Wiriyarattanakul Amphawan, Xie Wanting, Toopradab Borwornlak, Wiriyarattanakul Sopon, Shi Liyi, Rungrotmongkol Thanyada, Maitarad Phornphimon
Program in Chemistry, Faculty of Science and Technology, Uttaradit Rajabhat University, Uttaradit 53000, Thailand.
Research Center of Nano Science and Technology, College of Sciences, Shanghai University, Shanghai 200444, P. R. China.
ACS Omega. 2024 Feb 7;9(7):7817-7826. doi: 10.1021/acsomega.3c07386. eCollection 2024 Feb 20.
Quantitative structure-activity relationship (QSAR) analysis, an silico methodology, offers enhanced efficiency and cost effectiveness in investigating anti-inflammatory activity. In this study, a comprehensive comparative analysis employing four machine learning algorithms (random forest (RF), gradient boosting regression (GBR), support vector regression (SVR), and artificial neural networks (ANNs)) was conducted to elucidate the activities of naturally derived compounds from durian extraction. The analysis was grounded in the exploration of structural attributes encompassing steric and electrostatic properties. Notably, the nonlinear SVR model, utilizing five key features, exhibited superior performance compared to the other models. It demonstrated exceptional predictive accuracy for both the training and external test datasets, yielding values of 0.907 and 0.812, respectively; in addition, their RMSE resulted in 0.123 and 0.097, respectively. The study outcomes underscore the significance of specific structural factors (denoted as shadow ratio, dipole , methyl, ellipsoidal volume, and methoxy) in determining anti-inflammatory efficacy. Thus, the findings highlight the potential of molecular simulations and machine learning as alternative avenues for the rational design of novel anti-inflammatory agents.
定量构效关系（QSAR）分析作为一种计算机辅助方法，在研究抗炎活性方面具有更高的效率和成本效益。在本研究中，采用四种机器学习算法（随机森林（RF）、梯度提升回归（GBR）、支持向量回归（SVR）和人工神经网络（ANNs））进行了全面的比较分析，以阐明榴莲提取物中天然衍生化合物的活性。该分析基于对包括空间和静电性质在内的结构属性的探索。值得注意的是，利用五个关键特征的非线性SVR模型表现出比其他模型更优的性能。它在训练数据集和外部测试数据集上均显示出卓越的预测准确性，分别得到0.907和0.812的值；此外，它们的均方根误差分别为0.123和0.097。研究结果强调了特定结构因素（表示为阴影比、偶极、甲基、椭球体积和甲氧基）在确定抗炎功效中的重要性。因此，这些发现突出了分子模拟和机器学习作为新型抗炎药物合理设计替代途径的潜力。
