药物—靶标相互作用及药物对组合研究
|
摘要
药物研发是全球性的发展问题，过去几十年中，药物靶向治疗策略取得了相当大的成绩，确定药物治疗靶点，寻找针对靶点的特异性药物，是医药企业以及实验室研究的着力点，并且已经取得了相当大的成绩，为人类健康做出了不可磨灭的贡献。然而，近些年，新药研发速率不断下降，研发成本不断上升，究其原因：一是药物研发早期阶段筛选大量的药物候选物，仍然主要依靠耗时耗力的实验手段，后期发现药物的疗效不理想或者副作用导致研发失败；二是大部分人类疾病是由多因素引起的复杂疾病，而生物系统具有一定的冗余度和鲁棒性，单一药物对单一靶点的干扰不能引起系统表型的改变。
随着不同组学技术的进步，累积了很多的的生物学数据，使得生物学数据库逐渐增加。生物信息学与计算生物学的发展，对于解开药物研发面临的困境，提供了一种有效手段。特别是在药物研发的早期阶段，虚拟筛选技术提供了一种高效而高通量的手段，为早期研发锁定目标、节约成本起到了重要作用。运用计算手段，整合多种数据资源，挖掘数据中隐含的关联信息，筛选可靠的药物-靶标关系和有效的药物组合恰逢其时。
本文从公开数据库资源入手，针对医药领域一直关心的两大热点问题：药物-靶标关系预测以及药物组合研究，设计了不同的计算模型，并验证了模型的有效性。本文的研究工作主要包含以下三个部分：
1、建立了一个化学相似性系综模型，在大范围的公开数据库内探索蛋白-配体的相互作用关系。研究共涵盖了53092个配体小分子和14732个人类蛋白，选用的蛋白不仅包含少量已知的药物靶标，而是包含已获得较多配体信息（大于5个配体）的人类蛋白；选用的配体也不限于少量的上市药物，而是包含药物、小分子化合物、离子等可作为蛋白配体的小分子，极大地丰富了化学相似性系综法的应用范围。在蛋白-配体相互关系的预测中，使用了GpiDAPH3和MACCS key两种不同编码类型的指纹表示配体小分子，预测结果的ROC曲线下面积AUC分别达到了0.6608和0.8344。可以发现，基于MACCS key指纹建立的化学相似性系综模型仍然保持了较好的预测效果，说明了化学相似性系综法具有较好的拓展功能。后来，为中药成分寻找蛋白靶标的研究，进一步说明了化学相似性系综模型对于预测新的药物-靶标关系具有一定效力。
2、建立了一个基于化学倾向性信息的支持向量机模型。特征向量的构建抛弃了蛋白结构信息，完全使用蛋白已知配体的化学信息。332个特征分别取自配体的指纹信息以及已知的蛋白-配体相互关系，这样构建的特征向量被我们称之为化学倾向性特征向量。该模型对于预测蛋白-配体相互作用关系显示了出色的能力，超过了化学相似性系综模型的预测结果。五倍交叉检验和独立检验都显示出很好的结果，ROC曲线下面积AUC分别达到0.9914和0.9878。随后的特征选择，初步揭示了配体-蛋白（药物-靶标）关系确立的本质联系。最后，应用该模型筛选了精神分裂症靶点DAO的抑制剂，并进行了实验。实验结果进一步显示了该模型的优势，10个预测到的药物候选物中，有7个获得文献或实验支持，并且发现了4个新的DAO抑制剂，进一步印证了基于化学倾向性的支持向量机模型对于预测药物前体和靶标具有良好的效果。
3、提出了一个新的计算方法，通过整合药物作用下的基因芯片数据，药物作用下的子网络以及现有的信号通路信息，构建了一个机器学习模型，用于预测药物组合。首先使用单独用药的基因表达数据，预测组合药物作用下的基因表达变化比率。根据用药前后的基因表达变化比率，定义现有PPI网络的权重，用jActiveModules筛选药物作用下的最优子网。最优子网中的基因被认为是药物干扰引起细胞系统响应的基因。以药物组合及单独用药下最优子网中的基因在信号通路中出现的频率构建特征向量，优化特征并建立模型。“留一法”交叉验证结果显示，ROC曲线下面积AUC的均值达到0.7941，说明该模型能够较好地实现药物组合与负样本的分类。以癌症为例的案例分析发现，预测到的前10个癌症药物组合中，有3个是数据库中已经存在的，有2个找到了文献支持，进一步说明了该模型的有效性。
Drug discovery and development have raised widespread attention in the past twodecades and the target-orienented drug pharmacology has also achived great success.Identifying therapeutic targets and seeking specific drugs for targets, which are thefocal point for pharmaceutical enterprises and laboratory research, have alreadyachieved great progress and made indelible contributions to human health. However,in recent year, new drug development rate slows down and the cost of researchcontinues to rise, mainly due to two reasons: first is that vast screening of drugcandidates in early state still relies on time and labor consuming experimental means,while in later stage the unsatisfactory efficacy or side-effects of the drug may lead tofailures; second is that as most human diseases are complex disease induced by manyfactors, and the biological system has a certain degree of redundancy and robustness,the interference on single target by single drug can not alter the system phenotype.
With the development of all kinds of omics, the accumulation of large amounts ofbiological data leads to the continuous expansion of biological database. Thedevelopment of bioinformatics and computational biology provides an effectivemeans to solve difficulties in drug development. Especially in the early stages of drugdevelopment, virtual screening method provides an efficient and high-throughputtechnique, which plays an important role in saving cost and narrowing down theresearch scope. It is at just the right time to use in silico methods for the integration ofa variety of data sources, data mining of the underlying associations, and screening ofreliable drug-target interactions and effective drug combinations.
