环境化合物毒性定量构效关系建模方法研究
|
摘要
大量存在于空气、土壤和水等诸多环境要素中的化合物，它们对人类和动植物的毒性的定性与定量是当前迫切需要解决的问题。这些大量的环境化合物的毒性的当前检测手段是动物实验，其中便宜并且快速的试管实验用于初检，昂贵并且费时的体内实验用于终检。动物实验所面临的最大问题是伦理问题，随着人类文明程度的提高和人类对于自身与其共居地球的动植物之间关系的认识的深入，伦理问题将成为动物实验所面临的最大问题；其次，动物实验尤其是体内实验的高时间成本和高金钱成本也限制了动物实验检测化合物的数量。为解决动物实验的检测瓶颈问题，定量构效关系技术出现于世并且逐渐发展起来，定量构效关系涉及数学和统计学、量子力学、生物学、和计算机科学，是化合物的分子结构及其毒性之间的定量因果关系模型。定量构效关系以数学和统计学理论为基础建立数学模型，以计算机科学为工具实现数学和统计学理论，以量子力学为工具获取化合物的分子结构，以生物学为工具获取化合物的毒性数据以及认识化合物的致毒机理，利用所建立的模型可不经动物实验直接从化合物的分子结构获取化合物的毒性值。定量构效关系技术替代动物实验成为化合物毒性的检测手段的可能性，已经使得定量构效关系对当前的化合物毒性检测技术产生了重大影响，并且可以预见，定量构效关系对于当前检测技术的未来发展方向也将产生深远的影响。
本论文以环境化合物的毒性为检测目标，以定量构效关系技术为检测手段，探索了以定量构效关系技术替代动物实验检测化合物毒性的可能性，一共建立了三个定量构效关系模型，分别是致癌性分类模型、雌激素受体绑定能力分类模型和脑血屏障可透性分类模型，并且利用动物实验检测值对三个所建模型的性能进行了评价。
首先，利用美国环保局提供的1153个环境化合物的分子结构数据和长期啮齿类动物致癌性生物鉴定值，建立了环境化合物的致癌性分类模型。根据化合物的分子结构描述符的正态分布假设和化合物毒性分类值的二项分布假设，取得全部1153个化合物的分子结构和毒性值的罗杰斯分布函数式；利用拉普拉斯前提改造负对数似然函数取得罗杰斯分布的稀疏性和拟合性矛盾二者的制衡；利用交叉校验从729个分子结构描述符的权重排序中选择9个分子结构描述符，作为化合物致癌性分类模型的结构数据；以化合物致癌性的阴性和阳性之间距离的最大化为优化条件，选取797个化合物作为支持向量，选取高斯核函数度量两两化合物之间的相关性，利用支持向量机构造超平面将1153个化合物分类为阴性和阳性；用1153个化合物的长期啮齿类动物致癌性生物鉴定值对所建的化合物致癌性分类模型的性能进行了评价，模型对1153个化合物的致癌性的分类正确率是66.86%。
其次，利用美国环保局提供的278个环境化合物的分子结构数据和大鼠子宫细胞溶质雌激素受体竞争性绑定实验值，建立了环境化合物的雌激素受体绑定能力分类模型。利用化合物的熵构造化合物的对称无常，利用对称无常同时度量化合物的分子结构描述符两两之间的冗余性和分子结构描述符与雌激素受体绑定能力之间的因果性；设计算法从278个化合物的729个分子结构描述符中选择8个高因果性并且低冗余性的分子结构描述符，作为雌激素受体绑定能力分类模型的结构数据；构造8维笛卡尔特征空间，采用欧几里得距离度量278个化合物两两之间的相似性，采用k个最近邻居利用4个结构最相似的化合物投票决定待测化合物的雌激素受体绑定能力的阴性或阳性；利用278个化合物的大鼠子宫细胞溶质雌激素受体竞争性绑定实验值对所建的雌激素受体绑定能力分类模型的性能进行了评价，模型对278个化合物的雌激素受体绑定能力的分类正确率是96.76%。
最后，利用QSAR World提供的80个环境化合物的分子结构数据和脑血屏障可透性活体测量值，建立了环境化合物的脑血屏障可透性分类模型。构造全部80个化合物的完全图，利用点积计算完全图的邻接矩阵、次数矩阵和拉普拉斯矩阵，利用奇异值分解取得拉普拉斯矩阵的特征值和特征向量，利用完全图谱度量分子结构描述符的优度；利用交叉校验从729个分子结构描述符的优度排序中选择9个分子结构描述符，作为脑血屏障可透性分类模型的结构数据；构造贝叶斯分类器作为化合物的脑血屏障可透性分类模型，利用朴素假设将联合概率转化为独立概率，利用频率计算化合物的脑血屏障可透性的阴性和阳性的概率，利用正态分布构造分子结构描述符的概率分布式，利用最大似然估计取得正态分布的均值和方差；利用10个化合物的脑血屏障可透性活体测量值对所建立的化合物脑血屏障可透性分类模型的性能进行了评价，模型对10个化合物的脑血屏障可透性的分类正确率是90.00%。
The large number of compounds present in the air, soil and water, and manyother environmental elements, the determination of their qualitative and quantitativetoxicities to human, animal and plant is an urgent problem needed to solve. Thecurrent testing means of the toxicities of environmental compounds is animalexperiments, where usually the cheap and fast in vitro experiments are used forprescreening, and the expensive and time-consuming in vivo experiments for finaltest. The biggest problem faced by animal experiments is ethical issue, and with theimprovement on human civilization and the deeper understanding upon therelationship between human beings and their co-residing Earth's flora and fauna, theethical issue would be a biggest problem facing animal experiments; secondly,animal experiments especially in vivo experiments, owing to their high time cost andhigh monetary costs, also limit the quantity of compound for testing in practice. Toalleviate such bottleneck of animal experiments, QSAR technology appeared andgradually grew up, it involving mathematics and statistics, quantum mechanics,biology, and computer science, is the causal relationship model between molecularstructure and toxicity of compound. QSAR is based on mathematical and statisticaltheory to model, uses computer science as a tool to realize the mathematical andstatistical theory, uses quantum mechanics as a tool to acquire the molecular structureof compound, uses biology as a tool to acquire the toxicity data and theunderstanding of toxicity mechanism of compound, by QSAR model the toxicityvalue of compound can be obtained directly from molecular structure of compoundwithout animal experiments. It’s this possibility that QSAR technology would canreplace animal experiments to be a testing means to compound toxicity, that has ledto a great impact upon the current testing technology for compound toxicity by QSAR, and it would be forecasted that, QSAR would further exert profound impactupon the future development of current testing technologies.
This dissertation targets at the test for toxicity of environmental compounds,uses QSAR technology as the testing means, explores the possibility of QSAR to bea testing means to compound toxicity instead of animal experiments, a total of threeQSAR models are built, respectively carcinogenic classification model, estrogenreceptor binding capability classification model and cerebral blood barrierpermeability classification model, the performances of three models are evaluated bymeasurements of animal experiments.
Firstly, using the molecular structures and the long-term rodent animalcarcinogenicity bioassays values of1153environmental compounds provided by U.S.Environmental Protection Agency, build the carcinogenicity classification model ofenvironmental compounds. Based on the assumptions that molecular descriptorsfollow normal distribution and compound toxicity classification values followbinomial distribution, Rogers distribution function is constructed which the whole ofmolecular descriptors and toxicity classification values of1153compounds follow;use Laplace premise to transform negative logarithm likelihood function so that thebalance between the contradicting sparsity and fitting of Rogers distribution is gained;use cross-check to select9molecular descriptors from the sequence ordered byweights of729molecular descriptors, which serve as the structure data ofcarcinogenicity classification mode of compound to be built; by maximizing thedistance between negative and positive carcinogenic compound which is theoptimizing condition, select797compounds from all1153compounds as the supportvectors, select Gaussian kernel function to measure the relativity between pairwisecompounds, use support vector machine to construct super plane which classifies1153compounds into two classes of negative and positive; use the long-term rodentcarcinogenicity bioassays values of1153carcinogenic compounds to evaluate theperformance of classification model built, the classification accuracy rate of1153compounds in carcinogenicity by model is66.86%.
