Predictive QSAR Models as Virtual Screening Tools

1 Predictive QSAR Models as Virtual Screening Tools 

In our important paper titled Beware of we have demonstrated the 

Validation of QSAR models is one of the most critical problems of QSAR. Recently, we have extended our requirements for the validation of multiple QSAR models selected by acceptable statistics criteria of prediction of the test set. Additional studies in this critical component of QSAR modeling should establish reliable and commonly accepted good practices for model development. 

2 Applicability Domains and QSAR Model Acceptability Criteria 

One of the most important problems in QSAR analysis is establishing the domain of applicability for each model. In the absence of the applicability domain restriction, each model can formally predict the activity of any compound, even with a completely dilferent structure from those included in the training set. Thus, the absence of the model applicability domain as a mandatory component of any QSAR model would lead to the unjustified extrapolation of the model in the chemistry space and, as a result, a high likelihood of inaccurate predictions. In our research we have always paid particular attention to this issue.The various definitions of applicability domains have been reviewed in Chapter 8 and we refer interested readers to this excellent chapter for additional information on this important subject. 

---