人工智能算法在生物药剂学中的应用
|
摘要
人工神经网络(Artificial Neural Network,ANN)是对人脑若干基本特性通过数学方法进行的抽象和模拟,是一种模仿人脑结构及其功能的非线性信息处理系统。BP(Back-Propagation)网络是一种采用反向传播学习算法的神经网络,对于在任意闭区间内的一个连续函数都可以用单隐层的BP网络逼近,一个三层的BP网络就可以完成任意的n维到m维的映射。
遗传算法(Genetic Algorithm,GA)以生物进化过程为背景,模拟生物进化的步骤,将繁殖、杂交、变异、竞争和选择等概念引入到算法中,通过维持一组可行解,并对可行解进行重新组合,改进可行解在多维空间内的移动轨迹或趋向,最终走向最优解。它克服了传统优化方法容易陷入局部极值的缺点,是一种全局优化算法。
本文第一部分将神经网络应用到药物透过人皮肤的渗透性能预测研究中。采集两组数据样本,用Matlab自编程序分别建立了预测药物经皮渗透速率BP网络和预测经皮渗透系数的BP网络模型。两个模型的输入变量相同,为药物的分子量(Mr),油水分配系数(logK_(ow)),供氢数(Hd)和受氢数(Ha)。输出变量分别为药物经皮渗透速率(logJ_(max))和经皮渗透系数(logKp)。前者模型测试组预测logJ_(max)与实际logJ_(max)的相关系数平方为0.997,回归直线的斜率为0.970。后者模型测试组预测得到的logKp与实际logKp的相关系数为0.95,均方误差平方根(RMSE)为0.37。本研究表明BP神经能够很好地预测药物透过皮肤的渗透性能。
第二部分旨在建立一个生物药剂学分类系统(BCS)预测模型。药物在BCS中的分类取决于其溶解性和渗透性。故首先建立药物特征溶解度模型和绝对生物利用度模型。用多元线性回归和神经网络建立溶解度的线性模型和非线性模型,通过模型预测值与实际值的相关系数(R)、均方误差平方根(RMSE)和AIC比较,神经网络模型比逐步线性回归模型优越。用神经网络建立两种预测药物口服绝对生物利用度的模型。前者的输入变量为7个已能明确解释的理论参数,后者的输入变量有15个,包括上述变量和用遗传算法筛选出来的8个变量。通过比较,后者的预测效能优越。采集16个BCS分类明确的药物样本,用自行建立的溶解度模型和生物利用度模型预测分类,溶解度预测准确度为93.8%,渗透性预测准确度为81.2%,生物药剂学分类系统预测准确度为75.0%。
第三部分将神经网络应用到药动学参数的预测,用BP网络预测新生儿丁胺卡那霉素消除速率常数。建立梯度下降BP网络(GD-BP-NN),贝叶斯标准化BP网络(BR-BP-NN)和遗传BP网络(G-BP-NN),以23例新生儿静脉滴注丁胺卡那霉素相关临床资料为研究对象,研究新生儿胎龄、日龄和体重对丁胺卡那霉素消除速率的影响,预测患者的消除速率常数,并比较三种网络的预测精度和运行效率。结果表明GD-BP-NN,BR-BP-NN和G-BP-NN测试组预测值和实验计算值的相关系数分别为0.92,0.91和0.98;测试组均方误差平方根(RMSE)分别是0.020,0.024和0.010;相同的预测精度条件下,GD-BP-NN,BR-BP-NN和G-BP-NN分别运行了2000,219和82步。从中可以看出遗传算法对BP神经网络权值和阈值进行优化,从而克服了BP神经网络训练速度慢,容易陷入局域极小和全局搜索能力弱等缺点,故G-BP-NN预测效果更好。
Artificial neural network(ANN) is a type of mathematical model that simulates the biological nervous system and draws on analogues of adaptive biological learning.It is known to be a powerful tool to simulate various non-linear systems.The most popular ANN architecture is the multiplayer perception that generally trains the input-output relationship using a back propagation of error algorithm.
Genetic algorithm(GA) is a kind of search and optimized algorithm that has been produced from stimulated biologic heredities and long evolutionary processes of creatures.Three elemental operators of the genetic algorithm are selection,crossover,and mutation.GA is capable of global optimum searching and it is a parallel process to population change and provides intrinsic parallelism.
In the first section,Back-Propagation(BP) neural network was used to predict transdermal flux(1ogK_(ow)) and permeation coefficient(logK_p) of the compounds through the human skin.Two ANNs had different output neuron.However,the input neurons were the same,namely molecule weight(Mr),octanol-water partition coefficient (logK_(ow)),hydrogen-bond donor(Hd) and hydrogen-bond acceptor(Ha).For the first model,the correlation coefficient with predicted logJ_(max) and actual logJ_(max) of the testing drugs was 0.997.For the second model,the correlation coefficient between actual logK_p and calculated logK_p and root mean squared error(RMSE) of the testing set were 0.95 and 0.37.It demonstrated that BP neural network was of great help in predicting human skin permeability.
The second section was aimed to establish a model for predicting biopharmaceutics classification system(BCS).Solubility and permeability of the drug decide which BCS class it belongs to.First intrinsic solubility model and absolute bioavailability model were set up.Linear algorithm and ANN were applied and compared for the solubility model and the later was chosen for higher coefficient(R),lower RMSE and lower AIC. For human oral bioavailability model,two ANNs were established.The main difference was that the second had additional eight input parameters chosen by GA,besides the seven input parameters of the first ANN which can be explained theoretically.And the second one was selected for preferable predicting efficiency.In the BCS prediction stage, sixteen durgs were chosen and self-established solubility and bioavailability models were used for prediction.The prediction accuracy of solubility,bioavailability,and BCS class were 93.8%,81.2%and 75.0%,respectively.
In the third section,BP neural network was used for predicting the elimination rate constant of amikacin in neonates.Gradient descent backpropagation neural network (GD-BP-NN),bayesian regularized backpropagation neural network(BR-BP-NN) and genetic backpropagation neural network(G-BP-NN) were established.The data of amikacin serum concentrations and clinical information of 23 neonates were used to train, validate,and test the models,the effects of gestational age(w),postnatal age(d) and body weight(kg) were analyzed.The prediction precision and running efficiency were compared between the three models.Correlation coefficient of experiment calculative data and predicted data with GD-BP-NN,BR-BP-NN and G-BP-NN for the testing set were 0.92,0.91 and 0.98,respectively.Root mean squared error(RMSE) were 0.020, 0.024 and 0.010.Under the same prediction precision,running epochs of GD-BP-NN, BR-BP-NN and G-BP-NN were 2000,219 and 82.G-BP-NN is much better in the prediction of elimination rate constant of amikacin in neonates.It can overcome the weakness of BP-NN,such as the slow training speed and the vulnerability to local area pole smallness.