Secondly, using the molecular structures and the rat uterine cytosol estrogenreceptor competitive binding experimental values of278environmental compoundsprovided by U.S. Environmental Protection Agency, build the estrogen receptorbinding capacity classification model of environmental compounds. Use entropy to construct the symmetry impermanence of compound, use symmetrical impermanenceto measure simultaneously the causality between molecular descriptor and estrogenreceptor binding capacity of compound as well as the redundancy between pairwisemolecular descriptors; design an algorithm to select8high causal and low redundantmolecular descriptors from729molecular descriptors of278compounds, whichserve as the structure data of estrogen receptor binding capacity classification modelof compound to be built; construct a8-dimensional Cartesian feature space, useEuclidean distance to measure the pairwise similarity of278compounds, by knearest neighbor use4most similar compounds in structure to determine the negativeor positive of estrogen receptor binding ability of compound; use the rat uterinecytosol estrogen receptor competitive binding experiment values of278compoundsto evaluate the performance of estrogen receptor binding capacity classificationmodel of compound built, the classification accuracy rate of278compounds inestrogen receptor binding ability by model is96.76%.
Finally, using the molecular structures and the cerebral blood barrierpermeability in vivo measurement values of80environmental compounds providedby QSAR World, build cerebral blood barrier permeability classification model ofenvironmental compounds. Construct the complete graph of all80compounds, usedot product to calculate adjacency matrix, scale matrix and Laplace matrix, usesingular value decomposition to obtain the eigenvalue and eigenvectors of Laplacematrix, use the spectrum of full graph to measure the goodness of moleculardescriptor; use cross-check to select9molecular descriptors from the sequenceordered by goodnesses of729molecular descriptors, which serve as the structuredata of cerebral blood barrier permeability classification model of compound to bebuilt; construct Bayesian classifier to serve as the cerebral blood barrier permeabilityclassification model of compound, use the naivety assumption to transform jointprobability into independent probability, use frequency to calculate the negative andpositive probability of cerebral blood barrier permeability of compound, use normaldistribution to construct the probability distribution of molecular descriptors, usemaximum likelihood estimate to obtain the mean and variance values of normaldistribution; use the cerebral blood barrier permeability in vivo measurements of10compounds to evaluate the performance of cerebral blood barrier permeability classification model of compound built, the classification accuracy rate in cerebralblood barrier permeability by model is90.00%.
本论文以环境化合物的毒性为检测目标，以定量构效关系技术为检测手段，探索了以定量构效关系技术替代动物实验检测化合物毒性的可能性，一共建立了三个定量构效关系模型，分别是致癌性分类模型、雌激素受体绑定能力分类模型和脑血屏障可透性分类模型，并且利用动物实验检测值对三个所建模型的性能进行了评价。
首先，利用美国环保局提供的1153个环境化合物的分子结构数据和长期啮齿类动物致癌性生物鉴定值，建立了环境化合物的致癌性分类模型。根据化合物的分子结构描述符的正态分布假设和化合物毒性分类值的二项分布假设，取得全部1153个化合物的分子结构和毒性值的罗杰斯分布函数式；利用拉普拉斯前提改造负对数似然函数取得罗杰斯分布的稀疏性和拟合性矛盾二者的制衡；利用交叉校验从729个分子结构描述符的权重排序中选择9个分子结构描述符，作为化合物致癌性分类模型的结构数据；以化合物致癌性的阴性和阳性之间距离的最大化为优化条件，选取797个化合物作为支持向量，选取高斯核函数度量两两化合物之间的相关性，利用支持向量机构造超平面将1153个化合物分类为阴性和阳性；用1153个化合物的长期啮齿类动物致癌性生物鉴定值对所建的化合物致癌性分类模型的性能进行了评价，模型对1153个化合物的致癌性的分类正确率是66.86%。
其次，利用美国环保局提供的278个环境化合物的分子结构数据和大鼠子宫细胞溶质雌激素受体竞争性绑定实验值，建立了环境化合物的雌激素受体绑定能力分类模型。利用化合物的熵构造化合物的对称无常，利用对称无常同时度量化合物的分子结构描述符两两之间的冗余性和分子结构描述符与雌激素受体绑定能力之间的因果性；设计算法从278个化合物的729个分子结构描述符中选择8个高因果性并且低冗余性的分子结构描述符，作为雌激素受体绑定能力分类模型的结构数据；构造8维笛卡尔特征空间，采用欧几里得距离度量278个化合物两两之间的相似性，采用k个最近邻居利用4个结构最相似的化合物投票决定待测化合物的雌激素受体绑定能力的阴性或阳性；利用278个化合物的大鼠子宫细胞溶质雌激素受体竞争性绑定实验值对所建的雌激素受体绑定能力分类模型的性能进行了评价，模型对278个化合物的雌激素受体绑定能力的分类正确率是96.76%。
最后，利用QSAR World提供的80个环境化合物的分子结构数据和脑血屏障可透性活体测量值，建立了环境化合物的脑血屏障可透性分类模型。构造全部80个化合物的完全图，利用点积计算完全图的邻接矩阵、次数矩阵和拉普拉斯矩阵，利用奇异值分解取得拉普拉斯矩阵的特征值和特征向量，利用完全图谱度量分子结构描述符的优度；利用交叉校验从729个分子结构描述符的优度排序中选择9个分子结构描述符，作为脑血屏障可透性分类模型的结构数据；构造贝叶斯分类器作为化合物的脑血屏障可透性分类模型，利用朴素假设将联合概率转化为独立概率，利用频率计算化合物的脑血屏障可透性的阴性和阳性的概率，利用正态分布构造分子结构描述符的概率分布式，利用最大似然估计取得正态分布的均值和方差；利用10个化合物的脑血屏障可透性活体测量值对所建立的化合物脑血屏障可透性分类模型的性能进行了评价，模型对10个化合物的脑血屏障可透性的分类正确率是90.00%。
The large number of compounds present in the air, soil and water, and manyother environmental elements, the determination of their qualitative and quantitativetoxicities to human, animal and plant is an urgent problem needed to solve. Thecurrent testing means of the toxicities of environmental compounds is animalexperiments, where usually the cheap and fast in vitro experiments are used forprescreening, and the expensive and time-consuming in vivo experiments for finaltest. The biggest problem faced by animal experiments is ethical issue, and with theimprovement on human civilization and the deeper understanding upon therelationship between human beings and their co-residing Earth's flora and fauna, theethical issue would be a biggest problem facing animal experiments; secondly,animal experiments especially in vivo experiments, owing to their high time cost andhigh monetary costs, also limit the quantity of compound for testing in practice. Toalleviate such bottleneck of animal experiments, QSAR technology appeared andgradually grew up, it involving mathematics and statistics, quantum mechanics,biology, and computer science, is the causal relationship model between molecularstructure and toxicity of compound. QSAR is based on mathematical and statisticaltheory to model, uses computer science as a tool to realize the mathematical andstatistical theory, uses quantum mechanics as a tool to acquire the molecular structureof compound, uses biology as a tool to acquire the toxicity data and theunderstanding of toxicity mechanism of compound, by QSAR model the toxicityvalue of compound can be obtained directly from molecular structure of compoundwithout animal experiments. It’s this possibility that QSAR technology would canreplace animal experiments to be a testing means to compound toxicity, that has ledto a great impact upon the current testing technology for compound toxicity by QSAR, and it would be forecasted that, QSAR would further exert profound impactupon the future development of current testing technologies.
