Support vector regression-guided unravelling: antioxidant capacity and quantitative structure-activity relationship predict reduction and promotion effects of flavonoids on acrylamide formation.
Support vector regression-guided unravelling: antioxidant capacity and quantitative structure-activity relationship predict reduction and promotion effects of flavonoids on acrylamide formation.
复制标题
支持向量回归引导的解析：抗氧化能力和定量构效关系预测黄酮类化合物对丙烯酰胺形成的减少和促进作用
DOI：
10.1038/srep32368
复制
发表时间：
2016-09-02
影响因子：
4.6
通讯作者：
Zhang Y
中科院分区：
文献类型：
--
作者：
Huang M;Wei Y;Wang J;Zhang Y
采用支持向量回归（SVR）方法预测和揭示了低水分Maillard反应体系中特征黄酮类化合物对丙烯酰胺生成的抑制/促进作用。结果表明，黄酮类化合物在1-10000 μmol/L范围内具有还原/促进作用。黄酮类化合物、黄酮醇类化合物和异黄酮类化合物在100 μmol/L和10000 μmol/L浓度下，抑制率和促进率分别为51.7%、68.8%和26.1%和57.7%、178.8%和27.5%。还原/促进效应与trolox等效抗氧化能力（ΔTEAC）的变化密切相关，并通过SVR模型的三重ΔTEAC测量得到了很好的预测（R：0.633-0.900）。黄酮醇类化合物对丙烯酰胺生成的影响强于黄酮类化合物和异黄酮类化合物及其O-糖苷衍生物，这可能与酚羟基和3-烯醇羟基的数量和位置有关。采用优化的定量构效关系（QSAR）描述符和支持向量回归（SVR）模型对还原/促进效应进行了较好的预测（R：0.926-0.994）。与人工神经网络和多元线性回归模型相比，SVR模型在TEAC依赖和QSAR依赖的预测工作中表现出更好的拟合性能。这些观察结果表明，SVR模型能够预测我们对未来使用天然抗氧化剂减少丙烯酰胺形成的理解。
We used the support vector regression (SVR) approach to predict and unravel reduction/promotion effect of characteristic flavonoids on the acrylamide formation under a low-moisture Maillard reaction system. Results demonstrated the reduction/promotion effects by flavonoids at addition levels of 1–10000 μmol/L. The maximal inhibition rates (51.7%, 68.8% and 26.1%) and promote rates (57.7%, 178.8% and 27.5%) caused by flavones, flavonols and isoflavones were observed at addition levels of 100 μmol/L and 10000 μmol/L, respectively. The reduction/promotion effects were closely related to the change of trolox equivalent antioxidant capacity (ΔTEAC) and well predicted by triple ΔTEAC measurements via SVR models (R: 0.633–0.900). Flavonols exhibit stronger effects on the acrylamide formation than flavones and isoflavones as well as their O-glycosides derivatives, which may be attributed to the number and position of phenolic and 3-enolic hydroxyls. The reduction/promotion effects were well predicted by using optimized quantitative structure-activity relationship (QSAR) descriptors and SVR models (R: 0.926–0.994). Compared to artificial neural network and multi-linear regression models, SVR models exhibited better fitting performance for both TEAC-dependent and QSAR descriptor-dependent predicting work. These observations demonstrated that the SVR models are competent for predicting our understanding on the future use of natural antioxidants for decreasing the acrylamide formation.
登录
查看更多内容
影响因子：
13.1
作者：
Goodarzi, Mohammad;Funar-Timofei, Simona;Vander Heyden, Yvan
通讯作者：
Vander Heyden, Yvan
影响因子：
5.6
作者：
Brunetti C;Di Ferdinando M;Fini A;Pollastri S;Tattini M
通讯作者：
Tattini M
影响因子：
3.9
作者：
Li, Dong;Chen, Yaqi;Zhang, Yingy
通讯作者：
Zhang, Yingy
影响因子：
6.1
作者：
Jiao, Jingjing;Zhang, Yu;Zhang, Ying
通讯作者：
Zhang, Ying
影响因子：
6.1
作者：
Locas, Carolina Perez;Yaylayan, Varoujan A.
通讯作者：
Yaylayan, Varoujan A.