Validity assessments of QSARs

Models in QSAR analysis are local, and hence are valid only for limited changes in chemical structures and biological activity. Outside this range, the models validity is not substantiated. A validity assessment of a QSAR evaluates the accuracy and precision of the estimates with due regard to the experimental variability in the respective endpoint. It is trivial, but still needs to be remembered, that QSAR predictions can never be more exact than the underlying experimental data. The criteria for assessing the validity of a QSAR model concern  

The statistical validity of the model The range of the model compound classes range of descriptors. 

The standards regarding the statistical validity of a QSAR model (section 3.2) relate to the goodness of fit of the equation to the training-set data. For 

Only within these limits of the descriptor values can the relationship be assumed to hold. Beyond this domain, the model may reveal a different type of relationship of the activity on the structural descriptors, which evidently must result in erroneous predictions. A striking example of the pitfalls of inapt extrapolations can be demonstrated with the application of a fourth-order polynominal log BCF/log QSAR (Connell and Hawker, 1988) outside its parameter range (log 2.6-9.8). Because of the curvature of the model, higher BCF estimates result for compounds with log P = 0 than for 

Cross-validation is one method to check the soundness of a statistical model (Cramer, Bunce and Patterson, 1988 Eriksson, Verhaar and Hermens, 1994). The data set is divided into groups, usually five to seven, and the model is recalculated without the data from each of the groups. Consecutively, predictions are obtained for the omitted compounds and compared to the actual data. The divergences are quantified by the prediction error sum of squares (PRESS sum of squares of predicted minus observed values), which can be transformed to a dimensionless term (Q ) by relating it to the initial sum of squares of the dependent variable (X(AT) )- 

---