This dissertation targets at the test for toxicity of environmental compounds,uses QSAR technology as the testing means, explores the possibility of QSAR to bea testing means to compound toxicity instead of animal experiments, a total of threeQSAR models are built, respectively carcinogenic classification model, estrogenreceptor binding capability classification model and cerebral blood barrierpermeability classification model, the performances of three models are evaluated bymeasurements of animal experiments.
Firstly, using the molecular structures and the long-term rodent animalcarcinogenicity bioassays values of1153environmental compounds provided by U.S.Environmental Protection Agency, build the carcinogenicity classification model ofenvironmental compounds. Based on the assumptions that molecular descriptorsfollow normal distribution and compound toxicity classification values followbinomial distribution, Rogers distribution function is constructed which the whole ofmolecular descriptors and toxicity classification values of1153compounds follow;use Laplace premise to transform negative logarithm likelihood function so that thebalance between the contradicting sparsity and fitting of Rogers distribution is gained;use cross-check to select9molecular descriptors from the sequence ordered byweights of729molecular descriptors, which serve as the structure data ofcarcinogenicity classification mode of compound to be built; by maximizing thedistance between negative and positive carcinogenic compound which is theoptimizing condition, select797compounds from all1153compounds as the supportvectors, select Gaussian kernel function to measure the relativity between pairwisecompounds, use support vector machine to construct super plane which classifies1153compounds into two classes of negative and positive; use the long-term rodentcarcinogenicity bioassays values of1153carcinogenic compounds to evaluate theperformance of classification model built, the classification accuracy rate of1153compounds in carcinogenicity by model is66.86%.
Secondly, using the molecular structures and the rat uterine cytosol estrogenreceptor competitive binding experimental values of278environmental compoundsprovided by U.S. Environmental Protection Agency, build the estrogen receptorbinding capacity classification model of environmental compounds. Use entropy to construct the symmetry impermanence of compound, use symmetrical impermanenceto measure simultaneously the causality between molecular descriptor and estrogenreceptor binding capacity of compound as well as the redundancy between pairwisemolecular descriptors; design an algorithm to select8high causal and low redundantmolecular descriptors from729molecular descriptors of278compounds, whichserve as the structure data of estrogen receptor binding capacity classification modelof compound to be built; construct a8-dimensional Cartesian feature space, useEuclidean distance to measure the pairwise similarity of278compounds, by knearest neighbor use4most similar compounds in structure to determine the negativeor positive of estrogen receptor binding ability of compound; use the rat uterinecytosol estrogen receptor competitive binding experiment values of278compoundsto evaluate the performance of estrogen receptor binding capacity classificationmodel of compound built, the classification accuracy rate of278compounds inestrogen receptor binding ability by model is96.76%.
Finally, using the molecular structures and the cerebral blood barrierpermeability in vivo measurement values of80environmental compounds providedby QSAR World, build cerebral blood barrier permeability classification model ofenvironmental compounds. Construct the complete graph of all80compounds, usedot product to calculate adjacency matrix, scale matrix and Laplace matrix, usesingular value decomposition to obtain the eigenvalue and eigenvectors of Laplacematrix, use the spectrum of full graph to measure the goodness of moleculardescriptor; use cross-check to select9molecular descriptors from the sequenceordered by goodnesses of729molecular descriptors, which serve as the structuredata of cerebral blood barrier permeability classification model of compound to bebuilt; construct Bayesian classifier to serve as the cerebral blood barrier permeabilityclassification model of compound, use the naivety assumption to transform jointprobability into independent probability, use frequency to calculate the negative andpositive probability of cerebral blood barrier permeability of compound, use normaldistribution to construct the probability distribution of molecular descriptors, usemaximum likelihood estimate to obtain the mean and variance values of normaldistribution; use the cerebral blood barrier permeability in vivo measurements of10compounds to evaluate the performance of cerebral blood barrier permeability classification model of compound built, the classification accuracy rate in cerebralblood barrier permeability by model is90.00%.
引文
[1] MARTIN M T, KNUDSEN T B, REIF D M, et al. Predictive model of ratreproductive toxicity from ToxCast high throughput screening[J]. Biology ofReproduction,2011,85:327-339.
[2] ZHANG L, ZHU H, OPREA T, et al. QSAR modeling of the blood-brainbarrier permeability for diverse organic compounds[J]. Pharm. Res.,2008,25:1902-1914.
[3] WILLIAMS E S, PANKO J, PAUSTENBACH D J. The European Union’sREACH regulation: a review of its history and requirements[J]. Crit. Rev.Toxicol.,2009,39:553-675.
[4] TROPSHA A. Best practices for QSAR model development validation andexploitation[J]. Mol. Inf.,2010,29:476-488.
[5] CETIN S, YATKIN A, BAYRAM M. Ambient concentrations and sourceapportionment of pcbs and trace elements around an industrial area[J]. I. Zmir.Chemosphere,2007,(69):1267-1277.
[6] CINDORUK S S, TASDEMIR Y. Characterization of gas particleconcentrations and partitioning of polychlorinated biphenyls[J]. TurkeyEnviron. Pollut,2007,143:325-333.
[7] CINDORUK S S, TASDEMIR Y. Deposition of atmospheric particulate pcbsin suburban site of turkey[J]. Atmos. Res.,2007,85:300-309.
[8] CINDORUK S S, ESEN F, TASDEMIR Y. Concentration and gas particlepartitioning of polychlorinated biphenyls[J]. Res,2007,85:338-350.
[9] TROMELIN A, MERABTINE Y, ANDRIOT I, et al. Retention-releaseequilibrium of aroma compounds in polysaccharide study by quantitativestructure-activity property relationships approach[J]. Flavour Frag. J.,2010,25:431-442.
[10] TOROPOVA A P, TOROPOV AA, LOMBARDO A. A new bioconcentrationfactor model based on SMILES and indices of presence of atoms[J]. Eur. J.Med. Chem.,2010,5:4399-4402.
[11] SINGH A, SINGH DK. Molluscicidal activity of Lawsonia inermis and itsbinary and tertiary combinations with other plant derived molluscicides[J].Indian J Exp Biol,2001Mar,39(3):263-8.
[12] ROY P P, ROY K. Molecular docking and QSAR studies of aromataseinhibitor androstenedione derivatives[J]. Pharm. Pharmacol.,2010,62:1717-1728.
[13] ROY P P, ROY K. On some aspects of variable selection for partial leastsquares regression models[J]. QSAR Comb. Sci.,2008,27:302-313.
[14] MANOHARAN P, VIJAYAN R S K, GHOSHAL N. Rationalizing fragmentbased drug discovery for bace1: insights from fb-qsar, fb-qssr, multi objective(mo-qspr) and mif studies[J]. Journal Of Computer-Aided Molecular Design,2010,24(10):843-864.
[15] ROY P P, PAUL S, MITRA I, ROY K. On two novel parameters for validationof predictive QSAR models[J]. Molecules,2009,14:1660-1701.
[16] Rallo1R, Espinosa G. Using an ensemble of neural based qsars for theprediction of toxicological properties of chemical contaminants[C].7th WorldCongress of Chemical Engineering, July2005,83(4):387-392.
[17] CINDORUK S S. Determination of the concentrations dry deposition and airwater interface fluxes of pcbs[J]. Uludag University,2007,41:31-36.
[18] MASSARELLI I, IMBRIANI M, COI A. Development of QSAR models forpredicting hepatocarcinogenic toxicity of chemicals[J]. Med. Chem.,2009,44:3658-3664.
[19] KAR S, HARDING A P, ROY K, POPELIER P L A. QSAR with quantumtopological molecular similarity indices: toxicity of aromatic aldehydes totetrahymena pyriformis[J]. SAR QSAR Environ. Res.,2010,21:149-168.
