An investigation into pharmaceutically relevant mutagenicity data and the influence on Ames predictive potential
Tools
Tools
Mccarren, Patrick, Springer, Clayton and Whitehead, Lewis (2011) An investigation into pharmaceutically relevant mutagenicity data and the influence on Ames predictive potential. Journal of Cheminformatics, 3 (1). p. 51. ISSN 1758-2946
Abstract
Mutagenicity presents a challenging problem in modeling despite the addition of modern prediction methods and easier access to data. Previous studies have focused mainly on treatment of all mutagenic compound classes, while some have focused on a very small sets of alerting compounds such as aromatic amines with quantitative mutagenicity data. Data currently available at Novartis provide a large, unique set of mutagenicity data originating from one laboratory, providing compounds connected to the discovery and production of medicinal compounds rather than compounds associated with agricultural, environmental and foodstuff concern. We were especially interested in predicting the The performance of commonly used descriptors and methods performed quite poorly for the set of aromatic amines, while using the reaction energy to produce a reactive intermediate provides a prediction accuracy of at least 70% across multiple data sets. Whereas many papers have represented the study of aromatic amines and Ames results as a platform for study of prediction methods with good performance, we show that the set is quite difficult. The performance of methods in our hands will be compared with previously compiled datasets and reported models.
| Item Type: | Article |
|---|---|
| Related URLs: | |
| Related URLs: | |
| Date Deposited: | 13 Oct 2015 13:15 |
| Last Modified: | 13 Oct 2015 13:15 |
| URI: | https://oak.novartis.com/id/eprint/4069 |