Önlü S, Türker Saçan M
a Boğaziçi University, Institute of Environmental Sciences , Hisar Campus, Istanbul , Turkey.
SAR QSAR Environ Res. 2017 Jun;28(6):491-509. doi: 10.1080/1062936X.2017.1343253. Epub 2017 Jul 14.
Quantitative structure-activity relationship (QSAR) modelling is a major tool employed in the prediction of various endpoints. However, current QSAR literature is missing a full understanding of the impact of quantum chemical calculation methods on the estimation of molecular descriptors and model performance. Here, we provide a comprehensive analysis of the quantitative effects of different geometry optimization methods (semi-empirical, ab initio Hartee-Fock and density functional theory) on the molecular descriptors. Using experimental binding affinity to human serum albumin (HSA) data, we comparatively investigated the influence of employing descriptors derived from three calculation methods on the QSAR models. We propose a 4-descriptor QSAR model in line with the OECD validation principles for the prediction of drug binding affinity to HSA (log K) as a potential tool for drug development. We also confirm the prediction capability of the proposed model on a heterogeneous external set of chemicals. Furthermore, we recommend an activity-independent rational approach for the selection of geometry optimization method for an improved QSAR model development.
定量构效关系（QSAR）建模是预测各种终点的主要工具。然而，当前的QSAR文献对量子化学计算方法对分子描述符估计和模型性能的影响缺乏全面理解。在此，我们全面分析了不同几何优化方法（半经验方法、从头算Hartree-Fock方法和密度泛函理论）对分子描述符的定量影响。利用与人类血清白蛋白（HSA）结合亲和力的实验数据，我们比较研究了采用源自三种计算方法的描述符对QSAR模型的影响。我们根据经合组织（OECD）验证原则提出了一个四描述符QSAR模型，用于预测药物与HSA的结合亲和力（log K），作为药物开发的潜在工具。我们还证实了所提出模型对一组异类外部化学品的预测能力。此外，我们推荐一种与活性无关的合理方法来选择几何优化方法，以改进QSAR模型开发。