Based on the public database resources, this paper designs different computationalmodels, and verifies their effectiveness aiming at the two hot issues that concern in the medical field, drug-target interaction and drug combination prediction. The mainresearch work of this paper includes the following three parts:
1. A chemical similarity ensemble model is established to explore the protein-ligandinteractions from public databases in a large scale. This research covers a total of53092ligand and14732human proteins: the selected proteins contains not only afew known drug targets, but also those with rich ligand information (more than5ligands each); the selection of ligands is not limited to a few commercial drugs,but contains drugs, small molecular compounds, ions et al that can be used asprotein ligands. Our reasearch has greatly enriched the application scope ofchemical similarity ensemble method. Using two different ligand fingerprintsGpiDAPH3and MACCS key, the areas under the ROC curves (AUC) achieve0.6608and0.8344respectively. It can be found that, the similarity ensemblemodel using MACCS key fingerprint still maintains a good prediction capability,showing strong extensibility. Later, the study of seeking protein targets forTraditional Chinese Medicine composition further illustrates that the chemicalsimilarity ensemble method has a certain validity to predict new drug-targetinteractions.
2. A support vector machine (SVM) model based on the chemical-protein bindingsfrom STITCH is developed. New features have been built from ligand structurespace and ligand-protein networks and then chosen as the the input parameters forSVM model.332feature vectors are constructed from both ligand fingerprint andprotein-ligand interactions, called as chemical preference feature vectors. Thismodel shows good ability in predicting protein-ligand interactions, whichoutperforms the state-of-the-art method based on ligand similarity. The resultedAUC for5-fold cross validation and independent test reaches as high as0.9914and0.9878, respectively, achiving a very high accuracy of prediction.Furthermore, in order to simplify the model,182distinct features in pairs havebeen chosen to rebuild a new model which still shows similar outcome as the one built on the whole332features. Then, this refined model is used to search for thepotential D-amino acid oxidase (DAO) inhibitors out of STITCH database andthe predicted results are finally verified by our wet experiments. Out of10candidates obtained, seven DAO inhibitors have been verified, in which four arenewly found in the present study, and one may have a new application in therapyof psychiatric disorders other than being an antineoplastic agent. Obviously, themodel in this paper possesses abilities for high-throughput new drug and targetdiscovery in a timely manner.
