Publication Details

Category Text Publication
Reference Category Journals
DOI 10.1002/1521-3838(200205)21:1<3::AID-QSAR3>3.0.CO;2-D
Title (Primary) Impact of orthogonal signal correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes
Author Bohác, M.; Loeprecht, B.; Damborsky, J.; Schüürmann, G.
Source Titel Quantitative Structure-Activity Relationships
Year 2002
Department OEC; COE
Volume 21
Issue 1
Page From 3
Page To 11
Language englisch
Keywords OSC;signal correction;CoMFA;3D-QSAR;external prediction;nitroaromatics
Abstract The impact of orthogonal signal correction (OSC) on the prediction power of CoMFA models was studied using a data set of 47 nitrobenzenes with toxicities (log 1/IC50) towards the aquatic ciliates Tetrahymena pyriformis. Comparative analyses of different data pre-treatments shows that block unscaled weighting (BUW) results in significantly better PLS models than no scaling, centering or autoscaling for OSC. One OSC component is optimal for the signal correction and reduces the X variance by about 40%. While OSC yields improved calibration and cross-validation statistics, standard CoMFA is superior with respect to the external prediction power as evaluated by models built from complementary subsets. Moreover, external prediction reveals some cases of severe OSC overfitting, which needs attention in future investigations.
Persistent UFZ Identifier https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=5371
Bohác, M., Loeprecht, B., Damborsky, J., Schüürmann, G. (2002):
Impact of orthogonal signal correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes
Quant. Struct.-Act. Relat. 21 (1), 3 - 11 10.1002/1521-3838(200205)21:1<3::AID-QSAR3>3.0.CO;2-D