Abstract
Descriptors based on multivariate image analysis have been used to derive predictive QSTR models of the acute toxicities of phenylsulphonylcarboxylates to Vibrio fischeri. Classical and multilinear partial least squares, PLS and N-PLS, respectively, were applied as regression methods, demonstrating similar predictive capability to each other. Model performance was improved in c. 10% after removing an outlier, and the results were in general agreement with the ones previously obtained through CoMFA and extended topochemical atom indices analysis. Overall, this study showed that a simple procedure is able to give highly predictive models, useful in ecotoxicology, independent of the regression method used for this class of compounds.
Original language | English (US) |
---|---|
Pages (from-to) | 953-959 |
Number of pages | 7 |
Journal | Molecular Simulation |
Volume | 36 |
Issue number | 12 |
DOIs | |
State | Published - Oct 2010 |
Keywords
- MIA-QSTR
- N-PLS
- PLS
- Vibrio fischeri
- phenylsulphonyl carboxylates
ASJC Scopus subject areas
- General Chemistry
- Information Systems
- Modeling and Simulation
- General Chemical Engineering
- General Materials Science
- Condensed Matter Physics