遗传算法(Genetic Algorithm,GA)以生物进化过程为背景,模拟生物进化的步骤,将繁殖、杂交、变异、竞争和选择等概念引入到算法中,通过维持一组可行解,并对可行解进行重新组合,改进可行解在多维空间内的移动轨迹或趋向,最终走向最优解。它克服了传统优化方法容易陷入局部极值的缺点,是一种全局优化算法。
本文第一部分将神经网络应用到药物透过人皮肤的渗透性能预测研究中。采集两组数据样本,用Matlab自编程序分别建立了预测药物经皮渗透速率BP网络和预测经皮渗透系数的BP网络模型。两个模型的输入变量相同,为药物的分子量(Mr),油水分配系数(logK_(ow)),供氢数(Hd)和受氢数(Ha)。输出变量分别为药物经皮渗透速率(logJ_(max))和经皮渗透系数(logKp)。前者模型测试组预测logJ_(max)与实际logJ_(max)的相关系数平方为0.997,回归直线的斜率为0.970。后者模型测试组预测得到的logKp与实际logKp的相关系数为0.95,均方误差平方根(RMSE)为0.37。本研究表明BP神经能够很好地预测药物透过皮肤的渗透性能。
第二部分旨在建立一个生物药剂学分类系统(BCS)预测模型。药物在BCS中的分类取决于其溶解性和渗透性。故首先建立药物特征溶解度模型和绝对生物利用度模型。用多元线性回归和神经网络建立溶解度的线性模型和非线性模型,通过模型预测值与实际值的相关系数(R)、均方误差平方根(RMSE)和AIC比较,神经网络模型比逐步线性回归模型优越。用神经网络建立两种预测药物口服绝对生物利用度的模型。前者的输入变量为7个已能明确解释的理论参数,后者的输入变量有15个,包括上述变量和用遗传算法筛选出来的8个变量。通过比较,后者的预测效能优越。采集16个BCS分类明确的药物样本,用自行建立的溶解度模型和生物利用度模型预测分类,溶解度预测准确度为93.8%,渗透性预测准确度为81.2%,生物药剂学分类系统预测准确度为75.0%。
第三部分将神经网络应用到药动学参数的预测,用BP网络预测新生儿丁胺卡那霉素消除速率常数。建立梯度下降BP网络(GD-BP-NN),贝叶斯标准化BP网络(BR-BP-NN)和遗传BP网络(G-BP-NN),以23例新生儿静脉滴注丁胺卡那霉素相关临床资料为研究对象,研究新生儿胎龄、日龄和体重对丁胺卡那霉素消除速率的影响,预测患者的消除速率常数,并比较三种网络的预测精度和运行效率。结果表明GD-BP-NN,BR-BP-NN和G-BP-NN测试组预测值和实验计算值的相关系数分别为0.92,0.91和0.98;测试组均方误差平方根(RMSE)分别是0.020,0.024和0.010;相同的预测精度条件下,GD-BP-NN,BR-BP-NN和G-BP-NN分别运行了2000,219和82步。从中可以看出遗传算法对BP神经网络权值和阈值进行优化,从而克服了BP神经网络训练速度慢,容易陷入局域极小和全局搜索能力弱等缺点,故G-BP-NN预测效果更好。
Artificial neural network(ANN) is a type of mathematical model that simulates the biological nervous system and draws on analogues of adaptive biological learning.It is known to be a powerful tool to simulate various non-linear systems.The most popular ANN architecture is the multiplayer perception that generally trains the input-output relationship using a back propagation of error algorithm.
Genetic algorithm(GA) is a kind of search and optimized algorithm that has been produced from stimulated biologic heredities and long evolutionary processes of creatures.Three elemental operators of the genetic algorithm are selection,crossover,and mutation.GA is capable of global optimum searching and it is a parallel process to population change and provides intrinsic parallelism.
In the first section,Back-Propagation(BP) neural network was used to predict transdermal flux(1ogK_(ow)) and permeation coefficient(logK_p) of the compounds through the human skin.Two ANNs had different output neuron.However,the input neurons were the same,namely molecule weight(Mr),octanol-water partition coefficient (logK_(ow)),hydrogen-bond donor(Hd) and hydrogen-bond acceptor(Ha).For the first model,the correlation coefficient with predicted logJ_(max) and actual logJ_(max) of the testing drugs was 0.997.For the second model,the correlation coefficient between actual logK_p and calculated logK_p and root mean squared error(RMSE) of the testing set were 0.95 and 0.37.It demonstrated that BP neural network was of great help in predicting human skin permeability.
The second section was aimed to establish a model for predicting biopharmaceutics classification system(BCS).Solubility and permeability of the drug decide which BCS class it belongs to.First intrinsic solubility model and absolute bioavailability model were set up.Linear algorithm and ANN were applied and compared for the solubility model and the later was chosen for higher coefficient(R),lower RMSE and lower AIC. For human oral bioavailability model,two ANNs were established.The main difference was that the second had additional eight input parameters chosen by GA,besides the seven input parameters of the first ANN which can be explained theoretically.And the second one was selected for preferable predicting efficiency.In the BCS prediction stage, sixteen durgs were chosen and self-established solubility and bioavailability models were used for prediction.The prediction accuracy of solubility,bioavailability,and BCS class were 93.8%,81.2%and 75.0%,respectively.
In the third section,BP neural network was used for predicting the elimination rate constant of amikacin in neonates.Gradient descent backpropagation neural network (GD-BP-NN),bayesian regularized backpropagation neural network(BR-BP-NN) and genetic backpropagation neural network(G-BP-NN) were established.The data of amikacin serum concentrations and clinical information of 23 neonates were used to train, validate,and test the models,the effects of gestational age(w),postnatal age(d) and body weight(kg) were analyzed.The prediction precision and running efficiency were compared between the three models.Correlation coefficient of experiment calculative data and predicted data with GD-BP-NN,BR-BP-NN and G-BP-NN for the testing set were 0.92,0.91 and 0.98,respectively.Root mean squared error(RMSE) were 0.020, 0.024 and 0.010.Under the same prediction precision,running epochs of GD-BP-NN, BR-BP-NN and G-BP-NN were 2000,219 and 82.G-BP-NN is much better in the prediction of elimination rate constant of amikacin in neonates.It can overcome the weakness of BP-NN,such as the slow training speed and the vulnerability to local area pole smallness.
引文
[1]闻新,周露,王丹力,等.Matlab神经网络应用设计[M].北京:科学出版社,2000.207.
[2]魏晓红,吴建军,梁文权.神经网络用于口服缓释制剂的处方设计[J].药学学报,2001,36(9):690-694.
[3]Yuksel N,Turkoglu M,Baykara T.Modelling of the solvent evaporation mothod for the preparation of controlled release acrylic microspheres using neural networks[J].J Micro encapsul,2000,17(5):541.
[4]李新城,王泽,朱伟兴,等.基于人工神经网络与遗传算法的硫酸沙丁胺醇渗透泵控释片剂释药行为预测研究[J].中国药学杂志,2006,41(2):115-118.
[5]Husseini G A,Abdel-Jabbar N M,Mjalli F S,et al.Modeling and sensitivity analysis of acoustic release of doxorubicin from unstabilized pluronic Pl05 using an artificial neural network model[J].Technol Cancer Res Treat,2007,6(1):49-56.
[6]Turkoglu M,Varol H,Celikok M.Tableting and stability evaluation of enteric-coated omeprazole pellets[J].Eur JPharm Biopharm,2004,57(2):279-286.
[7]杨铭,汪文娟.BP神经网络结合遗传算法用于丹参提取工艺的多目标优化[J].药学报务与研究,2007,7(6):417-421.
[8]Shigeo Yamamura.Clinical application of artificial neural network(ANN) modeling to predict pharmacokinetic parameters of severely ill patients[J].Adv Drug Deliv Rev,2003,55(9):1233-1251.
[9]李凌冰,张娜.人工神经网络结合药动学模型设计氯氮平非pH依赖型缓释片[J],中国药学杂志,2005,40(17):1323-1326.
[10]王泽,李新城,朱伟兴.药物生物利用度遗传神经网络预测研究[J].药学学报,2006,41(12):1180-1183.
[11]傅旭春.用神经网络法预测药物在体透过人皮肤的渗透性[J].浙江大学学报(医学版),2003,32(2):152-154,158.
[12]Shin-ichi Fujiwara,Fumiyoshi Yamashita,Mitsuru Hashida.Prediction of Caco-2 cell permeability using a combination of MO-calculation and neural network[J],lnt J Pharm,2002,237(1-2):95-105.
[13]Armida Di Fenza,Giuliano Alagona,Caterina Ghio,et al.Caco-2 cell permeability modelling:a neural network coupled genetic algorithm approach[J].J Comput Aided Mol Des,2007,21(4):207-221.
[14]Po,tts R.O,Guy R H.Predicting skin permeability[J].Pharma Res,1992,9(5):663-669.
[15]Lien E J,Gao H.QSAR analysis of skin permeability of various in man as compared to in vivo and in vitro studies in rodents[J].Pharm Res,1995,12(4):583-587.
[16]傅旭春,俞庆森,梁文权.一个修正的药物经皮吸收数学模型[J].中国药学杂志,2000,35(4):276-277.
[17]Chen X Q,Cho S J,Li Y,et al.Prediction of aqueous solubility of organic compounds using a quantitative structure-property relationship[J].JPharm Sci,2002,91(8):1838-1852.
[18]Cheng A,Merz K M Jr.Prediction of aqueous solubility of a diverse set of compounds using quantitative structure-property relationships[J],dMed Chem,2003,46(17):3572-3580.
[19]Delaney J S.ESOL:estimating Aqueous Solubility Directly from Molecular Structure[J].J Chem Inf Comput Sci,2004,44(3):1000-1005.
[20]Hou T J,Xia K,Zhang W,et al.ADME evaluation in drug discovery.4.Prediction of aqueous solubility based on atom contribution approach[J].J Chem lnfComput Sci,2004,44(1):266-275.
[21]Palmer D S,O'Boyle N M,Glen R C,et al.Random forest models to predict aqueous solubility[J].JChem InfModel,2007,47(1):150-158.
