Anti-inflammatory activity of a series of tri-substituted pyrimidine derivatives was predicted using two Quantitative Structure-Activity Relationship models. These relationships were developed from molecular descripto...Anti-inflammatory activity of a series of tri-substituted pyrimidine derivatives was predicted using two Quantitative Structure-Activity Relationship models. These relationships were developed from molecular descriptors calculated using the DFT quantum chemistry method using the B3LYP/6-31G(d,p) level of theory and molecular lipophilicity. Thus, the four descriptors which are the dipole moment μ<sub>D</sub>, the energy of the highest occupied molecular orbital E<sub>HOMO</sub>, the isotropic polarizability α and the ACD/logP lipophilicity were selected for this purpose. The Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models are respectively accredited with the following statistical indicators: R<sup>2</sup>=91.28%, R<sup>2</sup><sub>aj</sub>=89.11%, RMCE = 0.2831, R<sup>2</sup><sub>ext</sub>=86.50% and R<sup>2</sup>=98.22%, R<sup>2</sup><sub>aj</sub>=97.75%, RMCE = 0.1131, R<sup>2</sup><sub>ext</sub>=98.54%. The results obtained with the artificial neural network are better than those of the multiple linear regression. However, these results show that the two models developed have very good predictive performance of anti-inflammatory activity. These two models can therefore be used to predict anti-inflammatory activity of new similar pyrimidine derivatives.展开更多
Based on molecular topological chemical theory,as well as the structural characteristic and the valence connection bonding atom i,we introduced structure information index mE(m=0,1).Combing with electronic structure p...Based on molecular topological chemical theory,as well as the structural characteristic and the valence connection bonding atom i,we introduced structure information index mE(m=0,1).Combing with electronic structure parameter of chlorophenols,the new method with ANN analysis was used to predict the biology-toxicity parameters of chlorophenols.The prediction result was more satisfied than others analysis.展开更多
In this article, generalized torsion angles of derivatives of 1 [(2 hydroxyethoxy)methyl] 6 (phenylthio)thymine(HEPT) were calculated, which include abundant three dimensional information of molecules. Molecular simil...In this article, generalized torsion angles of derivatives of 1 [(2 hydroxyethoxy)methyl] 6 (phenylthio)thymine(HEPT) were calculated, which include abundant three dimensional information of molecules. Molecular similarity matrix was built based on the calculated generalized torsion angles. These similarities were taken as the new variables, and the new variables were selected by using Leaps and Bounds regression analysis. Multiple regression analysis and neural networks were performed, and the satisfactory results were achieved by using the neural networks.展开更多
文摘Anti-inflammatory activity of a series of tri-substituted pyrimidine derivatives was predicted using two Quantitative Structure-Activity Relationship models. These relationships were developed from molecular descriptors calculated using the DFT quantum chemistry method using the B3LYP/6-31G(d,p) level of theory and molecular lipophilicity. Thus, the four descriptors which are the dipole moment μ<sub>D</sub>, the energy of the highest occupied molecular orbital E<sub>HOMO</sub>, the isotropic polarizability α and the ACD/logP lipophilicity were selected for this purpose. The Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models are respectively accredited with the following statistical indicators: R<sup>2</sup>=91.28%, R<sup>2</sup><sub>aj</sub>=89.11%, RMCE = 0.2831, R<sup>2</sup><sub>ext</sub>=86.50% and R<sup>2</sup>=98.22%, R<sup>2</sup><sub>aj</sub>=97.75%, RMCE = 0.1131, R<sup>2</sup><sub>ext</sub>=98.54%. The results obtained with the artificial neural network are better than those of the multiple linear regression. However, these results show that the two models developed have very good predictive performance of anti-inflammatory activity. These two models can therefore be used to predict anti-inflammatory activity of new similar pyrimidine derivatives.
文摘Based on molecular topological chemical theory,as well as the structural characteristic and the valence connection bonding atom i,we introduced structure information index mE(m=0,1).Combing with electronic structure parameter of chlorophenols,the new method with ANN analysis was used to predict the biology-toxicity parameters of chlorophenols.The prediction result was more satisfied than others analysis.
文摘In this article, generalized torsion angles of derivatives of 1 [(2 hydroxyethoxy)methyl] 6 (phenylthio)thymine(HEPT) were calculated, which include abundant three dimensional information of molecules. Molecular similarity matrix was built based on the calculated generalized torsion angles. These similarities were taken as the new variables, and the new variables were selected by using Leaps and Bounds regression analysis. Multiple regression analysis and neural networks were performed, and the satisfactory results were achieved by using the neural networks.
