人工神经网络在吡喃酮类化合物生物活性预测中的应用

Application of Artificial Neural Network on Bioactivity Prediction of Pyranones

采用Chemoffice 2004中的MOPAC-PM3算法对吡喃酮类化合物的量子化学结构参数进行计算,并将筛选后的量化参数作为吡喃酮类化合物的结构描述符。采用分子结构描述符对吡喃酮类化合物进行结构表征和抗人类免疫缺陷病毒(HIV)的活性预测,利用人工神经网络中的径向基网络建立分子结构描述符与生物活性间的相关模型。当sp=0.41时,结果显示网络训练集预测均方差MSE几乎为0,而网络仿真预测MSE为0.0066,总MSE为0.000 7。结果表明径向基人工神经网络具有高数值逼近能力,提高了对吡喃酮类化合物结构的预测精度。

MOPAC-PM3 algorithm in Chemoffice 2004 was used to calculate quantum chemical structure parameters of pyranones,and the quantization parameter selection were used as descriptors of pyra-nones. With molecular descriptors,the structure of pyranones compounds were characterized and antihuman immunodeficiency virus(HIV)activity was predicted. The model on molecular descriptors andbiological activity was established with RBF neural network of artificial neural network. When sp= 0. 41,the results showed that the predicting variance of MSE for network training set is nearly 0,and the net-work simulation and prediction of MSE was 0. 006 6,the total MSE was 0. 000 7. The results showedthat the RBF neural network had the feature of high digital approximation,which improved the predition accuracy of structure of pyranones compounds.