Yaffe Denise, Cohen Yoram, Espinosa Gabriela, Arenas Alex, Giralt Francesc
Department of Chemical Engineering, University of California, Los Angeles, Los Angeles, California 90095-1592, USA.
J Chem Inf Comput Sci. 2003 Jan-Feb;43(1):85-112. doi: 10.1021/ci025561j.
Quantitative structure-property relationships (QSPRs) for estimating a dimensionless Henry's Law constant of organic compounds at 25 degrees C were developed based on a fuzzy ARTMAP and back-propagation neural networks using a heterogeneous set of 495 organic compounds. A set of molecular descriptors developed from PM3 semiempirical MO-theory and topological descriptors (second-order molecular connectivity index) were used as input parameters to the neural networks. Quantum chemical input descriptors included average molecular polarizability, dipole moments (total point charge, total hybridization, and total sum), ionization potential, and heat of formation. The fuzzy ARTMAP/QSPR correlated Henry's Law constant for -6.72 </= logH </= 2.87 with average absolute errors of 0.03 and 0.13 logH units for the overall data and the test set, respectively. The optimal 7-17-1 back-propagation/QSPR model was less accurate and exhibited larger average absolute errors of 0.28 and 0.27 logH units for the validation (recall) and test sets, respectively. The fuzzy ARTMAP-based QSPR was superior to the back-propagation and multiple linear regression/QSPR models for Henry's Law constant of organic compounds.
基于模糊ARTMAP和反向传播神经网络,并使用495种有机化合物的异质集合,开发了用于估算25℃下有机化合物无因次亨利定律常数的定量结构-性质关系(QSPRs)。一组由PM3半经验分子轨道理论和拓扑描述符(二阶分子连接性指数)开发的分子描述符被用作神经网络的输入参数。量子化学输入描述符包括平均分子极化率、偶极矩(总点电荷、总杂化和总和)、电离势和生成热。模糊ARTMAP/QSPR对-6.72≤logH≤2.87时的亨利定律常数进行关联,总体数据和测试集的平均绝对误差分别为0.03和0.13 logH单位。最优的7-17-1反向传播/QSPR模型准确性较低,验证(召回)集和测试集的平均绝对误差分别为0.28和0.27 logH单位。基于模糊ARTMAP的QSPR在有机化合物的亨利定律常数方面优于反向传播和多元线性回归/QSPR模型。