Quantitative structure–activity relationship study using artificial neural network (ANN) methodology were conducted to predict the inhibition constants of 127 symmetrical and unsymmetrical cyclic urea and cyclic cyan...Quantitative structure–activity relationship study using artificial neural network (ANN) methodology were conducted to predict the inhibition constants of 127 symmetrical and unsymmetrical cyclic urea and cyclic cyanoguanidine derivatives containing different substituent groups such as: benzyl, isopropyl, 4-hydroxybenzyl, ketone, oxime, pyrazole, imidazole, triazole and having anti-HIV-1 protease activities. The results obtained by artificial neural network give advanced regression models with good prediction ability. The two optimal artificial neural network models obtained have coefficients of determination of 0.746 and 0.756. The lowest prediction’s root mean square error obtained is 0.607. Artificial neural networks provide improved models for heterogeneous data sets without splitting them into families. Both the external and cross-validation methods are used to validate the performances of the resulting models. Randomization test is employed to check the suitability of the models.展开更多
The Quantitative Structure-Activity Relationship （QSAR） of a series of novel calanolide analogues,which exhibit inhibitory activities of HIV-1,has been studied with a combined method of ab initio （HF）,molecular me...The Quantitative Structure-Activity Relationship （QSAR） of a series of novel calanolide analogues,which exhibit inhibitory activities of HIV-1,has been studied with a combined method of ab initio （HF）,molecular mechanics （MM＋） and statistics. The established QSAR model （Eq. 1） shows a reasonable regressive performance （R2 = 0.885）. Both the surface area of the substituted group attached on C10,SR3,and the distance between atoms O13 and X14 （O,N,S）,L,of the calanolide analogues play important roles in determining the inhibitory activity of HIV-1.展开更多
文摘Quantitative structure–activity relationship study using artificial neural network (ANN) methodology were conducted to predict the inhibition constants of 127 symmetrical and unsymmetrical cyclic urea and cyclic cyanoguanidine derivatives containing different substituent groups such as: benzyl, isopropyl, 4-hydroxybenzyl, ketone, oxime, pyrazole, imidazole, triazole and having anti-HIV-1 protease activities. The results obtained by artificial neural network give advanced regression models with good prediction ability. The two optimal artificial neural network models obtained have coefficients of determination of 0.746 and 0.756. The lowest prediction’s root mean square error obtained is 0.607. Artificial neural networks provide improved models for heterogeneous data sets without splitting them into families. Both the external and cross-validation methods are used to validate the performances of the resulting models. Randomization test is employed to check the suitability of the models.
基金supported by the Scientific Research Foundation of Department of Education of Yunnan Province ( No. 09Y0181)
文摘The Quantitative Structure-Activity Relationship （QSAR） of a series of novel calanolide analogues,which exhibit inhibitory activities of HIV-1,has been studied with a combined method of ab initio （HF）,molecular mechanics （MM＋） and statistics. The established QSAR model （Eq. 1） shows a reasonable regressive performance （R2 = 0.885）. Both the surface area of the substituted group attached on C10,SR3,and the distance between atoms O13 and X14 （O,N,S）,L,of the calanolide analogues play important roles in determining the inhibitory activity of HIV-1.