[20] MERSCH-SUNDERMANN V. Biodegradability of some antibiotics,elimination of their genotoxicity and affection of waste water bacteria in asimple test[J]. Chemosphere,2000,40(7):701-710．
[21] HELGUERA A M, CORDEIRO M N D S, COMBES R D. Quantitativestructure carcinogenicity relationship for detecting structural alerts innitroso-compounds species rat sex male route of administration water[J].Toxicol. Appl. Pharmacol.,2008,231:197-207.
[22] MENG F H, SUN Y Z, LI Z J. The application of qsar in the study ofchemicals toxicity[J]. Chemistry&Bioenging,2009,24(11):5-7.
[23] FJODOROVA N, ZHOLDAKOVA Z, SINITSYNA O. Regulatory assessmentof chemicals within OECD member countries, EU and in Russia[J]. Environ.Sci. Health,2008,26:40-88.
[24] DEVILLERS J, DEVILLERS H. Prediction of acute mammalian toxicity fromQSARs and interspecies correlations[J]. SAR QSAR Environ. Res.,2009,20(5):467-500.
[25] GARCIA MORENO E, RUIZ M A, BARBAS C, et al. Determination oforganic peroxide in reversed micells with a poly-n-methylpyrrole horseradishperoxidase amperometric biosensor[J]. Analytica Chimica Acta,2001,448:9-17.
[26] RUZICKOVA J, KLANOVA P, CUPR G. An assessment of air-soil exchangeof polychlorinated biphenyls and organochlorine pesticides across central andsouthern europe[J]. Environ. Sci. Technol.,2008,42(1):179-185.
[27] WAN P J, PAKARINEN D R, HRON R J. Refining test method for thedetermination of cottonseed oil color[J]. JAOCS,1996,73:815.
[28] LEWIS DF, LAKE BG. Molecular orbital-generated QSARs in a homologousseries of alkoxyresorufins and studies of their interactive docking withP450s[J]. Xenobiotica,1995Dec,25(12):1355-69.
[29] MEDINA F J L. Quantitative structure-activity relationship analysis ofpyridinone hiv-1reverse transcriptase inhibitors using the k nearest neighbormethod and qsar-based database mining[J]. Comput Aided Moldes,2009,19(8):229-242.
[30] BENIGNI R, BOSSA C, RICHARD A M, YANG C. A novel approach:chemical relational databases, and the role of the ISSCAN database onassessing chemical carcinogenicity[J]. Ann.1st. Super,2008,44:48-56.
[31] BENFENATI E, BENIGNI R, DEMARINI D, HELMA C. Predictive modelsfor carcinogenicity: frameworks, state-of-the-art, and perspectives[J]. Environ.Sci. Health,2009,27:57-90.
[32] WAN P J, PAKARINEN D R. Comparison of visual and automatedcolorimeter for refined and bleached cottonseed oils[J]. JAOCS,1995,75:455-459.
[33] TAFAZOLI M, BAETEN A. In vitro mutagenicity and genotoxicity study of anumber of short-chain chlorinated hydrocarbons using the micronucleus testand the alkaline single cell gel electrophoresis technique (Comet assay) inhuman lymphocytes: a structure-activity relationship (QSAR) analysis of thegenotoxic and cytotoxic potential[J]. Mutagenesis,1998Mar,13(2):115-26.
[34] SCHNEIDER K, SCHWARZ M, BURKHOLDER I. A new tool to assess thereliability of toxicological data[J]. Toxicol. Lett.,2009,189(2):138-144.
[35] SCHüüRMANN G, EBERT R U, KüHNE R. Quantitative read-across forpredicting the acute fish toxicity of organic compounds[J]. Environ. Sci.Technol.,2011,45:4616-4622.
[36] DEARDEN J C. In silico prediction of drug toxicity[J]. Comput Aided MolDes,2009,17(9):119-127.
[37] VENKATAPATHYR, MOUDGAL C J, BRUCE R M. Assessment of the oralrat chronic lowest observed adverse effect level model in TOPKATA,a QSARsoftware package for toxicity prediction[J]. Chem. Inf. Comput. Sci.,2009,44(2):1623-1629.
[38] SUN F X, ZHOU Z M. Determination of oil color by image analysis[J].JAOCS,2001,78(7):749-752.
[39] LUKOVITS I A. Compact form of the adjacency matrix[J]. Chem. Inf.Comput. Sci.,2009,40(8):1147-1150.
[40] VAN D E, VOORT F R, SEDMAN J, et al. Stoichiometric determination ofhydroperoxides in fats and oils by Fourier transform infrared spectroscopy[J].J Am Oil Chem. Soc.,1997,74(8):897-906.
[41] PATLEWICZ G, CHEN M W, BELLIN C A. Non-testing approaches underREACH-help or hindrance, perspectives from a practitioner within industry[J].SAR QSAR Environ. Res.,2011,22(1):67-88.
[42] FENTON S E, CONDON M, ETTINGER A S, et al. Collection and use ofexposure data from human milk miomonitoring in the United States[J].Toxicol Environ Health,2009,68(14):1691-1712.
[43] MARQUART H, MEIJSTER T, VAN DE BOVENKAMP M. A structuredapproach to exposure based waiving of human health endpoints underREACH developed in the OSIRIS project[J]. Regul. Toxicol. Pharm.,2012,62(2):231-240.
[44] VAN DAMME S, BULTINCK P. A new computer program for qsar-analysis:arte-qsar[J]. Comput. Chem.,2007,28(11):1924-1928.
[45] KüHNE R, EBERT R U, SCHüüRMANN G. Chemical domain of QSARmodels from atom-centered fragments[J]. Chem. Inf. Model,2009,49:2660-2669.
[46] JI L, SCHüüRMANN G. Computational evidence for a-nitrosamino radicalas initial metabolite for both the p450dealkylation and denitrosation ofcarcinogenic nitrosamines[J]. Phys. Chem. B.,2012,116:903-912.
[47] ROY P P, PAUL S, MITRA I, ROY K. Two novel parameters for validation ofpredictive qsar models[J]. Molecules,2009,14(5):1660-1701.
[48] ROY P P. On some aspects of variable selection for partial least squaresregression models[J]. QSAR&Combinatorial Science,2008,27(3):302-313.
[49] ALDENBERG T, JAWORSKA J S. Multiple test in silico weight-of-evidencefor toxicological endpoints[J]. The Royal Society of Chemistry,2010,558-583.
[50] ROY P P, J. THOMAS LEONARD, KUNAL ROY. Exploring the impact ofsize of training sets for the development of predictive QSAR models[J].Chemometrics and Intelligent Laboratory Systems,2008,90(1):31-42.
[51] BENIGNI R, BOSSA C. Structure alerts for carcinogenicity and theSalmonella assay system: a novel insight through the chemical relationaldatabase technology[J]. Mutat. Res.,2008,659:248-261.
[52] DEBNATH AK, HANSCH C. The importance of hydrophobicity in themutagenicity of methanesulfonic acid esters with Salmonella typhimuriumTA100[J]. Chem Res Toxicol,1993May-Jun,6(3):310-2.
[53] ESCHER S E, TLUCZKIEWICZ I, BATKE M. Evaluation of inhalation TTCvalues with the database[J]. RepDose. Regul. Toxicol. Pharm.,2010,58(2):259-274.
[54] FELTER S, LANE R W, LATULIPPE M E. Refining the threshold oftoxicological concern (TTC) for risk prioritization of trace chemicals infood[J]. Food Chem. Toxicol.,2009,47:2236-2245.
[55] LI W, LEE F, WANG X R, et al. Feasibility study of quantifying anddiscriminating soybean oil adulteration in camellia oils by attenuated totalreflectance MIR and fiber optic diffuse reflectance NIR[J]. Food Chemistry,2006,95:529-536.
