Abstract
In any modelling including QSAR, it is very important to validate the resulting model. For this purpose one should consider the QSAR model’s predictive ability. Several tools are available for QSAR validation. The most demanding manner is by (I) external validation which consists of making predictions for an independent set of compounds not available during model training. External validation, however is often difficult in QSAR because it takes time and money to make new compounds and alternatives to external validation are hence of great interest. The alternatives discussed here are (II) cross-validation, (III) splitting the data into a training and a test set where both are present at modelling, and (IV) response permutation tests.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M. Tysklind, P. Andersson, P. Haglund, B. van Bavel and C. Rappe, Selection of polychlorinated biphenyls for use in quantitative structure-activity modelling, SAR QSAR Env. Res. 4: 11 (1995).
L. Eriksson, P. Andersson, E. Johansson, M. Tysklind, M. Sandberg and S. Wold, The constrained principal property (CPP) space in QSAR- Directional and Non-directional modelling approaches, This volume.
L. Eriksson, E. Johansson, and S. Wold, QSAR model validation”, in QSAR in Environmental Chemistry — VII Proceedings of the 7th International Workshop on QSAR in Environmental Sciences, June 24–28, 1996, Elsinore Denmark. F.Chen & G. Schuurmann (Eds) SETAC Press Pensacola, Florida, (1997), pp. 381–397
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media New York
About this chapter
Cite this chapter
Johansson, E., Eriksson, L., Sandberg, M., Wold, S. (2000). QSAR Model Validation. In: Gundertofte, K., Jørgensen, F.S. (eds) Molecular Modeling and Prediction of Bioactivity. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-4141-7_36
Download citation
DOI: https://doi.org/10.1007/978-1-4615-4141-7_36
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6857-1
Online ISBN: 978-1-4615-4141-7
eBook Packages: Springer Book Archive