Quality Control in QSAR Model Development 

Quantitative Structure Property Relationship (QSPR) modeling finds growing applications in chemical data mining and combinatorial library design. This presentation emphasizes the importance of rigorous validation as a crucial component of QSPR model development. I shall present a set of simple guidelines for developing validated and predictive QSPR models. I will discuss several validation strategies including (1) randomization of the modelled property, also called Y-scrambling, (2) external validation using rational division of a dataset into training and test sets, and (3) identification of the model applicability domain in the chemical space to flag molecules for which predictions may be unreliable. I will summarize these developments in the form of QSPR workflow that should be followed by QSPR practitioners. I will present examples of successful database mining using validated QSPR models. Finally, I shall discuss the application of QSPR modelling strategies in structure based drug discovery.