[56] JAWORSKA J S, GABBERT S, ALDENBERG T. Towards optimization ofchemical testing under REACH: a bayesian network approach to integratedtesting strategies[J]. Regul. Toxicol. Pharm.,2010,57:157-167.
[57] RUBEN MAGGIO, TEODORO KAUFMAN. Monitoring of fatty acidcomposition in virgin olive oil by Fourier transformed infrared spectroscopycoupled with partial least squares [J]. Food Chemistry,2009,114:1549-1554.
[58] PAGNI F, BELLA C. Structure and function of rat lymph nodes[J]. Arch.Histol. Cytol.,2008,71:69-76.
[59] NAMBIAR P R, TURNQUIST SE, MORTON D. Spontaneous tumorincidence in rasH2mice review of internal data and published literature[J].Toxicol. Pathol.,2012,40:614-623.
[60] MULLER L. In-vitro genotoxicity tests to detect carcinogenicity systemicreview[J]. Hum. Exp. Toxicol.,2009,28:131-133.
[61] ELGOWEINI M, CHETTY R. Primary nodal hemangioma[J]. Arch. Pathol.Lab. Med.,2012,136:110-112.
[62] ARMENTA S, GARRIGUES S, GUARDIA M DE LA. Determination ofedible oil parameters by near infrared spectroscopy[J]. Analytica ChimicaActa,2007,596:330-337.
[63] ZHAO J, SHI X, CASTRANOVA V, DING M. Occupational toxicology ofnickel and nickel compounds[J]. Environ. Pathol. Toxicol. Oncol.,2009,28(3):177-208.
[64] DING M. Metallic nickel nano and fine particles induce JB6cell apoptosisthrough a caspase-8mediated cytochrome independent[J]. Nanobiotechnology,2009,7:2-14.
[65] WANG H, CHO C H. Effect of NF-kappa signaling on apoptosis in chronicinflammation-associated carcinogenesis[J]. Curr. Cancer Drug Targets,2010,10(6):593-599.
[66] SALNIKOW K, ZHITKOVICH A. Genetic and epigenetic mechanisms inmetal carcinogenesis and cocarcinogenesis nickel arsenic and chromium[J].Chem. Res. Toxicol.,2008,21(1):28-44.
[67] PHILLIP J I, GREEN F Y, DAVIS J C A. Pulmonary and systemic toxicityfollowing exposure to nickel nanoparticles[J]. Am. J. Ind. Med.,2010,53:763-767.
[68] MORIMOTO Y, OYABU T, OGAMI A, et al. Investigation of gene expressionof MMP-2and TIMP-2mRNA in rat lung in inhaled nickel oxide and titaniumdioxide nanoparticles[J]. Ind. Health,2011,49(3):344-352.
[69]吴洪.阱基单胺氧化酶抑制剂活性与电子结构构效关系的计算分析[J].中国生物化学与分子生物学报，2007，（11）：959-962.
[70]苟绍华,李磊民.亚肼基二硫杂环戊烷化合物对水稻常见病菌的室内抑菌试验[J].西南科技大学学报,2008,23(4):88-91.
[71]张明,卢俊瑞,陈丽然,等.邻羟基苯基芳基及取代席夫碱的合成、表征及抑菌活性研究[J].天津理工大学学报,2009,25(1):1-4.
[72]李响,刘征涛,沈萍萍,孔志明.卤代酚类物质对抗氧化酶活性的影响研究及构效分析[J].环境科学学报,2004,24(5)：900-904.
[73]桑艳双,刘薇,王安娜,等.布洛伪麻自微乳化制剂的处方筛选及体外溶出的评价[J].沈阳药科大学学报,2008,25(8):598-602.
[74]张明,卢俊瑞.取代苯基-卤代邻羟基苄胺的合成、表征及抑菌活性[J].有机化学,2009,10:29-31.
[75]陈莉敏,刘洋,李光文,等.姜黄素金属配合物的合成、表征和抗瘤活性研究[J].中国新药杂志,2008,17(19):1676-1678.
[76]张辉，李娜，马梅，等.15种取代酚对淡水发光菌Q67的毒性及定量构效分析[J].生态毒理学报,2012,7(4)：373-380.
[77]陈莉敏,林友文,康建军,等.姜黄素-钌配合物的合成和抗氧化活性研究[J].海峡药学,2010,22(5):224-226.
[78] HODGE R, QUIGLEY J, JAMES I, MARSHALL J. Integrating reliabilityimprovement modeling into practice-challenges and pitfalls[C]. IEEEProceedings of the Annual Reliability and Maintainability Symposium,2002,158-164.
[79] MUNOZ A, COSTA M. Elucidating the mechanisms of nickel compounduptake a review of particulate and nano-nickel endocytosis and toxicity[J].Toxicol. Appl. Pharmacol.,2012,260(1):1-16.
[80] LIBERDA E N, CUEVAS A K, GILLESPIE P A. Exposure to inhaled nickelnanoparticles causes a reduction in number and function of bone marrowendothelial progenitor cells[J]. Inhal. Toxicol.,2010,22:95-99.
[81] GAVIN C. CAWLEY, NICOLA L C. Gene selection in cancer classificationusing sparse logistic regression with Bayesian regularization[J].Bioinformatics,2006,2(19):2348-2355.
[82] MAGAYE R, ZHAO J, BOWMAN L, DING M. Genotoxicity andcarcinogenicity of cobalt, nickel and copper-based nanoparticles[J]. Exp. Ther.Med.,2012,4(4):551-561.
[83] KAUR G, LONE I A, ATHAR M, ALAM M S. GUILANDINA BONDUC L.Possesse antioxidant activity and precludes ferric nitrilotriacetate (Fe-NTA)induced renal toxicity and tumor promotion response[J]. Environ. Pathol.Toxicol. Oncol.,2009,28(2):163-175.
[84] SU L, ZHAO G, ZHANG R. Translation-invariant wavelet de-noising methodwith improved thresholding[C]. IEEE International Symposium onCommunications and Information Technology,2005,599-602.
[85] DONALDSON K, POLAND C. Inhaled nanoparticles and lung cancer whatwe can learn from conventional particle toxicology[J]. Swiss Med. Wkly.,2012,22(1):11-15.
[86] GILLESPIE P A., KANG G S, ELDER A. Pulmonary response after exposureto inhaled nickel hydroxide nanoparticles: short and long-term studies inmice[J]. Nanotoxicology,2010,4(1):106-119.
[87] CAMERON K S, BUCHNER V, TCHOUNWOU P B. Exploring themolecular mechanisms of nickel-induced genotoxicity and carcinogenicity aliterature review[J]. Rev. Environ. Health,2011,26(2):81-92.
[88] LEI YU, HUAN LIU. Feature selection for high-dimensional data: a fastcorrelation-based filter solution[C]. Proceedings of the Twentieth InternationalConference on Machine Leaning,2003,12(2):111-123.
[89] CHO W S, DUFFIN R, POLAND C A, HOWIE S.E., MACNEE W.,BRADLEY M., MEGSON I.L., DONALDSON K.. Metal oxide nanoparticlesinduce unique inflammatory footprints in the lung: important implications fornanoparticle testing[J]. Environ. Health Perspect.,2010,118(12):1699-1706.
[90] BAN I, DROFENIK S J, MAKOVEC M D. Synthesis of copper-nickelnanoparticles prepared by mechanical milling for use in magnetichyperthermia[J]. Magn. Magn. Mater.,2011,323(17):2254-2258.
[91] GOODMAN J E, PRUEITT R L, THAKALI S. The nickel ion bioavailabilitymodel of the carcinogenic potential of nickel-containing substances in thelung[J]. Crit. Rev. Toxicol,2011,41(2):142-174.