3. A new calculation method is proposed by integrating gene chip data andsub-network under the drug effect, as well as pathway information available, tobuild a machine learning model, for the prediction of drug combination. Firstlygene expression data of single drug is used to forecast gene expression variationratio of drug combinations. The weight of existing PPI network is definedaccording to gene expression ratios before and after the treatment, and theoptimal drug sub-network is identified by jActiveModules. Genes in the optimalsub-network is thought to be the response of cell system to drug interference. Thefrequencies of the genes in the optimal sub-network by drug combinations andsingle drug alone appearing in different pathways are adopted as the featurevectors to optimize the features and construct the model. Results of the crossvalidation indicate that mean area under the ROC curve reaches0.7941, whichindicates that this model can classify the positive and negative samples of drugcombination very well. A case study in cancer as an instance finds that, amongthe first10forecasted drug combinations, three already exist in the database andtwo others are supported in literature review, further indicating the effectivenessof the model.
随着不同组学技术的进步，累积了很多的的生物学数据，使得生物学数据库逐渐增加。生物信息学与计算生物学的发展，对于解开药物研发面临的困境，提供了一种有效手段。特别是在药物研发的早期阶段，虚拟筛选技术提供了一种高效而高通量的手段，为早期研发锁定目标、节约成本起到了重要作用。运用计算手段，整合多种数据资源，挖掘数据中隐含的关联信息，筛选可靠的药物-靶标关系和有效的药物组合恰逢其时。
本文从公开数据库资源入手，针对医药领域一直关心的两大热点问题：药物-靶标关系预测以及药物组合研究，设计了不同的计算模型，并验证了模型的有效性。本文的研究工作主要包含以下三个部分：
1、建立了一个化学相似性系综模型，在大范围的公开数据库内探索蛋白-配体的相互作用关系。研究共涵盖了53092个配体小分子和14732个人类蛋白，选用的蛋白不仅包含少量已知的药物靶标，而是包含已获得较多配体信息（大于5个配体）的人类蛋白；选用的配体也不限于少量的上市药物，而是包含药物、小分子化合物、离子等可作为蛋白配体的小分子，极大地丰富了化学相似性系综法的应用范围。在蛋白-配体相互关系的预测中，使用了GpiDAPH3和MACCS key两种不同编码类型的指纹表示配体小分子，预测结果的ROC曲线下面积AUC分别达到了0.6608和0.8344。可以发现，基于MACCS key指纹建立的化学相似性系综模型仍然保持了较好的预测效果，说明了化学相似性系综法具有较好的拓展功能。后来，为中药成分寻找蛋白靶标的研究，进一步说明了化学相似性系综模型对于预测新的药物-靶标关系具有一定效力。
2、建立了一个基于化学倾向性信息的支持向量机模型。特征向量的构建抛弃了蛋白结构信息，完全使用蛋白已知配体的化学信息。332个特征分别取自配体的指纹信息以及已知的蛋白-配体相互关系，这样构建的特征向量被我们称之为化学倾向性特征向量。该模型对于预测蛋白-配体相互作用关系显示了出色的能力，超过了化学相似性系综模型的预测结果。五倍交叉检验和独立检验都显示出很好的结果，ROC曲线下面积AUC分别达到0.9914和0.9878。随后的特征选择，初步揭示了配体-蛋白（药物-靶标）关系确立的本质联系。最后，应用该模型筛选了精神分裂症靶点DAO的抑制剂，并进行了实验。实验结果进一步显示了该模型的优势，10个预测到的药物候选物中，有7个获得文献或实验支持，并且发现了4个新的DAO抑制剂，进一步印证了基于化学倾向性的支持向量机模型对于预测药物前体和靶标具有良好的效果。
3、提出了一个新的计算方法，通过整合药物作用下的基因芯片数据，药物作用下的子网络以及现有的信号通路信息，构建了一个机器学习模型，用于预测药物组合。首先使用单独用药的基因表达数据，预测组合药物作用下的基因表达变化比率。根据用药前后的基因表达变化比率，定义现有PPI网络的权重，用jActiveModules筛选药物作用下的最优子网。最优子网中的基因被认为是药物干扰引起细胞系统响应的基因。以药物组合及单独用药下最优子网中的基因在信号通路中出现的频率构建特征向量，优化特征并建立模型。“留一法”交叉验证结果显示，ROC曲线下面积AUC的均值达到0.7941，说明该模型能够较好地实现药物组合与负样本的分类。以癌症为例的案例分析发现，预测到的前10个癌症药物组合中，有3个是数据库中已经存在的，有2个找到了文献支持，进一步说明了该模型的有效性。
Drug discovery and development have raised widespread attention in the past twodecades and the target-orienented drug pharmacology has also achived great success.Identifying therapeutic targets and seeking specific drugs for targets, which are thefocal point for pharmaceutical enterprises and laboratory research, have alreadyachieved great progress and made indelible contributions to human health. However,in recent year, new drug development rate slows down and the cost of researchcontinues to rise, mainly due to two reasons: first is that vast screening of drugcandidates in early state still relies on time and labor consuming experimental means,while in later stage the unsatisfactory efficacy or side-effects of the drug may lead tofailures; second is that as most human diseases are complex disease induced by manyfactors, and the biological system has a certain degree of redundancy and robustness,the interference on single target by single drug can not alter the system phenotype.
