Journal
ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY
Volume 66, Issue 3, Pages 353-361Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.ecoenv.2006.02.005
Keywords
quantitative structure-activity relationships; cyclopentaphenanthrenes; Salmonella reversion (Ames) test; k-nearest neighbors (k-NN); classification and regression tree (CART); holistic molecular descriptors
Categories
Ask authors/readers for more resources
Various polycyclic aromatic hydrocarbons (PAHs), ubiquitous environmental pollutants, are recognized mutagens and carcinogens. A homogeneous set of mutagenicity data (TA98 and TA 100, +S9) for 32 benzocyclopentaphenanthrenes/chrysenes was modeled by the quantitative structure-activity relationship classification methods k-nearest neighbor and classification and regression tree, using theoretical holistic molecular descriptors. Genetic algorithm provided the selection of the best subset of variables for modeling mutagenicity. The models were validated by leave-one-out and leave-50%-out approaches and have good performance, with sensitivity and specificity ranges of 90-100%. Mutagenicity assessment for these PAHs requires only a few theoretical descriptors of their molecular structure. (c) 2006 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available