【摘要】 目的　应用人工神经网络方法对 6 1种抗生素进行药物分子结构和药物血浆蛋白结合率的定量结构 -药物动力学关系的研究 (QSPR)。方法　建立了含一个隐含层的反传神经网络 ,输出层为实验获得的药物血浆蛋白结合率 ;输入层为计算获得的药物分子的理化参数 ,量化参数和分子连接性指数等药物分子结构参数。为了验证网络训练结果 ,随机挑选 5 1个药物为训练集 ,进行了leave-one -out分析。结果　最后利用挑选剩下的 10个药物进行预测 ,其血浆蛋白结合率的预测值能很好地与实验数据相吻合。结论　所建立的神经网络模型能够有效地进行药物血浆蛋白结合率与药物分子结构的相关性分析。同时也证明了人工神经网络功能强大 ,将成为药物QSPR研究的一个有效工具更多还原

【Abstract】 OBJECTIVE To study and demonstrate the application of neural network to research the quantitative structure-pharmacokinetic relationship(QSPR)of 61 kinds of antimicrobial agents.METHODS Firstly,three-layer back propagation system network was established including an input layer, a hidden layer and an output layer. The input layer of the neural network is the quantum chemistry parameter, physical-chemistry parameter and molecular connectivity index of drug. The output of the neural network is the pharmacokinetic property -drug plasma protein binding(DPPB) of antimicrobial agents which is derived from the experimental data . Secondly, the prediction ability of the network is tested by the leave-one-out method.RESULTS The test involved the prediction of the pharmacokinetic properties(DPPB) of ten compound which have never been seen by the network. The predicted by neural network values shew good agreement with the experimental values. CONCLUSION This result indicates that the neural network described in this study is proper and effective for QSPR research.更多还原