[92] KAUR G, LONE I A, ATHAR M, ALAM MS. Guilandina possessesantioxidant activity and precludes ferric nitrilotriacetate induced renal toxicityand tumor promotion response[J]. Environ. Pathol. Toxicol. Oncol,2009,28(2):163-175.
[93] KORNICK R, ZUG K A. Reversible lung lesions in rats due to short-termexposure to ultrafine cobalt particles[J]. Ind. Health,2008,30(3-4):103-118.
[94] LIBERDA E N, CUEVAS A K, GILLESPIE P A. Exposure to inhaled nickelnanoparticles causes a reduction in number and function of bone marrowendothelial progenitor cells[J]. Inhal. Toxicol,2010,22:95-99.
[95] MAGAYE R, ZHAO J, BOWMAN L, DING M. Genotoxicity andcarcinogenicity of cobalt nickel and copper-based nanoparticles[J]. Exp. Ther.Med,2012,4(4):551-561.
[96] MORIMOTO Y, KOBAYASHI N, SHINOHARA N, MYOJO T, TANAKA I,NAKANISHI J. Hazard assessments of manufactured nanomaterials[J]. Occup.Health,2010,52(6):325-334.
[97] SHAW P, BOVEY R, TARDY S, et al. Induction of apoptosis by wild-typep53in a human colon tumor-derived cell line[J]. PMAS,1992,89(10):4495-4499.
[98] ROSE K, GUREWITZ E, FOX GC. Statistical mechanics and phasetransitions in clustering [J]. Phys. Rev. Lett,1990,65(8):945-948.
[99] ROSE K. Deterministic annealing for clustering, compression, classification,regression, and related optimization problems[J]. Proceedings of the IEEE,1998,86(11):2210-2239.
[100] POGUE-GEILE K, GEISER J R, SHU M, et al. Ribosomal protein genes areoverexpressed in colorectal cancer: isolation of a cDNA clone encoding thehuman S3ribosomal protein[J]. Mol. Cell. Biol,1991,11(8):3842-3849.
[101] ZHAO ZG, LIU H. Spectral feature selection for supervised and unsupervisedlearning[C]. Proceedings of the24th Annual International Conference onMachine Learning (ICML),2007,599-602.
[2] ZHANG L, ZHU H, OPREA T, et al. QSAR modeling of the blood-brainbarrier permeability for diverse organic compounds[J]. Pharm. Res.,2008,25:1902-1914.
[3] WILLIAMS E S, PANKO J, PAUSTENBACH D J. The European Union’sREACH regulation: a review of its history and requirements[J]. Crit. Rev.Toxicol.,2009,39:553-675.
[4] TROPSHA A. Best practices for QSAR model development validation andexploitation[J]. Mol. Inf.,2010,29:476-488.
[5] CETIN S, YATKIN A, BAYRAM M. Ambient concentrations and sourceapportionment of pcbs and trace elements around an industrial area[J]. I. Zmir.Chemosphere,2007,(69):1267-1277.
[6] CINDORUK S S, TASDEMIR Y. Characterization of gas particleconcentrations and partitioning of polychlorinated biphenyls[J]. TurkeyEnviron. Pollut,2007,143:325-333.
[7] CINDORUK S S, TASDEMIR Y. Deposition of atmospheric particulate pcbsin suburban site of turkey[J]. Atmos. Res.,2007,85:300-309.
[8] CINDORUK S S, ESEN F, TASDEMIR Y. Concentration and gas particlepartitioning of polychlorinated biphenyls[J]. Res,2007,85:338-350.
[9] TROMELIN A, MERABTINE Y, ANDRIOT I, et al. Retention-releaseequilibrium of aroma compounds in polysaccharide study by quantitativestructure-activity property relationships approach[J]. Flavour Frag. J.,2010,25:431-442.
[10] TOROPOVA A P, TOROPOV AA, LOMBARDO A. A new bioconcentrationfactor model based on SMILES and indices of presence of atoms[J]. Eur. J.Med. Chem.,2010,5:4399-4402.
[11] SINGH A, SINGH DK. Molluscicidal activity of Lawsonia inermis and itsbinary and tertiary combinations with other plant derived molluscicides[J].Indian J Exp Biol,2001Mar,39(3):263-8.
[12] ROY P P, ROY K. Molecular docking and QSAR studies of aromataseinhibitor androstenedione derivatives[J]. Pharm. Pharmacol.,2010,62:1717-1728.
[13] ROY P P, ROY K. On some aspects of variable selection for partial leastsquares regression models[J]. QSAR Comb. Sci.,2008,27:302-313.
[14] MANOHARAN P, VIJAYAN R S K, GHOSHAL N. Rationalizing fragmentbased drug discovery for bace1: insights from fb-qsar, fb-qssr, multi objective(mo-qspr) and mif studies[J]. Journal Of Computer-Aided Molecular Design,2010,24(10):843-864.
[15] ROY P P, PAUL S, MITRA I, ROY K. On two novel parameters for validationof predictive QSAR models[J]. Molecules,2009,14:1660-1701.
[16] Rallo1R, Espinosa G. Using an ensemble of neural based qsars for theprediction of toxicological properties of chemical contaminants[C].7th WorldCongress of Chemical Engineering, July2005,83(4):387-392.
[17] CINDORUK S S. Determination of the concentrations dry deposition and airwater interface fluxes of pcbs[J]. Uludag University,2007,41:31-36.
[18] MASSARELLI I, IMBRIANI M, COI A. Development of QSAR models forpredicting hepatocarcinogenic toxicity of chemicals[J]. Med. Chem.,2009,44:3658-3664.
[19] KAR S, HARDING A P, ROY K, POPELIER P L A. QSAR with quantumtopological molecular similarity indices: toxicity of aromatic aldehydes totetrahymena pyriformis[J]. SAR QSAR Environ. Res.,2010,21:149-168.
[20] MERSCH-SUNDERMANN V. Biodegradability of some antibiotics,elimination of their genotoxicity and affection of waste water bacteria in asimple test[J]. Chemosphere,2000,40(7):701-710．
[21] HELGUERA A M, CORDEIRO M N D S, COMBES R D. Quantitativestructure carcinogenicity relationship for detecting structural alerts innitroso-compounds species rat sex male route of administration water[J].Toxicol. Appl. Pharmacol.,2008,231:197-207.
[22] MENG F H, SUN Y Z, LI Z J. The application of qsar in the study ofchemicals toxicity[J]. Chemistry&Bioenging,2009,24(11):5-7.
[23] FJODOROVA N, ZHOLDAKOVA Z, SINITSYNA O. Regulatory assessmentof chemicals within OECD member countries, EU and in Russia[J]. Environ.Sci. Health,2008,26:40-88.
[24] DEVILLERS J, DEVILLERS H. Prediction of acute mammalian toxicity fromQSARs and interspecies correlations[J]. SAR QSAR Environ. Res.,2009,20(5):467-500.
[25] GARCIA MORENO E, RUIZ M A, BARBAS C, et al. Determination oforganic peroxide in reversed micells with a poly-n-methylpyrrole horseradishperoxidase amperometric biosensor[J]. Analytica Chimica Acta,2001,448:9-17.
[26] RUZICKOVA J, KLANOVA P, CUPR G. An assessment of air-soil exchangeof polychlorinated biphenyls and organochlorine pesticides across central andsouthern europe[J]. Environ. Sci. Technol.,2008,42(1):179-185.
[27] WAN P J, PAKARINEN D R, HRON R J. Refining test method for thedetermination of cottonseed oil color[J]. JAOCS,1996,73:815.
[28] LEWIS DF, LAKE BG. Molecular orbital-generated QSARs in a homologousseries of alkoxyresorufins and studies of their interactive docking withP450s[J]. Xenobiotica,1995Dec,25(12):1355-69.