[22]Huuskonen J,Salo M,Taskinen J.Aqueous solubility prediction of drugs based on molecular topology and neural network modeling[J].JChem lnfComput Sci,1998,38(3):450-456.
[23]Engkvist O,Wrede P.High-throughput,in silico prediction of aqueous solubility based on one-and two-dimensional descriptors[J].J Chem InfComput Sci,2002,42(5):1247-1249.
[24]Hansen N T,Kouskoumvekaki I,Jorgensen F S,et al.Prediction of pH-dependent aqueous solubility of druglike molecules[J].JChem InfModel,2006,46(6):2601-2609.
[25]Wegner J K,Zell A.Prediction of aqueous solubility and partition coefficient optimized by a genetic algorithm based descriptor selection method[J].J Chem InfComput Sci,2003,43(3):1077-1084.
[26]Yan A,Gasteiger J,Krug M,et al.Linear and nonlinear functions on modeling of aqueous solubility of organic compounds by two structure representation methods[J].J Comput-Aided Mol Des,2004,18(2):75-87.
[27]Yan A,Gasteiger J.Prediction of aqueous solubility of organic compounds by topological descriptors[J].QSAR Comb Sci,2003,22(8):821-829.
[28]Yan A,Gasteiger J.Prediction of aqueous solubility of organic compounds based on a 3D structure representation[J].J Chem InfComput Sci,2003,43(2):429-434.
[29]Schwaighofer A,Schroeter T,Mika S,et al.Accurate solubility prediction with error bars for electrolytes:a machine learning approach[J].J Chem InfModel,2007,47(2):407-424.
[30]Klamt A,Eckert F,Hornig M,et al.Prediction of aqueous solubility of drugs and pesticides with COSMO-RS[J].J Comput Chem,2002,23(2):275-281.
[31]Ikeda H,Chiba K,Kanou A,et al.Prediction of solubility of drugs by conductor-like screening model for real solvents[J].Chem Pharm Bull,2005,53(2):253-255.
[1]Todeschini R,V.Consonni.Handbook of molecular descriptors[M].2000,Weinheim:Wiley-VCH.
[2]Allinger N L.J Am.Conformational-analysis.130μm2-hydrocarbon force-field utilizing vi and v2 torsional terms[J].Chem Soc,1977,99(25):8127-8134.
[3]Allinger N L,Rahman M,Li J J,et al.A molecular mechanics force field(MM3) for alcohols and ethers[J].Am Chem Soc,1990,112(23):8293-8307.
[4]Clark M,Cramer Ⅲ R D,Van Opdenbosch N J.Validation of the general purpose Tripos 5.2force field[J].Comput Chem,1989,10(9):982-1012.
[5]Weiner S J,Koilman P A,et al.A new force field for molecular mechanical simulation of nucleic acids and proteins[J].JAm Chem Soc,1984,106:765-784.
[6]Weiner S J,Kollman P A,Nguyen DT,et al.An all atom force-field for simulations of proteins and nucleic acid[J].J Comput Chem,1986,7(2):230-252.
[7]Brooks B R,Bruccoleri R E,Olafson B D,et al.A program for macromolecular energy,minmimization,and dynamics calculations[J].J Comput Chem,1983,4(2):187-217.
[8]Dauber-Osguthorpe P,Roberts V A,et al.Structure and energetics of ligand binding to proteins:E coli dihydrofolate reductase-trimethoprim,a drug-receptor system.《Proteins:Structure,Functionand Genetics》[M],1988,4,31-47.
[9]Van Gunsteren W F,Berendsen H J C.In:Molecular Dynamics and Protein Structure,Hemans J(Eds)[M].Western Springs:Polycrystal books Service,1985,5-14.
[10]林红卫,赵军,毛新平等.应用量化参数研究d4T核苷酸类似物的结构与抗HIV-1活性的相关性[J].计算机与应用化学,2007,24(4):536-538.
[11]蒋柳云,刘玉明.黄酮类化合物抗肿瘤活性的构效关系研究[J].计算机与应用化学,2005,22(4):265-268.
[12]李江波,林瑞森,俞庆森.影响喹诺酮C-4位构效关系的若干因素[J].化学研究与应用,1999,11(3):279-281.
[13]赵军,许旋,罗一帆.具有抗癌活性的喜树碱类化合物的构效关系研究[J].中国药物化学杂志,2003,13(2):83-88.
[1] Scheuplein R J. Mechanism of percutaneous absorption I Routes of penetration and the influence of solubility [J]. J Invest Dermatol, 1965, 45 (5): 334-346.
[2] Scheuplein R J, Blank I H, Brauner G J, et al. Percutaneous absorption of steroids [J]. J Invest Dermatol, 1969, 52 (1): 63-70.
[3] Roberts M S, Anderson R A, Swarbrick J. Permeability of human epidermis to phenolic compounds [J].J Pharm Pharmacol, 1977,29 (11): 677-683.
[4] Potts R O, Guy R H. Predicting skin permeability [J]. Pharm Res, 1992, 9 (7): 663- 669.
[5] El Tayar N, Tsai R, Testa B, et al. Percutaneous penetration of drugs:a quantitative structure permeability relationship study [J]. J Pharm Sci, 1991, 80(8): 744-749.
[6] Pugh W J, Hadgraft J. Ab inito prediction of human skin permeability coefficients [J]. Int J Pharm, 1994, 103 (2): 163-178.
[7] Lien E J, Gao H. QSAR analysis of skin permeability of various drugs in man as compared to in vivo and in vitro studies in rodents [J]. Pharm Res, 1995, 12 (4): 583-587.
[8] Lim C W, Fujiwara S, Yamashita F, et al. Prediction of human skin permeability using a combination of molecular orbital calculations and artificial neural network [J]. Biol Pharm Bull, 2002, 25 (3): 361-366.
[9] Magnusson B M, Anissimov Y G, Cross S E, et al. Molecular size as the main determinant of solute maximum flux across the skin [J]. J Invest Dermatol, 2004, 122 (4): 993-999.
[10] Roberts M S, Anderson R A, Swarbrick J. Permeability of human epidermis to phenolic compounds:the effect of vehicles on the penetration of phenol [J]. J Pharm Pharmacol, 1975,27 (8): 599-605.
[11] Roberts M, Anderson R, Swarbrick J. Permeability of human epidermis to phenolic compounds [J]. J Pharm Pharmacol, 1977, 29 (11): 677-683.
[12] Blank I, Scheuplein R, Macfarlane D. Mechanism of percutaneous absorption. III. The effect of temperature on the transport of non-electrolytes across the skin [J]. J Invest Dermatol, 1967,49 (6): 582-589.
[13] Scheuplein R, Blank I, Brauner G, et al. Percutaneous absorption of steroids [J]. J Invest Dermatol, 1969, 52 (1): 63-70.
[14] Peck K, Ghanem A, Higuchi W. The effect of temperature upon the permeation of polar and ionic solutes through human epidermal membranes [J]. J Pharm Sci, 1995, 84 (8):975-982.
[15] Scheuplein R, Blank I. Mechanism of percutaneous absorption. IV. Penetration of nonelectrol-ytes (alcohols) from aqueous solutions and from pure liquids [J]. J Invest, Dermatol, 1973, 60(5):286-296.
[16] Dalpozzo A, Donzelli G, Liggeri E, et al. Percutaneous absorption of nicotinic acid deriv-atives in vitro[J].JPharm Sci,1991,80(1):54-57.
[17]Singh P,Roberts M.Skin permeability and local tissue concentrations of nonsteroidal antiinflammatory drugs after topical application[J].J Pharmacol Exp Ther,1994,268(1):44-151.
[18]Bronaugh R,Congdon E.Percutaneous absorption of hair dyes:Correlation with partition coefficients[J].J Invest Dermatol,1984,83(2):124-127.
[19]Barber E,Teetsel N,Kolberg K,et ai.A comparative study of the rates of in vitro percutaneous absorption of eight chemicals using rat and human skin[J].Fundam Appl Toxicol,1992,19(4):493-497.
[20]Flynn G L.Physicochemical determinants of skin absorption.In:Gerrity T R,Henry,C J (Eds.),Principles of route-to-route exptrapolation for risk assessment[M].Elsevier,New York,1990,pp.93-127.
[21]梁文权.药物在皮肤内的扩散,经皮给药制剂[M].北京:中国医药出版社,1992,37-39.
[22]Tayer NE,Tasi RS,Testa B,et al.Percutaneous penetration of drugs:a quantitative structure-permeability relationship study[J].J Pharm Sci,1991,80(8):744-749.
