants of its acidic and basic groups. We estimate these constants using kernel ridge regression and graph kernels. The performance of our approach is similar to that of a semi-empirical model (Tehan et al, QSAR & Comb. Sci. 21(5): 457–472, 473–485) based on frontier electron theory, but uses only the annotated structure graph. In particular, no structure optimization is necessary. We discuss advantages and shortcomings of our approach.