With the artificial neural network（ANN） method combined with the multiple linear regression（MLR）,based on a series of quantum chemical descriptors and molecular connectivity indexes,quantitative structure-activity...With the artificial neural network（ANN） method combined with the multiple linear regression（MLR）,based on a series of quantum chemical descriptors and molecular connectivity indexes,quantitative structure-activity relationship（QSAR） models to predict the acute toxicity（-lgEC50） of substituted aromatic compounds to Photobacterium phosphoreum were established.Four molecular descriptors that appear in the MLR model,namely,the second order valence molecular connectivity index（2XV）,the energy of the highest occupied molecular orbital（EHOMO）,the logarithm of n-octyl alcohol/water partition coefficient（logKow） and the Connolly molecular area（MA）,were inputs of the ANN model.The root-mean-square error（RMSE） of the training and validation sets of the ANN model are 0.1359 and 0.2523,and the correlation coefficient（R） is 0.9810 and 0.8681,respectively.The leave-one-out（LOO） cross validated correlation coefficient（Q L2OO） of the MLR and ANN models is 0.6954 and 0.6708,respectively.The result showed that the two methods are complementary in the calculations.The regression method gave support to the neural network with physical explanation,and the neural network method gave a more accurate model for QSAR.In addition,some insights into the structural factors affecting the acute toxicity and toxicity mechanism of substituted aromatic compounds were discussed.展开更多
The antioxidant and gap junctional communication（GJC） activities of carotenoids are known to be the two main anticancer mechanisms.Quantitative structure-activity relationship（QSAR） models of the two activities we...The antioxidant and gap junctional communication（GJC） activities of carotenoids are known to be the two main anticancer mechanisms.Quantitative structure-activity relationship（QSAR） models of the two activities were developed using stepwise regression and multilayer perceptron neural network based on the calculated descriptors of quantum chemistry.The results showed that the significant molecular descriptor related to the antioxidant activity of carotenoids was the HOMO-LUMO energy gap（EHL） and the molecular descriptor related to the GJC was the lowest unoccupied molecular orbital energy（ELUMO）.The two models of antioxidant activity both showed good predictive power,but the predictive power of the neural network QSAR model of antioxidant activity was better.In addition,the two GJC models have similar,moderate predictive power.The possible mechanisms of antioxidant activity and GJC of carotenoids were discussed.展开更多
10 quantum chemical descriptors of 21 aromatic compounds have been calculated by the semi-empirical quantum chemical method AM1. The Quantitative Structure-Biodegradability Relationships （QSBR） studies were performe...10 quantum chemical descriptors of 21 aromatic compounds have been calculated by the semi-empirical quantum chemical method AM1. The Quantitative Structure-Biodegradability Relationships （QSBR） studies were performed by the multiple linear regression （MLR）, principal component regression （PCR） and back propagation artificial neural network （BP-ANN）, respectively. The root mean square error （RMSE） of the training and validation sets of the BP-ANN model are 0.1363 and 0.0244, the mean absolute percentage errors （MAPE） are 0.1638 and 0.0326, the squared correlation coefficients （R^2） are 0.9853 and 0.9996, respectively. The results show that the BP-ANN model achieved a better prediction result than those of MLR and PCR. In addition, some insights into the structural factors affecting the aerobic biodegradation mechanism were discussed in detail.展开更多
Based on the quantum chemical descriptors,quantitative structure-property relationship（QSPR） models have been developed to estimate and predict the photodegradation rate constant（logK） of polycyclic aromatic hydro...Based on the quantum chemical descriptors,quantitative structure-property relationship（QSPR） models have been developed to estimate and predict the photodegradation rate constant（logK） of polycyclic aromatic hydrocarbons（PAHs） by use of linear method（multiple linear regression,MLR） and non-linear method（back propagation artificial neural network,BP-ANN）.A BP-ANN with 3-3-1 architecture was generated by using three quantum chemical descriptors appearing in the MLR model.The standard heat of formation（HOF）,the gap of frontier molecular orbital energies（ΔELH） and total energy（TE） were inputs and its output was logK.Leave-One-Out（LOO） Cross-Validated correlation coefficient（R^2CV） of the established MLR and BP-ANN models were 0.6383 and 0.7843,respectively.The nonlinear BP-ANN model has better predictive ability compared to the linear MLR model with the root mean square error（RMSE） for training and validation sets to be 0.1071,0.1514 and the squared correlation coefficient（R^2） of 0.9791,0.9897,respectively.In addition,some insights into the molecular structural features affecting the photodegradation of PAHs were also discussed.展开更多