[23]Wilschut A,Ten Berge W F,Robinson P J,et al.Estimating skin permeation.The validation of five mathematical models[J].Chemosphere,1995,30(7):1275-1296.
[24]Abraham M H,Martins F,Mitchell R C.Algorithms for skin permeability using hydrogen bond descriptors:the problem of steroids[J].JPharm Pharmacol,1997,49(9):858-865.
[1]Oleszek-Kudlak S,Grabda M,Shibata E,et al.Application of the conductor-like screening model for real solvents for prediction of the aqueous solubility of chlorobenzenes depending on temperature and salinity[J].Environ Toxicol Chem,2005,24(6):1368-1375.
[2]C Hansch,J E Quinlan,G L Lawrence.Linear free-energy relationship between partition coefficients and the aqueous solubility of organic liquids[J].J Org Chem,1968,33(1):347-350.
[3]P Isnard,S Lambert.Aqueous solubility and n-oetanol/water partition coefficient correlations[J].Chemosphere,1989,18(9-10),1837-1853.
[4]P Ertl,B Rohde,P Selzer.Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties[J].J Med Chem,2000,43(20):3714-3717.
[5]M H Abraham,J Le.The correlation and prediction of the solubility of compounds in water using an amended solvation energy relationship[J].JPharm.Sci,1999,88(9):868-880.
[6]Hongzhou Zhang,Howard Y Ando,Linna Chen,et al.On-the-Fly Selection of a Training Set for Aqueous Solubility Prediction[J].Molpharm,2007,4(4):489-497.
[7]A Avdeef,C M Berger,C Brownell,pH-metric solubility 2:correlation between the acid-base titration and the saturation shake-flask solubility-pH methods[J].Pharm Res,2000,17(10):85-89.
[8]A Avdeef.Absorption and Drug Development,Wiley-Intersience,New York,2003.
[9]A Kristl,S Pecar.Hydrolipophilic anomalies of some guanine derivatives[J].Eur J Med Chem.1997,32:3-8.
[10]B Failer,H-P Grimm,F Loeuillet-Ritzler,et al.Highthroughput lipophilicity measurement with immobilized artificial membranes[J].JMed Chem,2005,48(7):2571-2576.
[11]B Failer,F Wohnsland.Physicochemicai parameters as tools in drug discovery and lead optimization.Editor(s):B.Testa.Pharmacokinetic Optimization in Drug Research:Biological,Physicochemical,andComputational Strategies,[LogP2000,Lipophilicity Symposium],2nd,Lausanne,Switzerland,Mar.5-9,2000(2001),MeetingDate 2000,257-273.Publisher:Verlag Helvetica Chimica Acta,Zurich,Switzerland.
[12]Bergstroem C A,Stratford M,Lazorova,et al.Absorption classification of oral drugs based on molecular surface properties[J].JMed Chem,2003,46(4):558-570.
[13]A Avdeef,C M Berger,pH-metric solubility:3.Dissolution titration template method for solubility determination[J].Eur JPharm Sci,2001,14(4):281-291.
[14]A Avdeef,Physicochemical profiling(solubility,permeability and charge state),Current Topics in Medicinal Chemistry 1(2001) 277-351(Hilversum,Netherlands).
[15]G Caron,G Steyaert,A Pagliara,et al.Structure lipophilicity relationships of neutral and protonated b-blockers.Part 1.Intraand intermolecular effects in isotropic solvent systems[J].Helv Chim Acta,1999,82(8):1211-1222.
[16]B Slater,A McCormack,A Avdeef,et al.pH-Metric log P.4.Comparison of partition coefficients determined by HPLC and potentiometric methods to literature values[J].J Pharm Sci,1994,83(9):1280-1283.
[17]M Kansy,H Fischer,K Kratzat,et al.High-throughput artificial membrane permeability studies in early lead discovery and development.I.Parrilla.Editor(s):B.Testa.Pharmacokinetic Optimization in Drug Research:Biological,Physicochemical,and Computational-Strategies,[LogP2000,Lipophilicity Symposium],2nd,Lausanne,Switzerland,Mar.5-9,2000(2001),Meeting Date 2000,447-464.Publisher:Verlag Helvetica Chimica Acta,Zurich,Switzerland.
[18]S Winiwarter,N M Bonham,F Ax,et al.Correlation of human jejunal permeability(in vivo) of drugs with experimentally and theoretically derived parameters,a multivariate data analysis approach.J Med Chem,1998,41(25):4939-4949.
[19]N Jain,S H Yalkowsky.Estimation of the aqueous solubility I:application to organic nonelectrolytes[J].JPharm Sci,2001,90(6):234-252.
[20]F Lombardo,M.Y Shalaeva,K A Tupper,et al.ElogPoct:a tool for lipophilicity determination in drug discovery[J].JMed Chem,2000,43(15):2922-2928.
[21]M Ponec,J Kempenaar,B Shroot,et al.Glucocorticoids:binding affinity and lipophilicity[J].J Pharm Sci,1986,75(10):973-975.
[22]T S Wiedmann,W Liang,L Kamel.Solubilization of drugs by physiological mixtures of bile salts[J].Pharm Res,2002,19(8):1203-1208.
[23]A Glomme,J Maerz,J B Dressman.Comparison of a miniaturized shake-flask solubility method with automated potentiometric acid/base titrations and calculated solubilities[J].J Pharm Sci,2005,94(7):1-16.
[24]Takayama K,Takahara J,Fujikawa M,et al.Formula optimization based on artificial neural networks in transdermal drug delivery.[J].JControl Release,1999,62(1-2):161-170.
[1]Clark DE.Rapid calculation of polar molecular surface area and its application to the prediction of transport phenomena.I.Prediction of intestinal absorption[J].J Pharm Sci,1999,88(8):807-814.
[2]Palm K,Stenberg P,Luthman K,Artursson P.Polar molecular surface properties predict and the intestinal absorption of drugs in humans[J].Pharm Res,1997,14(5):568-571.
[3]Palm K,Luthman K,Ungell AL,et al.Correlation of drug absorption with molecular surface properties[J].JPharm Sci,1996,85(1):32-39.
[4]Physicians' Desk Reference(PDR),59th ed.;Thomson,2005.
[5]Hardman J G,Limbird,L.E.;Gilman,A.G..Pharmacokinetic Data,10th ed.In Goodman s The Pharmacological Basis of Therapeutics;McGraw-Hill:United States of America,2001,p.1924.
[6]Sietsema W K.The absolute oral bioavailability of selected drugs[J].Int J Clin Pharmacol Ther Toxicol,1989,27(4):179-211.
[7]Ren S,Das A,Lien EJ.QSAR analysis of membrane permeability to organic compounds[J].J Drug Target,1996,4(2):103-107.
[8]Hamilton H W,Steinbaugh B A,Stewart B H,et al.Evaluation of physicochemical parameters important to the oral bioavailability of peptide-like compounds:implications for the synthesis of renin inhibitors[J].JMed Chem,1995,38(9):1446-1455.
[9]Roth B D,Bocan T M A,Blankley C J,et al.Relationship between tissue selectivityand lipophilicity for inhibitors of HMG-CoA reductase[J].JMed Chem,1991,34(I):463-466.
[10]Walter A,Gutknecht J.Permeability of small nonelectrolytes through lipid bilayer membranes[J].JMembr Biol,1986,90(3):207-217.
[11]Palm K,Luthman K,Ungeli A L,et al.Correlation of drug absorption with molecular surface properties[J].JPharm Sci,1996,85(1):32-39.
[1]Marc Lindenberg,Sabine Kopp,Jennifer B.Dressman.classification of orally administered drugs on the world health organization model list of essential medicines according to the biopharmaceutics classification system[J].Eur JPharm Biopharm,2004,58(2):265-278.
[2]Akash Khandelwal,Praveen M.Bahadduri,Cheng Chang,et al.Computational Models to Assign Biopharmaceutics Drug Disposition Classification from Molecular Structure[J].Pharm Res,2007,24(12):2249-2262.
[3]Essential Medicines WHO Model List(revised March 2005)
[4]Chi Yuan Wu,Leslie Z.Benet.Predicting drug disposition via application of BCS:transport/absorption/elimination interplay and development of a biopharmaceutics drug disposi-tion classification system[J].Pharm Res,2005,22(1):11-23.
[5]World health organization organisation mondiale de la sante.Proposal to waive in vivo bioequivalence requirements for the WHO model list of essential medicines immediate release,solid oral dosage forms.Working Document QAS/04.109/Rev.1:
[1]王珏.Monte Carlo法在群体药动学研究中的应用[D].杭州:浙江大学药学院,1996-1998.
