Artificial neural networks: Non-linear QSAR studies of HEPT derivatives as HIV-1 reverse transcriptase inhibitors

被引：24

作者：

Douali, Latifa ^{[1
]}

Villemin, Didier ^{[2
]}

Zyad, Abdelmajid ^{[3
]}

Cherqaoui, Driss ^{[1
]}

机构：

[1] Univ Cadi Ayyad, Dept Chim, Fac Sci Semlalia, Marrakech, Morocco

[2] ENSI, ISMRA, CNRS, LCMT,UMR 6507, F-14050 Caen, France

[3] Univ Cadi Ayyad, Lab Immunol Biochim & Biol Mol, Fac Sci & Tech, Beni Mellal, Morocco

来源：

MOLECULAR DIVERSITY | 2004年 / 8卷 / 01期

关键词：

anti-HIV; HEPT; neural networks; nonlinearity; quantitative structure-activity;

D O I：

10.1023/B:MODI.0000006753.11500.37

中图分类号：

Q5 [生物化学]; Q7 [分子生物学];

学科分类号：

071010 ; 081704 ;

摘要：

Structure-anti HIV activity relationships were established for a sample of 80 1-[2-hydroxyethoxy-methyl]-6-(phenylthio) thymine (HEPT) using a three-layer neural network (NN). Eight structural descriptors and physicochemical variables were used to characterize the HEPT derivatives under study. The network's architecture and parameters were optimized in order to obtain good results. All the NN architectures were able to establish a satisfactory relationship between the molecular descriptors and the anti-HIV activity. NN proved to give better results than other models in the literature. NN have been shown to be particularly successful in their ability to identify non-linear relationships.

引用

页码：1 / 8

页数：8

共 26 条

[1] APPLICATIONS OF NEURAL NETWORKS IN QUANTITATIVE STRUCTURE-ACTIVITY-RELATIONSHIPS OF DIHYDROFOLATE-REDUCTASE INHIBITORS [J].