• 综合性科技类中文核心期刊
    • 中国科技论文统计源期刊
    • 中国科学引文数据库来源期刊
    • 中国学术期刊文摘数据库(核心版)来源期刊
    • 中国学术期刊综合评价数据库来源期刊

电性距离矢量和神经网络用于三唑并嘧啶磺酰胺类除草剂的QSAR研究

陈艳, 冯长君, 堵锡华

陈艳, 冯长君, 堵锡华. 电性距离矢量和神经网络用于三唑并嘧啶磺酰胺类除草剂的QSAR研究[J]. 北京工业大学学报, 2014, 40(5): 771-775.
引用本文: 陈艳, 冯长君, 堵锡华. 电性距离矢量和神经网络用于三唑并嘧啶磺酰胺类除草剂的QSAR研究[J]. 北京工业大学学报, 2014, 40(5): 771-775.
CHEN Yan, FENG Zhang-jun, DU Xi-hua. QSAR Research of Triazolopyrimidine Herbcides by Electronegativity-distance Vector and Artificial Neural Network[J]. Journal of Beijing University of Technology, 2014, 40(5): 771-775.
Citation: CHEN Yan, FENG Zhang-jun, DU Xi-hua. QSAR Research of Triazolopyrimidine Herbcides by Electronegativity-distance Vector and Artificial Neural Network[J]. Journal of Beijing University of Technology, 2014, 40(5): 771-775.

电性距离矢量和神经网络用于三唑并嘧啶磺酰胺类除草剂的QSAR研究

基金项目: 

国家自然科学基金资助项目(21272095)

徐州工程学院培育项目(XKY2011102)

详细信息
    作者简介:

    陈艳(1968—),女,教授,主要从事有机合成及物质构效学方面的研究,E-mail:chenyan681110@126.com

  • 中图分类号: O626.41

QSAR Research of Triazolopyrimidine Herbcides by Electronegativity-distance Vector and Artificial Neural Network

  • 摘要: 为了研究三唑并嘧啶磺酰胺类除草剂对乙酰乳酸合成酶(aceto lactate synthase,ALS)抑制活性(pI50)的定量构效关系,以电性距离矢量(Mk)表征了31种三唑并嘧啶磺酰胺类化合物的分子结构;利用最佳变量子集回归的方法建立了含有6个参数(m2M10M14M15M67M85)的QSAR模型.该模型的相关系数R及交叉验证相关系数RCV分别为0.911、0.887,具有良好的稳健性和预测能力;以此6个参数为人工神经网络输入层,设定6∶3∶1的网络结构,构建人工神经网络的BP算法模型,相关系数R提升为0.988.结果表明:影响三唑并吡啶磺胺类除草剂抑制活性pI50的主要因素是-CH3、-CH2-、>C-、-O-、>N-及-X(-F,-Cl)等分子结构单元,且pI50与m2M10M14M15M67M85呈现良好的非线性关系,为设计高活性的ALS抑制剂提供理论依据.
    Abstract: To study the quantitative structure-activity relationship(QSAR) of the inhibited activity(pI50) for aceto lactate synthase(ALS) inhibitor,molecular electronegativity-distance vector(Mk) was used to describe the molecular structure of 31 triazolopyrimidine herbcides in this paper. The sixparameter(m2M10M14M15M67M85) QSAR model of pI50 for 31 the triazolopyrimidine compounds was constructed by leaps-and-bounds regression(LBR). The traditional correlation coefficient(R) and the cross-validation correlation coefficient(RCV) were 0.911 and 0.887,respectively. The six structural parameters were used as the input neurons of artificial neural network,and a 6∶ 3 ∶ 1 network architecture was employed. A satisfied model could be constructed with the back-propagation algorithm,the correlation coefficient R was 0. 988. The result demonstrates that the dominant influencing factors of inhibited activity are the molecular structure fragments:-CH3、-CH2-、> C-、-O-、> N-及-X(-F,-Cl),and there is a good non-linear relationship between the parameter m2M10M14M15M67M85) QSAR model of pI50 and pI50 of ALS. The model can provide some theoretical insights into the design of this series of ALS inhibitor with higher inhibited activity.
计量
  • 文章访问数:  8
  • HTML全文浏览量:  0
  • PDF下载量:  6
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-04-10
  • 网络出版日期:  2023-01-10

目录

    /

    返回文章
    返回