[29] MEDINA F J L. Quantitative structure-activity relationship analysis ofpyridinone hiv-1reverse transcriptase inhibitors using the k nearest neighbormethod and qsar-based database mining[J]. Comput Aided Moldes,2009,19(8):229-242.
[30] BENIGNI R, BOSSA C, RICHARD A M, YANG C. A novel approach:chemical relational databases, and the role of the ISSCAN database onassessing chemical carcinogenicity[J]. Ann.1st. Super,2008,44:48-56.
[31] BENFENATI E, BENIGNI R, DEMARINI D, HELMA C. Predictive modelsfor carcinogenicity: frameworks, state-of-the-art, and perspectives[J]. Environ.Sci. Health,2009,27:57-90.
[32] WAN P J, PAKARINEN D R. Comparison of visual and automatedcolorimeter for refined and bleached cottonseed oils[J]. JAOCS,1995,75:455-459.
[33] TAFAZOLI M, BAETEN A. In vitro mutagenicity and genotoxicity study of anumber of short-chain chlorinated hydrocarbons using the micronucleus testand the alkaline single cell gel electrophoresis technique (Comet assay) inhuman lymphocytes: a structure-activity relationship (QSAR) analysis of thegenotoxic and cytotoxic potential[J]. Mutagenesis,1998Mar,13(2):115-26.
[34] SCHNEIDER K, SCHWARZ M, BURKHOLDER I. A new tool to assess thereliability of toxicological data[J]. Toxicol. Lett.,2009,189(2):138-144.
[35] SCHüüRMANN G, EBERT R U, KüHNE R. Quantitative read-across forpredicting the acute fish toxicity of organic compounds[J]. Environ. Sci.Technol.,2011,45:4616-4622.
[36] DEARDEN J C. In silico prediction of drug toxicity[J]. Comput Aided MolDes,2009,17(9):119-127.
[37] VENKATAPATHYR, MOUDGAL C J, BRUCE R M. Assessment of the oralrat chronic lowest observed adverse effect level model in TOPKATA,a QSARsoftware package for toxicity prediction[J]. Chem. Inf. Comput. Sci.,2009,44(2):1623-1629.
[38] SUN F X, ZHOU Z M. Determination of oil color by image analysis[J].JAOCS,2001,78(7):749-752.
[39] LUKOVITS I A. Compact form of the adjacency matrix[J]. Chem. Inf.Comput. Sci.,2009,40(8):1147-1150.
[40] VAN D E, VOORT F R, SEDMAN J, et al. Stoichiometric determination ofhydroperoxides in fats and oils by Fourier transform infrared spectroscopy[J].J Am Oil Chem. Soc.,1997,74(8):897-906.
[41] PATLEWICZ G, CHEN M W, BELLIN C A. Non-testing approaches underREACH-help or hindrance, perspectives from a practitioner within industry[J].SAR QSAR Environ. Res.,2011,22(1):67-88.
[42] FENTON S E, CONDON M, ETTINGER A S, et al. Collection and use ofexposure data from human milk miomonitoring in the United States[J].Toxicol Environ Health,2009,68(14):1691-1712.
[43] MARQUART H, MEIJSTER T, VAN DE BOVENKAMP M. A structuredapproach to exposure based waiving of human health endpoints underREACH developed in the OSIRIS project[J]. Regul. Toxicol. Pharm.,2012,62(2):231-240.
[44] VAN DAMME S, BULTINCK P. A new computer program for qsar-analysis:arte-qsar[J]. Comput. Chem.,2007,28(11):1924-1928.
[45] KüHNE R, EBERT R U, SCHüüRMANN G. Chemical domain of QSARmodels from atom-centered fragments[J]. Chem. Inf. Model,2009,49:2660-2669.
[46] JI L, SCHüüRMANN G. Computational evidence for a-nitrosamino radicalas initial metabolite for both the p450dealkylation and denitrosation ofcarcinogenic nitrosamines[J]. Phys. Chem. B.,2012,116:903-912.
[47] ROY P P, PAUL S, MITRA I, ROY K. Two novel parameters for validation ofpredictive qsar models[J]. Molecules,2009,14(5):1660-1701.
[48] ROY P P. On some aspects of variable selection for partial least squaresregression models[J]. QSAR&Combinatorial Science,2008,27(3):302-313.
[49] ALDENBERG T, JAWORSKA J S. Multiple test in silico weight-of-evidencefor toxicological endpoints[J]. The Royal Society of Chemistry,2010,558-583.
[50] ROY P P, J. THOMAS LEONARD, KUNAL ROY. Exploring the impact ofsize of training sets for the development of predictive QSAR models[J].Chemometrics and Intelligent Laboratory Systems,2008,90(1):31-42.
[51] BENIGNI R, BOSSA C. Structure alerts for carcinogenicity and theSalmonella assay system: a novel insight through the chemical relationaldatabase technology[J]. Mutat. Res.,2008,659:248-261.
[52] DEBNATH AK, HANSCH C. The importance of hydrophobicity in themutagenicity of methanesulfonic acid esters with Salmonella typhimuriumTA100[J]. Chem Res Toxicol,1993May-Jun,6(3):310-2.
[53] ESCHER S E, TLUCZKIEWICZ I, BATKE M. Evaluation of inhalation TTCvalues with the database[J]. RepDose. Regul. Toxicol. Pharm.,2010,58(2):259-274.
[54] FELTER S, LANE R W, LATULIPPE M E. Refining the threshold oftoxicological concern (TTC) for risk prioritization of trace chemicals infood[J]. Food Chem. Toxicol.,2009,47:2236-2245.
[55] LI W, LEE F, WANG X R, et al. Feasibility study of quantifying anddiscriminating soybean oil adulteration in camellia oils by attenuated totalreflectance MIR and fiber optic diffuse reflectance NIR[J]. Food Chemistry,2006,95:529-536.
[56] JAWORSKA J S, GABBERT S, ALDENBERG T. Towards optimization ofchemical testing under REACH: a bayesian network approach to integratedtesting strategies[J]. Regul. Toxicol. Pharm.,2010,57:157-167.
[57] RUBEN MAGGIO, TEODORO KAUFMAN. Monitoring of fatty acidcomposition in virgin olive oil by Fourier transformed infrared spectroscopycoupled with partial least squares [J]. Food Chemistry,2009,114:1549-1554.
[58] PAGNI F, BELLA C. Structure and function of rat lymph nodes[J]. Arch.Histol. Cytol.,2008,71:69-76.
[59] NAMBIAR P R, TURNQUIST SE, MORTON D. Spontaneous tumorincidence in rasH2mice review of internal data and published literature[J].Toxicol. Pathol.,2012,40:614-623.
[60] MULLER L. In-vitro genotoxicity tests to detect carcinogenicity systemicreview[J]. Hum. Exp. Toxicol.,2009,28:131-133.
[61] ELGOWEINI M, CHETTY R. Primary nodal hemangioma[J]. Arch. Pathol.Lab. Med.,2012,136:110-112.
[62] ARMENTA S, GARRIGUES S, GUARDIA M DE LA. Determination ofedible oil parameters by near infrared spectroscopy[J]. Analytica ChimicaActa,2007,596:330-337.
[63] ZHAO J, SHI X, CASTRANOVA V, DING M. Occupational toxicology ofnickel and nickel compounds[J]. Environ. Pathol. Toxicol. Oncol.,2009,28(3):177-208.
[64] DING M. Metallic nickel nano and fine particles induce JB6cell apoptosisthrough a caspase-8mediated cytochrome independent[J]. Nanobiotechnology,2009,7:2-14.
[65] WANG H, CHO C H. Effect of NF-kappa signaling on apoptosis in chronicinflammation-associated carcinogenesis[J]. Curr. Cancer Drug Targets,2010,10(6):593-599.
[66] SALNIKOW K, ZHITKOVICH A. Genetic and epigenetic mechanisms inmetal carcinogenesis and cocarcinogenesis nickel arsenic and chromium[J].Chem. Res. Toxicol.,2008,21(1):28-44.