[2]Yang S,Bumgamer J G,Kruk L F,et al.Quantitative structure-activity relationships studies with micellar electrokinetic chromatography.Influence of surfacant type and mixed micelles on estimation of hydrophobicity and bioavailability[J].J Chromatogr A,1996,721(2):323-335.
[1]:闻新,周露,王丹力,等.Matlab神经网络应用设计[M].北京:科学出版社,2000.207
[2]:何勤,吴芳,蒋学华,等.药物动力学数据的神经网络处理方法[J].华西药学杂志,2002,17(2):123-125.
[3]:P C Wu,Y Obata,M Fujikawa,et al.Simultaneous optimization based on artificial neural networks in ketoprofen hydrogei formula containing O-enthy-3-butylcyciohexanol as percutaneous aborption enhancer[J].JPharm Sci,2001,90(7):1004-1014.
[4]:A P Plumb,R C Rowe,P York,et al.The effect of experimental design on the modeling of a tablet coating formulation using artifcial neural networks[J].Eur d Pharm Sci,2002,16(3):281-288.
[5]:Onuki Y,Hoshi M,Okabe H,et al.Formulation optimization of photocresslinked polyacrylic acid modified with 2-hydroxyethyl methacrylate hydrogel as an adhesive for a dermatological patch[J].J control release,2005,108(2-3):331-340.
[6]:Fan T,Takayama K,Hattori Y,et al.Formulation optimization of paclitaxel carried by PEGylated emulsions based on artificial nneural network[J].Pham Res,2004,21(9):1692-1697.
[7]:Lira CP,Quek SS,Peh KK.Prediction or drug release profiles using an intelligent learning system:an eperiment study in transdermal iontophoresis[J].J Pharm BiomedAnal,2003,31(1):159-168.
[8]:Plumb AP,Rowe RC,York P,et al.Effect of varying optimization parameters on optimization by guided evolutionary simulated annealing(GESA) using a tablet film coat as all example formulation[J].Eur J Pharm Sci,2003,18(3-4):259-266.
[9]:魏晓红,吴建军,梁文权.神经网络用于口服缓释制剂的处方设计[J].药学学报,2001,36(9):690-694.
[10]:Arulsudar N,Subramanian N,Muthy RS.Comparison of artificial neural network and multiple linear regression in the optimization of formulation parameters of leuprolide acetate loaded iiposomes[J].J Pharm Pharm Sci,2005,8(2):243-258.
[11]:Husseini GA,Abdel-Jabbar NM,Mjalli FS,et al.Modeling and sensitivity analysis of acoustic release of Doxorubicin from unstabilized pluronic P105 using an artificial neural network model [J].Technol Cancer Res Treat,2007,6(1):49-56.
[12]:Turkoglu M,Varol H,Celikok M.Tableting and stability evaluation of enteric-coated omeprazole pellets[J].Eur JPharm Biopharm,2004,57(2):279-286.
[13]:Shigeo Yamamura.Clinical application of artificial neural network(ANN) modeling to predict pharmacokinetic parameters of severely ill patients[J].Adv Drug Deliv Rev,2003,55(9):1233-1251.
[14]:李凌冰,张娜.人工神经网络结合药动学模型设计氯氮平非pH依赖型缓释片[J].中国药学杂志,2005,40(17):1321-1326.
[15]:傅旭春.用神经网络法预测药物在体透过人皮肤的渗透性[J].浙江大学学报(医学版),2003,32(2):152-154.
[16]:Shin-ichi Fujiwara,Fumiyoshi Yamashita,Mitsuru Hashida.Prediction of Caco-2 cell permeability using a combination of MO-calculation and neural network[J].Int J Pharm,2002,237(1-2,26):95-105.
[17]:Davis L FA.Handbook of genetic algorithm New York.NY:Van Ncem md Reinhold,1991
[18]:Forest S.Genetic algorithms:Principles of natural selection applied to computation[J].Science.1993.261(5123):872-878.
[19]:李进文,陈朝辉,曾平,等.基于遗传算法的药物动力学参数估计[J].数理医药学杂志,2006,19(5):529-530.
[20]:蔡煜东.遗传算法求算药物动力学参数的研究[J].中国药理学通报,1995,11(3):254-256.
[21]:Hanseh C,FujitaTl.p-σ-π Analysisl a method for the correlation of biological activity and chemical structure[J].Am Chem Soc,1964,86(8):16161.
[22]:Brick T,Schwefel H P.An overview of evolutionary algorithms for parameter optimization.Evol Comput,1993,1(1):1-23.
[23]:Agatonovic-Kustrin S,Beresford R,YusofAPM.Theoretically-derived descriptors important in human intestinal absorption[J].JPharm BiomedAnal,2001,25(2):227-237.
[24]:So SS,Karplus M.Evolutionary optimization in quantitative structure-activity relationship:an application of genetic neural networks[J].JMed Chem,1996,39(7):1521-1530.
[25]:So SS,Karplus M.Genetic neural networks for quantitative structure-activity relationships:improvements and application of benzodiazepine affinity for benzodiazepine/GABAA receptors[J].JMed Chem,1996,39(26):5246-5256.
[26]:Yasri A,Hartsough D.Toward an optimal procedure for variable selection and QSAR model building[J].JChem lnfComputSci,2001,41(5):1218-1227.
[27]:Guha R,Jurs P C.Development of QSAR models to predict and interpret the biological activity of artemisinin analogues[J].J Chem InfComput Sci,2004,44(4):1440-1449.
[28]:Armida Di Fenza,Giuliano Alagona,Caterina Ghio et ai.Caco-2 cell permeability modelling:a neural network coupled genetic algorithm approach[J].J Comput Aided Mol Des,2007,21(4):207-221.
[29]:李新城,王泽,朱伟兴,等.基于人工神经网络与遗传算法的硫酸沙丁胺醇渗透泵控释片剂释药行为预测研究[J].中国药学杂志,41(2):115-118.
[30]:杨铭,汪文娟.BP神经网络结合遗传算法用于丹参提取工艺的多目标优化[J].药学服务与 研究,2007,7(6):417-421.
[31]:刘红梅,李可意.基于BP神经网络和遗传算法优化莪术超临界萃取工艺[J].中国药学杂志,2006,41(5):371-374.
[32]:张宇飞,邵秀丽,雷建军.基于神经网络和遗传算法的中药滴丸制剂过程建模与优化[J].计算机工程与应用,2005,2(2):191-194.
[33]:王泽,李新城,朱伟兴.药物生物利用度遗传神经网络预测研究[J].药学学报,2006,41(12):1180-1183
[2]魏晓红,吴建军,梁文权.神经网络用于口服缓释制剂的处方设计[J].药学学报,2001,36(9):690-694.
[3]Yuksel N,Turkoglu M,Baykara T.Modelling of the solvent evaporation mothod for the preparation of controlled release acrylic microspheres using neural networks[J].J Micro encapsul,2000,17(5):541.
[4]李新城,王泽,朱伟兴,等.基于人工神经网络与遗传算法的硫酸沙丁胺醇渗透泵控释片剂释药行为预测研究[J].中国药学杂志,2006,41(2):115-118.
[5]Husseini G A,Abdel-Jabbar N M,Mjalli F S,et al.Modeling and sensitivity analysis of acoustic release of doxorubicin from unstabilized pluronic Pl05 using an artificial neural network model[J].Technol Cancer Res Treat,2007,6(1):49-56.
[6]Turkoglu M,Varol H,Celikok M.Tableting and stability evaluation of enteric-coated omeprazole pellets[J].Eur JPharm Biopharm,2004,57(2):279-286.
[7]杨铭,汪文娟.BP神经网络结合遗传算法用于丹参提取工艺的多目标优化[J].药学报务与研究,2007,7(6):417-421.
[8]Shigeo Yamamura.Clinical application of artificial neural network(ANN) modeling to predict pharmacokinetic parameters of severely ill patients[J].Adv Drug Deliv Rev,2003,55(9):1233-1251.
[9]李凌冰,张娜.人工神经网络结合药动学模型设计氯氮平非pH依赖型缓释片[J],中国药学杂志,2005,40(17):1323-1326.
[10]王泽,李新城,朱伟兴.药物生物利用度遗传神经网络预测研究[J].药学学报,2006,41(12):1180-1183.
[11]傅旭春.用神经网络法预测药物在体透过人皮肤的渗透性[J].浙江大学学报(医学版),2003,32(2):152-154,158.
