Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes

• Autoři: BOHÁČ Michal; LOEPRECHT Bjorn; DAMBORSKÝ Jiří; SCHUURMANN Gerrit
• Rok publikování: 2002
• Druh: Článek v odborném periodiku
• Časopis / Zdroj: Quantitative Structure-Activity Relationships
• Fakulta / Pracoviště MU: Přírodovědecká fakulta
• www: http://ncbr.chemi.muni.cz/~jiri/ABSTRACTS/qsarj02.html
• Obor: Mikrobiologie, virologie
• Klíčová slova: QSAR; VALIDATION; COMFA; GOLPE; VARIABLE SELECTION
• Popis: 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.

Související projekty

• Racionální re-design mikrobiálních enzymů podílejících se na degradaci toxických organických polutantů
• Strukturně-funkční vztahy biomolekul a jejich role v metabolismu