[67] PHILLIP J I, GREEN F Y, DAVIS J C A. Pulmonary and systemic toxicityfollowing exposure to nickel nanoparticles[J]. Am. J. Ind. Med.,2010,53:763-767.
[68] MORIMOTO Y, OYABU T, OGAMI A, et al. Investigation of gene expressionof MMP-2and TIMP-2mRNA in rat lung in inhaled nickel oxide and titaniumdioxide nanoparticles[J]. Ind. Health,2011,49(3):344-352.
[69]吴洪.阱基单胺氧化酶抑制剂活性与电子结构构效关系的计算分析[J].中国生物化学与分子生物学报，2007，（11）：959-962.
[70]苟绍华,李磊民.亚肼基二硫杂环戊烷化合物对水稻常见病菌的室内抑菌试验[J].西南科技大学学报,2008,23(4):88-91.
[71]张明,卢俊瑞,陈丽然,等.邻羟基苯基芳基及取代席夫碱的合成、表征及抑菌活性研究[J].天津理工大学学报,2009,25(1):1-4.
[72]李响,刘征涛,沈萍萍,孔志明.卤代酚类物质对抗氧化酶活性的影响研究及构效分析[J].环境科学学报,2004,24(5)：900-904.
[73]桑艳双,刘薇,王安娜,等.布洛伪麻自微乳化制剂的处方筛选及体外溶出的评价[J].沈阳药科大学学报,2008,25(8):598-602.
[74]张明,卢俊瑞.取代苯基-卤代邻羟基苄胺的合成、表征及抑菌活性[J].有机化学,2009,10:29-31.
[75]陈莉敏,刘洋,李光文,等.姜黄素金属配合物的合成、表征和抗瘤活性研究[J].中国新药杂志,2008,17(19):1676-1678.
[76]张辉，李娜，马梅，等.15种取代酚对淡水发光菌Q67的毒性及定量构效分析[J].生态毒理学报,2012,7(4)：373-380.
[77]陈莉敏,林友文,康建军,等.姜黄素-钌配合物的合成和抗氧化活性研究[J].海峡药学,2010,22(5):224-226.
[78] HODGE R, QUIGLEY J, JAMES I, MARSHALL J. Integrating reliabilityimprovement modeling into practice-challenges and pitfalls[C]. IEEEProceedings of the Annual Reliability and Maintainability Symposium,2002,158-164.
[79] MUNOZ A, COSTA M. Elucidating the mechanisms of nickel compounduptake a review of particulate and nano-nickel endocytosis and toxicity[J].Toxicol. Appl. Pharmacol.,2012,260(1):1-16.
[80] LIBERDA E N, CUEVAS A K, GILLESPIE P A. Exposure to inhaled nickelnanoparticles causes a reduction in number and function of bone marrowendothelial progenitor cells[J]. Inhal. Toxicol.,2010,22:95-99.
[81] GAVIN C. CAWLEY, NICOLA L C. Gene selection in cancer classificationusing sparse logistic regression with Bayesian regularization[J].Bioinformatics,2006,2(19):2348-2355.
[82] MAGAYE R, ZHAO J, BOWMAN L, DING M. Genotoxicity andcarcinogenicity of cobalt, nickel and copper-based nanoparticles[J]. Exp. Ther.Med.,2012,4(4):551-561.
[83] KAUR G, LONE I A, ATHAR M, ALAM M S. GUILANDINA BONDUC L.Possesse antioxidant activity and precludes ferric nitrilotriacetate (Fe-NTA)induced renal toxicity and tumor promotion response[J]. Environ. Pathol.Toxicol. Oncol.,2009,28(2):163-175.
[84] SU L, ZHAO G, ZHANG R. Translation-invariant wavelet de-noising methodwith improved thresholding[C]. IEEE International Symposium onCommunications and Information Technology,2005,599-602.
[85] DONALDSON K, POLAND C. Inhaled nanoparticles and lung cancer whatwe can learn from conventional particle toxicology[J]. Swiss Med. Wkly.,2012,22(1):11-15.
[86] GILLESPIE P A., KANG G S, ELDER A. Pulmonary response after exposureto inhaled nickel hydroxide nanoparticles: short and long-term studies inmice[J]. Nanotoxicology,2010,4(1):106-119.
[87] CAMERON K S, BUCHNER V, TCHOUNWOU P B. Exploring themolecular mechanisms of nickel-induced genotoxicity and carcinogenicity aliterature review[J]. Rev. Environ. Health,2011,26(2):81-92.
[88] LEI YU, HUAN LIU. Feature selection for high-dimensional data: a fastcorrelation-based filter solution[C]. Proceedings of the Twentieth InternationalConference on Machine Leaning,2003,12(2):111-123.
[89] CHO W S, DUFFIN R, POLAND C A, HOWIE S.E., MACNEE W.,BRADLEY M., MEGSON I.L., DONALDSON K.. Metal oxide nanoparticlesinduce unique inflammatory footprints in the lung: important implications fornanoparticle testing[J]. Environ. Health Perspect.,2010,118(12):1699-1706.
[90] BAN I, DROFENIK S J, MAKOVEC M D. Synthesis of copper-nickelnanoparticles prepared by mechanical milling for use in magnetichyperthermia[J]. Magn. Magn. Mater.,2011,323(17):2254-2258.
[91] GOODMAN J E, PRUEITT R L, THAKALI S. The nickel ion bioavailabilitymodel of the carcinogenic potential of nickel-containing substances in thelung[J]. Crit. Rev. Toxicol,2011,41(2):142-174.
[92] KAUR G, LONE I A, ATHAR M, ALAM MS. Guilandina possessesantioxidant activity and precludes ferric nitrilotriacetate induced renal toxicityand tumor promotion response[J]. Environ. Pathol. Toxicol. Oncol,2009,28(2):163-175.
[93] KORNICK R, ZUG K A. Reversible lung lesions in rats due to short-termexposure to ultrafine cobalt particles[J]. Ind. Health,2008,30(3-4):103-118.
[94] LIBERDA E N, CUEVAS A K, GILLESPIE P A. Exposure to inhaled nickelnanoparticles causes a reduction in number and function of bone marrowendothelial progenitor cells[J]. Inhal. Toxicol,2010,22:95-99.
[95] MAGAYE R, ZHAO J, BOWMAN L, DING M. Genotoxicity andcarcinogenicity of cobalt nickel and copper-based nanoparticles[J]. Exp. Ther.Med,2012,4(4):551-561.
[96] MORIMOTO Y, KOBAYASHI N, SHINOHARA N, MYOJO T, TANAKA I,NAKANISHI J. Hazard assessments of manufactured nanomaterials[J]. Occup.Health,2010,52(6):325-334.
[97] SHAW P, BOVEY R, TARDY S, et al. Induction of apoptosis by wild-typep53in a human colon tumor-derived cell line[J]. PMAS,1992,89(10):4495-4499.
[98] ROSE K, GUREWITZ E, FOX GC. Statistical mechanics and phasetransitions in clustering [J]. Phys. Rev. Lett,1990,65(8):945-948.
[99] ROSE K. Deterministic annealing for clustering, compression, classification,regression, and related optimization problems[J]. Proceedings of the IEEE,1998,86(11):2210-2239.
[100] POGUE-GEILE K, GEISER J R, SHU M, et al. Ribosomal protein genes areoverexpressed in colorectal cancer: isolation of a cDNA clone encoding thehuman S3ribosomal protein[J]. Mol. Cell. Biol,1991,11(8):3842-3849.
[101] ZHAO ZG, LIU H. Spectral feature selection for supervised and unsupervisedlearning[C]. Proceedings of the24th Annual International Conference onMachine Learning (ICML),2007,599-602.