Validation QSAR models

Validated QSAR Modeling as an Empirical Data-modeling Approach Combinatorial QSAR... 

Validated QSAR Models as Virtual Screening Tools 445... 

Bigure 16.5 summarizes our approach to using validated QSAR models for virtual screening as applied to the anticonvulsant dataset. It presents a practical example of the drug discovery workflow that can be generalized for any dataset in which sufficient data to develop reliable QSAR models is available. 

In our recent studies we were fortunate to recruit experimental collaborators who have validated computational hits identified by virtual screening of commercially available compound libraries using rigorously validated QSAR models. Examples include anticonvulsants (25), HIV-1 reverse transcriptase inhibitors (32), D1 antagonists (33), antitumor compounds (34), beta-lactamase inhibitors (35), human histone deacetylase (HDAC) inhibitors... 

Oloff, S., Mailman, R. B., Tropsha, A. (2005) Application of validated QSAR models of D1 dopaminergic antagonists for database mining. J Med Chem 48, 7322-7332. 

Chemical reactivity and biological activity can be related to molecular structure and physicochemical properties. QSAR models can be established among hydrophobic-lipophilic, electronic, and steric properties, between quantum-mechanics-related parameters and toxicity and between environmental fate parameters such as sorption and tendency for bioaccumulation. The main objective of a QSAR study is to develop quantitative relationships between given properties of a set of chemicals and their molecular descriptors. To develop a valid QSAR model, the following steps are essential ... 

Golbraikh, A., Shen, M., Xiao, Z., Xiao, Y.-D., Lee, K.-H. and Tropsha, A. (2003) Rational selection of training and test sets for the development of validated QSAR models./. Computer-Aided Mol. Design, 17, 241. 

P. Gramatica et al., Approaches for externally validated QSAR modelling of Nitrated Polycyclic Aromatic Hydrocarbon mutagenicity. SAR QSAR Environ. Res. 18, 169-178 (2007)... 

From the literature, 64 regression models for specific compound classes were retrieved, of which 35 could be tested with the MITI-I data, but only 7 QSARs were successfully validated. These models were derived with four to eight homologous substances and, because of their specificity, they are suitable for application to corresponding substances only. The number of validated QSAR models for specific compound classes is too low to make predictions solely on this basis in the MITI-I data set they were applicable for estimating the biodegradability of only 3% of the chemicals. 

Figure 10.1 Flowchart of predictive QSAR modeling framework based on the validated QSAR models.

To illustrate the power of validated QSAR models as virtual sereening tools we diseuss the examples of studies that resulted in experimentally eonfirmed hits. Sueh studies eould only be performed if there is sufficient data available for a series of tested compounds such that robust validated models could be developing using the workflow described in Figure 10.1. 

S. Zhang, L. Wei, K. Bastow, W. Zheng, A. Brossi, K. H. Lee and A. Tropsha, Antitumor Agents 252. Application of validated QSAR models to database mining discovery of novel tylophorine derivatives as potential anticancer agents., J. Comput. Aided Mol. Des, 2007, 21, 97-112. 

As discussed earlier, to obtain a reliable (validated) QSAR model, an available data set... 

Finally, explore and exploit validated QSAR models for possible mechanistic interpretation and prediction. 

In the modern age of medicinal chemistry, QSAR modeling remains one of the most important instruments of computer-aided drug design. Skillful application of various methodologies discussed in this chapter will afford validated QSAR models, which should continue to enrich and facilitate the experimental process of drug discovery and development. 

---