QSAR study of the 5-HT1A receptor affinities of arylpiperazines using a genetic algorithm–artificial neural network model

Quantitative Structure-Activity Relationship for High Affinity 5-HT1A Receptor Ligands Based on Norm Indexes

Arylpiperazine derivatives are promising 5-hydroxytryptamine (5-HT) receptor ligands which can inhibit serotonin reuptake effectively. In this work, some norm index descriptors were proposed and further utilized to develop a model for predicting 5-HT1A receptor affinity (pKi) of 88 arylpiperazine derivatives. Results showed that this new model could provide satisfactory predictions with the square of the correction coefficient (R(2)) of 0.8891 and the squared correlation coefficient of cross-validation (Q(2)) of 0.8082, respectively. In addition, the applicability domain of this model was validated by using the leverage approach and results which suggested potential large scale for further utilization of this model. The results of statistical values and validation tests demonstrated that our proposed norm index based model could be successfully applied for predicting the affinity 5-HT1A receptor ligands of arylpiperazine derivatives.

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.