[12]Shin-ichi Fujiwara,Fumiyoshi Yamashita,Mitsuru Hashida.Prediction of Caco-2 cell permeability using a combination of MO-calculation and neural network[J],lnt J Pharm,2002,237(1-2):95-105.
[13]Armida Di Fenza,Giuliano Alagona,Caterina Ghio,et al.Caco-2 cell permeability modelling:a neural network coupled genetic algorithm approach[J].J Comput Aided Mol Des,2007,21(4):207-221.
[14]Po,tts R.O,Guy R H.Predicting skin permeability[J].Pharma Res,1992,9(5):663-669.
[15]Lien E J,Gao H.QSAR analysis of skin permeability of various in man as compared to in vivo and in vitro studies in rodents[J].Pharm Res,1995,12(4):583-587.
[16]傅旭春,俞庆森,梁文权.一个修正的药物经皮吸收数学模型[J].中国药学杂志,2000,35(4):276-277.
[17]Chen X Q,Cho S J,Li Y,et al.Prediction of aqueous solubility of organic compounds using a quantitative structure-property relationship[J].JPharm Sci,2002,91(8):1838-1852.
[18]Cheng A,Merz K M Jr.Prediction of aqueous solubility of a diverse set of compounds using quantitative structure-property relationships[J],dMed Chem,2003,46(17):3572-3580.
[19]Delaney J S.ESOL:estimating Aqueous Solubility Directly from Molecular Structure[J].J Chem Inf Comput Sci,2004,44(3):1000-1005.
[20]Hou T J,Xia K,Zhang W,et al.ADME evaluation in drug discovery.4.Prediction of aqueous solubility based on atom contribution approach[J].J Chem lnfComput Sci,2004,44(1):266-275.
[21]Palmer D S,O'Boyle N M,Glen R C,et al.Random forest models to predict aqueous solubility[J].JChem InfModel,2007,47(1):150-158.
[22]Huuskonen J,Salo M,Taskinen J.Aqueous solubility prediction of drugs based on molecular topology and neural network modeling[J].JChem lnfComput Sci,1998,38(3):450-456.
[23]Engkvist O,Wrede P.High-throughput,in silico prediction of aqueous solubility based on one-and two-dimensional descriptors[J].J Chem InfComput Sci,2002,42(5):1247-1249.
[24]Hansen N T,Kouskoumvekaki I,Jorgensen F S,et al.Prediction of pH-dependent aqueous solubility of druglike molecules[J].JChem InfModel,2006,46(6):2601-2609.
[25]Wegner J K,Zell A.Prediction of aqueous solubility and partition coefficient optimized by a genetic algorithm based descriptor selection method[J].J Chem InfComput Sci,2003,43(3):1077-1084.
[26]Yan A,Gasteiger J,Krug M,et al.Linear and nonlinear functions on modeling of aqueous solubility of organic compounds by two structure representation methods[J].J Comput-Aided Mol Des,2004,18(2):75-87.
[27]Yan A,Gasteiger J.Prediction of aqueous solubility of organic compounds by topological descriptors[J].QSAR Comb Sci,2003,22(8):821-829.
[28]Yan A,Gasteiger J.Prediction of aqueous solubility of organic compounds based on a 3D structure representation[J].J Chem InfComput Sci,2003,43(2):429-434.
[29]Schwaighofer A,Schroeter T,Mika S,et al.Accurate solubility prediction with error bars for electrolytes:a machine learning approach[J].J Chem InfModel,2007,47(2):407-424.
[30]Klamt A,Eckert F,Hornig M,et al.Prediction of aqueous solubility of drugs and pesticides with COSMO-RS[J].J Comput Chem,2002,23(2):275-281.
[31]Ikeda H,Chiba K,Kanou A,et al.Prediction of solubility of drugs by conductor-like screening model for real solvents[J].Chem Pharm Bull,2005,53(2):253-255.
[1]Todeschini R,V.Consonni.Handbook of molecular descriptors[M].2000,Weinheim:Wiley-VCH.
[2]Allinger N L.J Am.Conformational-analysis.130μm2-hydrocarbon force-field utilizing vi and v2 torsional terms[J].Chem Soc,1977,99(25):8127-8134.
[3]Allinger N L,Rahman M,Li J J,et al.A molecular mechanics force field(MM3) for alcohols and ethers[J].Am Chem Soc,1990,112(23):8293-8307.
[4]Clark M,Cramer Ⅲ R D,Van Opdenbosch N J.Validation of the general purpose Tripos 5.2force field[J].Comput Chem,1989,10(9):982-1012.
[5]Weiner S J,Koilman P A,et al.A new force field for molecular mechanical simulation of nucleic acids and proteins[J].JAm Chem Soc,1984,106:765-784.
[6]Weiner S J,Kollman P A,Nguyen DT,et al.An all atom force-field for simulations of proteins and nucleic acid[J].J Comput Chem,1986,7(2):230-252.
[7]Brooks B R,Bruccoleri R E,Olafson B D,et al.A program for macromolecular energy,minmimization,and dynamics calculations[J].J Comput Chem,1983,4(2):187-217.
[8]Dauber-Osguthorpe P,Roberts V A,et al.Structure and energetics of ligand binding to proteins:E coli dihydrofolate reductase-trimethoprim,a drug-receptor system.《Proteins:Structure,Functionand Genetics》[M],1988,4,31-47.
[9]Van Gunsteren W F,Berendsen H J C.In:Molecular Dynamics and Protein Structure,Hemans J(Eds)[M].Western Springs:Polycrystal books Service,1985,5-14.
[10]林红卫,赵军,毛新平等.应用量化参数研究d4T核苷酸类似物的结构与抗HIV-1活性的相关性[J].计算机与应用化学,2007,24(4):536-538.
[11]蒋柳云,刘玉明.黄酮类化合物抗肿瘤活性的构效关系研究[J].计算机与应用化学,2005,22(4):265-268.
[12]李江波,林瑞森,俞庆森.影响喹诺酮C-4位构效关系的若干因素[J].化学研究与应用,1999,11(3):279-281.
[13]赵军,许旋,罗一帆.具有抗癌活性的喜树碱类化合物的构效关系研究[J].中国药物化学杂志,2003,13(2):83-88.
[1] Scheuplein R J. Mechanism of percutaneous absorption I Routes of penetration and the influence of solubility [J]. J Invest Dermatol, 1965, 45 (5): 334-346.
[2] Scheuplein R J, Blank I H, Brauner G J, et al. Percutaneous absorption of steroids [J]. J Invest Dermatol, 1969, 52 (1): 63-70.
[3] Roberts M S, Anderson R A, Swarbrick J. Permeability of human epidermis to phenolic compounds [J].J Pharm Pharmacol, 1977,29 (11): 677-683.
[4] Potts R O, Guy R H. Predicting skin permeability [J]. Pharm Res, 1992, 9 (7): 663- 669.
[5] El Tayar N, Tsai R, Testa B, et al. Percutaneous penetration of drugs:a quantitative structure permeability relationship study [J]. J Pharm Sci, 1991, 80(8): 744-749.
[6] Pugh W J, Hadgraft J. Ab inito prediction of human skin permeability coefficients [J]. Int J Pharm, 1994, 103 (2): 163-178.
[7] Lien E J, Gao H. QSAR analysis of skin permeability of various drugs in man as compared to in vivo and in vitro studies in rodents [J]. Pharm Res, 1995, 12 (4): 583-587.
[8] Lim C W, Fujiwara S, Yamashita F, et al. Prediction of human skin permeability using a combination of molecular orbital calculations and artificial neural network [J]. Biol Pharm Bull, 2002, 25 (3): 361-366.
[9] Magnusson B M, Anissimov Y G, Cross S E, et al. Molecular size as the main determinant of solute maximum flux across the skin [J]. J Invest Dermatol, 2004, 122 (4): 993-999.
[10] Roberts M S, Anderson R A, Swarbrick J. Permeability of human epidermis to phenolic compounds:the effect of vehicles on the penetration of phenol [J]. J Pharm Pharmacol, 1975,27 (8): 599-605.
[11] Roberts M, Anderson R, Swarbrick J. Permeability of human epidermis to phenolic compounds [J]. J Pharm Pharmacol, 1977, 29 (11): 677-683.
[12] Blank I, Scheuplein R, Macfarlane D. Mechanism of percutaneous absorption. III. The effect of temperature on the transport of non-electrolytes across the skin [J]. J Invest Dermatol, 1967,49 (6): 582-589.
