基于人工神经网络研究多羟基苯甲醛席夫碱类化合物的抗氧化活性  

Research on the Antioxidant Activity of Polyhydroxy Benzaldehyde Schiff bases on the Artificial Neural Network

作　　者：朱利兰 ZHU Li-lan(Department of Physical Education,Guangdong Industry Polytechnic,Guangzhou 510300,China)

机构地区：[1]广东轻工职业技术学院体育部,广东广州510300

出　　处：《安徽化工》2024年第6期69-72,共4页Anhui Chemical Industry

基　　金：广东轻工职业技术学院自然科学基金(KJ2019-032)资助。

摘　　要：为了研究多羟基苯甲醛席夫碱类化合物的抗氧化性(Fr)的定量构效关系,按照分子的拓扑环境编程计算了电性距离矢量(ED)。基于ED关联19种多羟基苯甲醛席夫碱类化合物的Fr,建立3参数E21、E66、E77的构效关系模型,非交叉验证与交叉验证的相关系数R^(2)和Q^(2)分别为0.717、0.538,具有良好的稳健性和预测能力。该模型显示,影响Fr的重要因素是-C-、=N≤、-OH等分子结构单元。以此三参数为人工神经网络输入层,设定3∶3∶1的网络结构,构建人工神经网络的BP算法(back-propagation algorithm,BP)模型,传统相关系数R^(2)为0.973,标准误差S为8.62。结果表明,多羟基苯甲醛席夫碱类化合物的抗氧化性与E_(21)、E_(66)、E_(77)呈良好的非线性关系,用其表征Fr具有合理性和有效性,为设计高抗氧化活性的多羟基苯甲醛席夫碱类化合物提供理论依据。In order to study the quantitative structure-activity relationship(QSAR)of the antioxidant activity(Fr)for 19 polyhydroxy benzaldehyde schiff bases,the molecular electronegativity distance vector(ED)was calculated by program ac⁃cording to molecular topological environment in this paper.On the basis of ED,the three-parameter(E21,E66,E77)QSAR model of Fr for above compounds was constructed.The traditional correlation coefficient(R^(2))and the cross-validation cor⁃relation coefficient(Q^(2))are 0.717 and 0.538,respectively.The result demonstrates that the model is highly reliable and has good predictive ability from the point of view of statistics.Form the three parameters of the model,it is known that the dominant influence factors of inhibited activity are the molecular structure fragments:−C−,=N≤,−OH in above molecules.The results showed that the stucturic parameter−C−,=N≤,−OH have good rationality and efficiency for the Fr.The three structural parameters are used as the input neurons of artificial neural network,and a 3∶3∶1 network architecture is em⁃ployed.A satisfied model can be constructed with the back-propagation algorithm,the correlation coefficient R and the standard error(s)are 0.973 and 8.62,respectively.This shows that the relationship between Fr and three structural param⁃eters is good nonlinear correlation.The results showed that the new parameter E_(21),E_(66),E_(77) have good rationality and effi⁃ciency for the Fr.Our model could provide some theoretical insights into the design of this series of polyhydroxy benzalde⁃hyde schiff bases with higher antioxidant activity.

关 键 词：多羟基苯甲醛席夫碱类化合物 抗氧化活性 电性距离矢量 定量构效关系 

分 类 号：TS202[轻工技术与工程—食品科学]