Image-Based Analysis to Predict the Activity of Tariquidar Analogs as P-Glycoprotein Inhibitors: The Importance of External Validation.

Permeability glycoprotein (P-gp) is involved in the pathology of various diseases including cancer and epilepsy, mainly through the translocation of some medicines across the cell membrane. Here, we employed image-based quantitative structure-activity relationship (QSAR) models to predict the P-gp inhibitory activity of some Tariquidar derivatives. The structures of 65 Tariquidar derivatives and their P-gp inhibition activities were collected from the literature. For each compound, the pixels of bidimensional images and their principal components (PCs) were calculated using MATLAB software. Various statistical methods including principal component regression, artificial neural networks, and support vector machines were employed to investigate the correlation between the PCs and the activity of the compounds. The predictability of the models was investigated using external validation and applicability domain analysis. An artificial neural network-based model demonstrated the best prediction results for the test set. Moreover, external validation analysis of the developed models supports the idea that R(2) cannot assure the validity of QSAR models and another criterion, i.e., the concordance correlation coefficient (CCC) parameter, should be involved to evaluate the validity of the QSAR models. The results of this study indicate that image analysis could be as suitable as descriptors calculated by commercial software to predict the activity of drug-like molecules.

Comparison of various methods for validity evaluation of QSAR models.

BACKGROUND: Quantitative structure-activity relationship (QSAR) modeling is one of the most important computational tools employed in drug discovery and development. The external validation of QSAR models is the main point to check the reliability of developed models for the prediction activity of not yet synthesized compounds. It was performed by different criteria in the literature. METHODS: In this study, 44 reported QSAR models for biologically active compounds reported in scientific papers were collected. Various statistical parameters of external validation of a QSAR model were calculated, and the results were discussed. RESULTS: The findings revealed that employing the coefficient of determination (r2) alone could not indicate the validity of a QSAR model. The established criteria for external validation have some advantages and disadvantages which should be considered in QSAR studies. CONCLUSION: This study showed that these methods alone are not only enough to indicate the validity/invalidity of a QSAR model.

Is regression through origin useful in external validation of QSAR models?

The external validation of QSAR models is crucial to ensure their reliability for assessing new chemicals. The most widely used criteria for external validations, which has been applied in hundreds of more recent QSAR studies are the Golbraikh-Tropsha and Roy methods which these criteria are based on the regression through origin (RTO). In this study, the calculations of the deviation parameters such as absolute errors are used for ascertaining the difference between training and test sets to evaluate the prediction capability of the models. However, these results were not in a good agreement with the proposed criteria for external validation and there is an inconsistency in the definition and calculation of r(2) of RTO and therefore the constructed criteria based on RTO is not optimal. Instead, the calculation of model errors for training and test sets and compare them, provide a possible reliable method to external validation of QSAR models.