Abstract

In this paper, an accurate and reliable QSAR model of 87 selective ligands for the thyroid hormone receptor β 1 (TRβ1) was developed, based on theoretical molecular descriptors to predict the binding affinity of compounds with receptor. The structural characteristics of compounds were described wholly by a large amount of molecular structural descriptors calculated by DRAGON. Six most relevant structural descriptors to the studied activity were selected as the inputs of QSAR model by a robust optimization algorithm Genetic Algorithm. The built model was fully assessed by various validation methods, including internal and external validation, Y-randomization test, chemical applicability domain, and all the validations indicate that the QSAR model we proposed is robust and satisfactory. Thus, the built QSAR model can be used to fast and accurately predict the binding affinity of compounds (in the defined applicability domain) to TRβ1. At the same time, the model proposed could also identify and provide some insight into what structural features are related to the biological activity of these compounds and provide some instruction for further designing the new selective ligands for TRβ1 with high activity.

Graphical abstract

Predicted −log IC₅₀ values versus experimental values for training set and prediction set (Two side lines express the confidence interval of 95%).

Full-size image (9K)

Keywords: QSAR; Thyroid hormone receptor β; Selective ligands; Drug design; Theoretical molecular descriptors; Genetic Algorithm; Splitting methods; Model validation

Article Outline

1. Introduction

2. Results and discussion

2.1. The analysis of data set

2.2. The splitting of data set

2.3. The construction and internal validation of QSAR models

2.4. The external validation

2.5. The further validation by the training and prediction set obtained from random splitting

2.6. Structural features responsible for activity

3. Conclusion

4. Methodology

4.1. Experimental data

4.2. Calculation of molecular descriptors

4.3. Variable selection based on Genetic Algorithm

4.4. Internal and external validation of models

4.5. Applicability domain of models

Acknowledgements

References