[13] Scheuplein R, Blank I, Brauner G, et al. Percutaneous absorption of steroids [J]. J Invest Dermatol, 1969, 52 (1): 63-70.
[14] Peck K, Ghanem A, Higuchi W. The effect of temperature upon the permeation of polar and ionic solutes through human epidermal membranes [J]. J Pharm Sci, 1995, 84 (8):975-982.
[15] Scheuplein R, Blank I. Mechanism of percutaneous absorption. IV. Penetration of nonelectrol-ytes (alcohols) from aqueous solutions and from pure liquids [J]. J Invest, Dermatol, 1973, 60(5):286-296.
[16] Dalpozzo A, Donzelli G, Liggeri E, et al. Percutaneous absorption of nicotinic acid deriv-atives in vitro[J].JPharm Sci,1991,80(1):54-57.
[17]Singh P,Roberts M.Skin permeability and local tissue concentrations of nonsteroidal antiinflammatory drugs after topical application[J].J Pharmacol Exp Ther,1994,268(1):44-151.
[18]Bronaugh R,Congdon E.Percutaneous absorption of hair dyes:Correlation with partition coefficients[J].J Invest Dermatol,1984,83(2):124-127.
[19]Barber E,Teetsel N,Kolberg K,et ai.A comparative study of the rates of in vitro percutaneous absorption of eight chemicals using rat and human skin[J].Fundam Appl Toxicol,1992,19(4):493-497.
[20]Flynn G L.Physicochemical determinants of skin absorption.In:Gerrity T R,Henry,C J (Eds.),Principles of route-to-route exptrapolation for risk assessment[M].Elsevier,New York,1990,pp.93-127.
[21]梁文权.药物在皮肤内的扩散,经皮给药制剂[M].北京:中国医药出版社,1992,37-39.
[22]Tayer NE,Tasi RS,Testa B,et al.Percutaneous penetration of drugs:a quantitative structure-permeability relationship study[J].J Pharm Sci,1991,80(8):744-749.
[23]Wilschut A,Ten Berge W F,Robinson P J,et al.Estimating skin permeation.The validation of five mathematical models[J].Chemosphere,1995,30(7):1275-1296.
[24]Abraham M H,Martins F,Mitchell R C.Algorithms for skin permeability using hydrogen bond descriptors:the problem of steroids[J].JPharm Pharmacol,1997,49(9):858-865.
[1]Oleszek-Kudlak S,Grabda M,Shibata E,et al.Application of the conductor-like screening model for real solvents for prediction of the aqueous solubility of chlorobenzenes depending on temperature and salinity[J].Environ Toxicol Chem,2005,24(6):1368-1375.
[2]C Hansch,J E Quinlan,G L Lawrence.Linear free-energy relationship between partition coefficients and the aqueous solubility of organic liquids[J].J Org Chem,1968,33(1):347-350.
[3]P Isnard,S Lambert.Aqueous solubility and n-oetanol/water partition coefficient correlations[J].Chemosphere,1989,18(9-10),1837-1853.
[4]P Ertl,B Rohde,P Selzer.Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties[J].J Med Chem,2000,43(20):3714-3717.
[5]M H Abraham,J Le.The correlation and prediction of the solubility of compounds in water using an amended solvation energy relationship[J].JPharm.Sci,1999,88(9):868-880.
[6]Hongzhou Zhang,Howard Y Ando,Linna Chen,et al.On-the-Fly Selection of a Training Set for Aqueous Solubility Prediction[J].Molpharm,2007,4(4):489-497.
[7]A Avdeef,C M Berger,C Brownell,pH-metric solubility 2:correlation between the acid-base titration and the saturation shake-flask solubility-pH methods[J].Pharm Res,2000,17(10):85-89.
[8]A Avdeef.Absorption and Drug Development,Wiley-Intersience,New York,2003.
[9]A Kristl,S Pecar.Hydrolipophilic anomalies of some guanine derivatives[J].Eur J Med Chem.1997,32:3-8.
[10]B Failer,H-P Grimm,F Loeuillet-Ritzler,et al.Highthroughput lipophilicity measurement with immobilized artificial membranes[J].JMed Chem,2005,48(7):2571-2576.
[11]B Failer,F Wohnsland.Physicochemicai parameters as tools in drug discovery and lead optimization.Editor(s):B.Testa.Pharmacokinetic Optimization in Drug Research:Biological,Physicochemical,andComputational Strategies,[LogP2000,Lipophilicity Symposium],2nd,Lausanne,Switzerland,Mar.5-9,2000(2001),MeetingDate 2000,257-273.Publisher:Verlag Helvetica Chimica Acta,Zurich,Switzerland.
[12]Bergstroem C A,Stratford M,Lazorova,et al.Absorption classification of oral drugs based on molecular surface properties[J].JMed Chem,2003,46(4):558-570.
[13]A Avdeef,C M Berger,pH-metric solubility:3.Dissolution titration template method for solubility determination[J].Eur JPharm Sci,2001,14(4):281-291.
[14]A Avdeef,Physicochemical profiling(solubility,permeability and charge state),Current Topics in Medicinal Chemistry 1(2001) 277-351(Hilversum,Netherlands).
[15]G Caron,G Steyaert,A Pagliara,et al.Structure lipophilicity relationships of neutral and protonated b-blockers.Part 1.Intraand intermolecular effects in isotropic solvent systems[J].Helv Chim Acta,1999,82(8):1211-1222.
[16]B Slater,A McCormack,A Avdeef,et al.pH-Metric log P.4.Comparison of partition coefficients determined by HPLC and potentiometric methods to literature values[J].J Pharm Sci,1994,83(9):1280-1283.
[17]M Kansy,H Fischer,K Kratzat,et al.High-throughput artificial membrane permeability studies in early lead discovery and development.I.Parrilla.Editor(s):B.Testa.Pharmacokinetic Optimization in Drug Research:Biological,Physicochemical,and Computational-Strategies,[LogP2000,Lipophilicity Symposium],2nd,Lausanne,Switzerland,Mar.5-9,2000(2001),Meeting Date 2000,447-464.Publisher:Verlag Helvetica Chimica Acta,Zurich,Switzerland.
[18]S Winiwarter,N M Bonham,F Ax,et al.Correlation of human jejunal permeability(in vivo) of drugs with experimentally and theoretically derived parameters,a multivariate data analysis approach.J Med Chem,1998,41(25):4939-4949.
[19]N Jain,S H Yalkowsky.Estimation of the aqueous solubility I:application to organic nonelectrolytes[J].JPharm Sci,2001,90(6):234-252.
[20]F Lombardo,M.Y Shalaeva,K A Tupper,et al.ElogPoct:a tool for lipophilicity determination in drug discovery[J].JMed Chem,2000,43(15):2922-2928.
[21]M Ponec,J Kempenaar,B Shroot,et al.Glucocorticoids:binding affinity and lipophilicity[J].J Pharm Sci,1986,75(10):973-975.
[22]T S Wiedmann,W Liang,L Kamel.Solubilization of drugs by physiological mixtures of bile salts[J].Pharm Res,2002,19(8):1203-1208.
[23]A Glomme,J Maerz,J B Dressman.Comparison of a miniaturized shake-flask solubility method with automated potentiometric acid/base titrations and calculated solubilities[J].J Pharm Sci,2005,94(7):1-16.
[24]Takayama K,Takahara J,Fujikawa M,et al.Formula optimization based on artificial neural networks in transdermal drug delivery.[J].JControl Release,1999,62(1-2):161-170.
[1]Clark DE.Rapid calculation of polar molecular surface area and its application to the prediction of transport phenomena.I.Prediction of intestinal absorption[J].J Pharm Sci,1999,88(8):807-814.
[2]Palm K,Stenberg P,Luthman K,Artursson P.Polar molecular surface properties predict and the intestinal absorption of drugs in humans[J].Pharm Res,1997,14(5):568-571.
[3]Palm K,Luthman K,Ungell AL,et al.Correlation of drug absorption with molecular surface properties[J].JPharm Sci,1996,85(1):32-39.
[4]Physicians' Desk Reference(PDR),59th ed.;Thomson,2005.
[5]Hardman J G,Limbird,L.E.;Gilman,A.G..Pharmacokinetic Data,10th ed.In Goodman s The Pharmacological Basis of Therapeutics;McGraw-Hill:United States of America,2001,p.1924.
[6]Sietsema W K.The absolute oral bioavailability of selected drugs[J].Int J Clin Pharmacol Ther Toxicol,1989,27(4):179-211.
[7]Ren S,Das A,Lien EJ.QSAR analysis of membrane permeability to organic compounds[J].J Drug Target,1996,4(2):103-107.
