化工进展
化工進展
화공진전
CHEMICAL INDUSTRY AND ENGINEERING PROGRESS
2010年
1期
25-28
,共4页
人工神经网络%定量结构-活性关系%三苯基丙烯腈衍生物
人工神經網絡%定量結構-活性關繫%三苯基丙烯腈衍生物
인공신경망락%정량결구-활성관계%삼분기병희정연생물
artificial neural network (ANN)%quantitative structure-activity relationship (QSAR)%triphenylacrylonitrile derivatives
采用人工神经网络(ANN)BP算法探讨了24个三苯基丙烯睛衍生物的1gl/C(C为半致死浓度)与X位羟基指示数I、分子表面积S_A和B环上原子净电荷之和Q_B之间的关系,以20个样本为训练集建立了定量结构-活性关系(QSAR)模型,其相关系数和标准偏差分别为R=0.9969和SD=0.0164,其余4个样本为测试集,得到R=0.9913和SD=0.1533;用多元线性回归(MLR)方法建立的QSAR模型R=0.9360,SD=0.3779.结果表明,ANN方法具有良好的预测能力,比MLR方法更精密.
採用人工神經網絡(ANN)BP算法探討瞭24箇三苯基丙烯睛衍生物的1gl/C(C為半緻死濃度)與X位羥基指示數I、分子錶麵積S_A和B環上原子淨電荷之和Q_B之間的關繫,以20箇樣本為訓練集建立瞭定量結構-活性關繫(QSAR)模型,其相關繫數和標準偏差分彆為R=0.9969和SD=0.0164,其餘4箇樣本為測試集,得到R=0.9913和SD=0.1533;用多元線性迴歸(MLR)方法建立的QSAR模型R=0.9360,SD=0.3779.結果錶明,ANN方法具有良好的預測能力,比MLR方法更精密.
채용인공신경망락(ANN)BP산법탐토료24개삼분기병희정연생물적1gl/C(C위반치사농도)여X위간기지시수I、분자표면적S_A화B배상원자정전하지화Q_B지간적관계,이20개양본위훈련집건립료정량결구-활성관계(QSAR)모형,기상관계수화표준편차분별위R=0.9969화SD=0.0164,기여4개양본위측시집,득도R=0.9913화SD=0.1533;용다원선성회귀(MLR)방법건립적QSAR모형R=0.9360,SD=0.3779.결과표명,ANN방법구유량호적예측능력,비MLR방법경정밀.
The relationship between the affinity of 24 triphenylacrylonitrile derivatives acting on estrogen receptor in calf uterine tissue (1gl/C)and X-hydroxy indicators (I), molecular surface area (S_A), and the sum of net charge on B ring (Q_B) was discussed based on an improved back-propagation (BP) algorithm of artificial neural network (ANN). Selecting 20 compounds as the training set, the QSAR model was established with the ANN method. The residual 4 compounds as the prediction set were applied to test the predicted effect of the QSAR model. It was obtained that the correlation coefficient of QSAR model was R=0.9969 and the standard deviationwas SD=0.0164. For the prediction set, R=0.9969 and SD=0.1533. The QSAR model for the same 24 compounds was also established with the multiple linear regression (MLR) method for comparison, with which R=0.9360 and SD=0.3779 were obtained. The results indicated that the fitted performance of ANN method is better than that of MLR model, which is comparatively precise and has a preferable predicted effect.