基金supported by the Natural Science Foundation of Fujian Province (D0710019)the Natural Science Foundation of Overseas Chinese Affairs Office of the State Council (06QZR09)
文摘With the artificial neural network（ANN） method combined with the multiple linear regression（MLR）,based on a series of quantum chemical descriptors and molecular connectivity indexes,quantitative structure-activity relationship（QSAR） models to predict the acute toxicity（-lgEC50） of substituted aromatic compounds to Photobacterium phosphoreum were established.Four molecular descriptors that appear in the MLR model,namely,the second order valence molecular connectivity index（2XV）,the energy of the highest occupied molecular orbital（EHOMO）,the logarithm of n-octyl alcohol/water partition coefficient（logKow） and the Connolly molecular area（MA）,were inputs of the ANN model.The root-mean-square error（RMSE） of the training and validation sets of the ANN model are 0.1359 and 0.2523,and the correlation coefficient（R） is 0.9810 and 0.8681,respectively.The leave-one-out（LOO） cross validated correlation coefficient（Q L2OO） of the MLR and ANN models is 0.6954 and 0.6708,respectively.The result showed that the two methods are complementary in the calculations.The regression method gave support to the neural network with physical explanation,and the neural network method gave a more accurate model for QSAR.In addition,some insights into the structural factors affecting the acute toxicity and toxicity mechanism of substituted aromatic compounds were discussed.
基金Supported by the Chinese National Key Technologies R&D Program of 11th Five-year Plan (2006BAD27B06)the Fundamental Research Funds for the Central Universities and Education Foundation of Innovative Engineering Key Project of Education Department (707034)
文摘The antioxidant and gap junctional communication（GJC） activities of carotenoids are known to be the two main anticancer mechanisms.Quantitative structure-activity relationship（QSAR） models of the two activities were developed using stepwise regression and multilayer perceptron neural network based on the calculated descriptors of quantum chemistry.The results showed that the significant molecular descriptor related to the antioxidant activity of carotenoids was the HOMO-LUMO energy gap（EHL） and the molecular descriptor related to the GJC was the lowest unoccupied molecular orbital energy（ELUMO）.The two models of antioxidant activity both showed good predictive power,but the predictive power of the neural network QSAR model of antioxidant activity was better.In addition,the two GJC models have similar,moderate predictive power.The possible mechanisms of antioxidant activity and GJC of carotenoids were discussed.
基金supported by the Natural Science Foundation of Fujian Province (D0710019)the Natural Science Foundation of Overseas Chinese Affairs Office of the State Council (09QZR07)
文摘10 quantum chemical descriptors of 21 aromatic compounds have been calculated by the semi-empirical quantum chemical method AM1. The Quantitative Structure-Biodegradability Relationships （QSBR） studies were performed by the multiple linear regression （MLR）, principal component regression （PCR） and back propagation artificial neural network （BP-ANN）, respectively. The root mean square error （RMSE） of the training and validation sets of the BP-ANN model are 0.1363 and 0.0244, the mean absolute percentage errors （MAPE） are 0.1638 and 0.0326, the squared correlation coefficients （R^2） are 0.9853 and 0.9996, respectively. The results show that the BP-ANN model achieved a better prediction result than those of MLR and PCR. In addition, some insights into the structural factors affecting the aerobic biodegradation mechanism were discussed in detail.
基金supported by the Natural Science Foundation of Fujian Province (D0710019)the Natural Science Foundation of Overseas Chinese Affairs Office of the State Council (06QZR09)
文摘Based on the quantum chemical descriptors,quantitative structure-property relationship（QSPR） models have been developed to estimate and predict the photodegradation rate constant（logK） of polycyclic aromatic hydrocarbons（PAHs） by use of linear method（multiple linear regression,MLR） and non-linear method（back propagation artificial neural network,BP-ANN）.A BP-ANN with 3-3-1 architecture was generated by using three quantum chemical descriptors appearing in the MLR model.The standard heat of formation（HOF）,the gap of frontier molecular orbital energies（ΔELH） and total energy（TE） were inputs and its output was logK.Leave-One-Out（LOO） Cross-Validated correlation coefficient（R^2CV） of the established MLR and BP-ANN models were 0.6383 and 0.7843,respectively.The nonlinear BP-ANN model has better predictive ability compared to the linear MLR model with the root mean square error（RMSE） for training and validation sets to be 0.1071,0.1514 and the squared correlation coefficient（R^2） of 0.9791,0.9897,respectively.In addition,some insights into the molecular structural features affecting the photodegradation of PAHs were also discussed.