[8]Hamilton H W,Steinbaugh B A,Stewart B H,et al.Evaluation of physicochemical parameters important to the oral bioavailability of peptide-like compounds:implications for the synthesis of renin inhibitors[J].JMed Chem,1995,38(9):1446-1455.
[9]Roth B D,Bocan T M A,Blankley C J,et al.Relationship between tissue selectivityand lipophilicity for inhibitors of HMG-CoA reductase[J].JMed Chem,1991,34(I):463-466.
[10]Walter A,Gutknecht J.Permeability of small nonelectrolytes through lipid bilayer membranes[J].JMembr Biol,1986,90(3):207-217.
[11]Palm K,Luthman K,Ungeli A L,et al.Correlation of drug absorption with molecular surface properties[J].JPharm Sci,1996,85(1):32-39.
[1]Marc Lindenberg,Sabine Kopp,Jennifer B.Dressman.classification of orally administered drugs on the world health organization model list of essential medicines according to the biopharmaceutics classification system[J].Eur JPharm Biopharm,2004,58(2):265-278.
[2]Akash Khandelwal,Praveen M.Bahadduri,Cheng Chang,et al.Computational Models to Assign Biopharmaceutics Drug Disposition Classification from Molecular Structure[J].Pharm Res,2007,24(12):2249-2262.
[3]Essential Medicines WHO Model List(revised March 2005)
[4]Chi Yuan Wu,Leslie Z.Benet.Predicting drug disposition via application of BCS:transport/absorption/elimination interplay and development of a biopharmaceutics drug disposi-tion classification system[J].Pharm Res,2005,22(1):11-23.
[5]World health organization organisation mondiale de la sante.Proposal to waive in vivo bioequivalence requirements for the WHO model list of essential medicines immediate release,solid oral dosage forms.Working Document QAS/04.109/Rev.1:
[1]王珏.Monte Carlo法在群体药动学研究中的应用[D].杭州:浙江大学药学院,1996-1998.
[2]Yang S,Bumgamer J G,Kruk L F,et al.Quantitative structure-activity relationships studies with micellar electrokinetic chromatography.Influence of surfacant type and mixed micelles on estimation of hydrophobicity and bioavailability[J].J Chromatogr A,1996,721(2):323-335.
[1]:闻新,周露,王丹力,等.Matlab神经网络应用设计[M].北京:科学出版社,2000.207
[2]:何勤,吴芳,蒋学华,等.药物动力学数据的神经网络处理方法[J].华西药学杂志,2002,17(2):123-125.
[3]:P C Wu,Y Obata,M Fujikawa,et al.Simultaneous optimization based on artificial neural networks in ketoprofen hydrogei formula containing O-enthy-3-butylcyciohexanol as percutaneous aborption enhancer[J].JPharm Sci,2001,90(7):1004-1014.
[4]:A P Plumb,R C Rowe,P York,et al.The effect of experimental design on the modeling of a tablet coating formulation using artifcial neural networks[J].Eur d Pharm Sci,2002,16(3):281-288.
[5]:Onuki Y,Hoshi M,Okabe H,et al.Formulation optimization of photocresslinked polyacrylic acid modified with 2-hydroxyethyl methacrylate hydrogel as an adhesive for a dermatological patch[J].J control release,2005,108(2-3):331-340.
[6]:Fan T,Takayama K,Hattori Y,et al.Formulation optimization of paclitaxel carried by PEGylated emulsions based on artificial nneural network[J].Pham Res,2004,21(9):1692-1697.
[7]:Lira CP,Quek SS,Peh KK.Prediction or drug release profiles using an intelligent learning system:an eperiment study in transdermal iontophoresis[J].J Pharm BiomedAnal,2003,31(1):159-168.
[8]:Plumb AP,Rowe RC,York P,et al.Effect of varying optimization parameters on optimization by guided evolutionary simulated annealing(GESA) using a tablet film coat as all example formulation[J].Eur J Pharm Sci,2003,18(3-4):259-266.
[9]:魏晓红,吴建军,梁文权.神经网络用于口服缓释制剂的处方设计[J].药学学报,2001,36(9):690-694.
[10]:Arulsudar N,Subramanian N,Muthy RS.Comparison of artificial neural network and multiple linear regression in the optimization of formulation parameters of leuprolide acetate loaded iiposomes[J].J Pharm Pharm Sci,2005,8(2):243-258.
[11]:Husseini GA,Abdel-Jabbar NM,Mjalli FS,et al.Modeling and sensitivity analysis of acoustic release of Doxorubicin from unstabilized pluronic P105 using an artificial neural network model [J].Technol Cancer Res Treat,2007,6(1):49-56.
[12]:Turkoglu M,Varol H,Celikok M.Tableting and stability evaluation of enteric-coated omeprazole pellets[J].Eur JPharm Biopharm,2004,57(2):279-286.
[13]:Shigeo Yamamura.Clinical application of artificial neural network(ANN) modeling to predict pharmacokinetic parameters of severely ill patients[J].Adv Drug Deliv Rev,2003,55(9):1233-1251.
[14]:李凌冰,张娜.人工神经网络结合药动学模型设计氯氮平非pH依赖型缓释片[J].中国药学杂志,2005,40(17):1321-1326.
[15]:傅旭春.用神经网络法预测药物在体透过人皮肤的渗透性[J].浙江大学学报(医学版),2003,32(2):152-154.
[16]:Shin-ichi Fujiwara,Fumiyoshi Yamashita,Mitsuru Hashida.Prediction of Caco-2 cell permeability using a combination of MO-calculation and neural network[J].Int J Pharm,2002,237(1-2,26):95-105.
[17]:Davis L FA.Handbook of genetic algorithm New York.NY:Van Ncem md Reinhold,1991
[18]:Forest S.Genetic algorithms:Principles of natural selection applied to computation[J].Science.1993.261(5123):872-878.
[19]:李进文,陈朝辉,曾平,等.基于遗传算法的药物动力学参数估计[J].数理医药学杂志,2006,19(5):529-530.
[20]:蔡煜东.遗传算法求算药物动力学参数的研究[J].中国药理学通报,1995,11(3):254-256.
[21]:Hanseh C,FujitaTl.p-σ-π Analysisl a method for the correlation of biological activity and chemical structure[J].Am Chem Soc,1964,86(8):16161.
[22]:Brick T,Schwefel H P.An overview of evolutionary algorithms for parameter optimization.Evol Comput,1993,1(1):1-23.
[23]:Agatonovic-Kustrin S,Beresford R,YusofAPM.Theoretically-derived descriptors important in human intestinal absorption[J].JPharm BiomedAnal,2001,25(2):227-237.
[24]:So SS,Karplus M.Evolutionary optimization in quantitative structure-activity relationship:an application of genetic neural networks[J].JMed Chem,1996,39(7):1521-1530.
[25]:So SS,Karplus M.Genetic neural networks for quantitative structure-activity relationships:improvements and application of benzodiazepine affinity for benzodiazepine/GABAA receptors[J].JMed Chem,1996,39(26):5246-5256.
[26]:Yasri A,Hartsough D.Toward an optimal procedure for variable selection and QSAR model building[J].JChem lnfComputSci,2001,41(5):1218-1227.
[27]:Guha R,Jurs P C.Development of QSAR models to predict and interpret the biological activity of artemisinin analogues[J].J Chem InfComput Sci,2004,44(4):1440-1449.
[28]:Armida Di Fenza,Giuliano Alagona,Caterina Ghio et ai.Caco-2 cell permeability modelling:a neural network coupled genetic algorithm approach[J].J Comput Aided Mol Des,2007,21(4):207-221.
[29]:李新城,王泽,朱伟兴,等.基于人工神经网络与遗传算法的硫酸沙丁胺醇渗透泵控释片剂释药行为预测研究[J].中国药学杂志,41(2):115-118.
[30]:杨铭,汪文娟.BP神经网络结合遗传算法用于丹参提取工艺的多目标优化[J].药学服务与 研究,2007,7(6):417-421.
[31]:刘红梅,李可意.基于BP神经网络和遗传算法优化莪术超临界萃取工艺[J].中国药学杂志,2006,41(5):371-374.
[32]:张宇飞,邵秀丽,雷建军.基于神经网络和遗传算法的中药滴丸制剂过程建模与优化[J].计算机工程与应用,2005,2(2):191-194.
[33]:王泽,李新城,朱伟兴.药物生物利用度遗传神经网络预测研究[J].药学学报,2006,41(12):1180-1183