Artificial neural network and fragmental approach in prediction of physicochemical properties of organic compounds

被引:20
作者
Artemenko, NV [1 ]
Baskin, II [1 ]
Palyulin, VA [1 ]
Zefirov, NS [1 ]
机构
[1] Moscow MV Lomonosov State Univ, Dept Chem, Moscow 119992, Russia
关键词
artificial neural networks; neural network modeling; viscosity; density; vapor pressure; physicochemical properties; fragmental descriptors; LIQUID VISCOSITY; VAPOR-PRESSURE; PHYSICAL-PROPERTIES; BIOLOGICAL-ACTIVITY; QSPR PREDICTION; DESCRIPTORS; HYDROCARBONS; MODEL;
D O I
10.1023/A:1022467508832
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
An approach based on fragmental descriptors (occurrence number of structural fragments in chemical structures) in conjunction with the artificial neural network technique was developed for predicting the physicochemical properties of organic compounds. The construction of neural network models for predicting the viscosity, density, and saturated vapor pressure for various classes of organic compounds is discussed.
引用
收藏
页码:20 / 29
页数:10
相关论文
共 69 条
[2]  
ARTEMENKO NV, 2001, DOKL AKAD NAUK, V381, P203
[3]  
AVIDON VV, 1978, KHIM FARM ZH+, V12, P88
[4]  
AVIDON VV, 1974, KHIM FARM ZH+, V8, P22
[5]   STRUCTURE-ACTIVITY RELATIONSHIP ORIENTED LANGUAGES FOR CHEMICAL-STRUCTURE REPRESENTATION [J].
AVIDON, VV ;
POMERANTSEV, IA ;
GOLENDER, VE ;
ROZENBLIT, AB .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1982, 22 (04) :207-214
[6]   Use of topostructural, topochemical, and geometric parameters in the prediction of vapor pressure: A hierarchical QSAR approach [J].
Basak, SC ;
Gute, BD ;
Grunwald, GD .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 1997, 37 (04) :651-655
[7]  
BASKIN II, 1993, DOKL AKAD NAUK+, V332, P713
[8]  
Baskin II, 1997, DOKL AKAD NAUK+, V357, P57
[9]  
BASKIN II, 2001, 7 VSER K NEIR I IKH, P419
[10]  
BASKIN II, 1990, C MOL GRAPHS CHEM ST, P5