Linked Life Data

18311639

Source:http://linkedlifedata.com/resource/pubmed/id/18311639

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
1-2
pubmed:dateCreated
2008-3-3
pubmed:abstractText
Polycyclic aromatic hydrocarbons (PAHs) are ubiquitous pollutants of high environmental concern. The experimental data of a mutagenicity test on human B-lymphoblastoid cells (alternative to the Ames bacterial test) for a set of 70 oxo-, nitro- and unsubstituted PAHs, detected in particulate matter (PM), were modelled by Quantitative Structure-Activity Relationships (QSAR) classification methods (k-NN, k-Nearest Neighbour, and CART, Classification and Regression Tree) based on different theoretical molecular descriptors selected by Genetic Algorithms. The best models were validated for predictivity both externally and internally. For external validation, Self Organizing Maps (SOM) were applied to split the original data set. The best models, developed on the training set alone, show good predictive performance also on the prediction set chemicals (sensitivity 69.2-87.1%, specificity 62.5-87.5%). The classification of PAHs according to their mutagenicity, based only on a few theoretical molecular descriptors, allows a preliminary assessment of the human health risk, and the prioritisation of these compounds.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:chemical
pubmed:status
MEDLINE
pubmed:issn
1062-936X
pubmed:author
pubmed:issnType
Print
pubmed:volume
19
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
115-27
pubmed:meshHeading
pubmed:articleTitle
Prediction of PAH mutagenicity in human cells by QSAR classification.
pubmed:affiliation
QSAR Research Unit in Environmental Chemistry and Ecotoxicology, Department of Structural and Functional Biology, University of Insubria, Varese, Italy. ester.papa@uninsubria.it
pubmed:publicationType
Journal Article, Research Support, Non-U.S. Gov't, Evaluation Studies