With the development of all kinds of omics, the accumulation of large amounts ofbiological data leads to the continuous expansion of biological database. Thedevelopment of bioinformatics and computational biology provides an effectivemeans to solve difficulties in drug development. Especially in the early stages of drugdevelopment, virtual screening method provides an efficient and high-throughputtechnique, which plays an important role in saving cost and narrowing down theresearch scope. It is at just the right time to use in silico methods for the integration ofa variety of data sources, data mining of the underlying associations, and screening ofreliable drug-target interactions and effective drug combinations.
Based on the public database resources, this paper designs different computationalmodels, and verifies their effectiveness aiming at the two hot issues that concern in the medical field, drug-target interaction and drug combination prediction. The mainresearch work of this paper includes the following three parts:
1. A chemical similarity ensemble model is established to explore the protein-ligandinteractions from public databases in a large scale. This research covers a total of53092ligand and14732human proteins: the selected proteins contains not only afew known drug targets, but also those with rich ligand information (more than5ligands each); the selection of ligands is not limited to a few commercial drugs,but contains drugs, small molecular compounds, ions et al that can be used asprotein ligands. Our reasearch has greatly enriched the application scope ofchemical similarity ensemble method. Using two different ligand fingerprintsGpiDAPH3and MACCS key, the areas under the ROC curves (AUC) achieve0.6608and0.8344respectively. It can be found that, the similarity ensemblemodel using MACCS key fingerprint still maintains a good prediction capability,showing strong extensibility. Later, the study of seeking protein targets forTraditional Chinese Medicine composition further illustrates that the chemicalsimilarity ensemble method has a certain validity to predict new drug-targetinteractions.
2. A support vector machine (SVM) model based on the chemical-protein bindingsfrom STITCH is developed. New features have been built from ligand structurespace and ligand-protein networks and then chosen as the the input parameters forSVM model.332feature vectors are constructed from both ligand fingerprint andprotein-ligand interactions, called as chemical preference feature vectors. Thismodel shows good ability in predicting protein-ligand interactions, whichoutperforms the state-of-the-art method based on ligand similarity. The resultedAUC for5-fold cross validation and independent test reaches as high as0.9914and0.9878, respectively, achiving a very high accuracy of prediction.Furthermore, in order to simplify the model,182distinct features in pairs havebeen chosen to rebuild a new model which still shows similar outcome as the one built on the whole332features. Then, this refined model is used to search for thepotential D-amino acid oxidase (DAO) inhibitors out of STITCH database andthe predicted results are finally verified by our wet experiments. Out of10candidates obtained, seven DAO inhibitors have been verified, in which four arenewly found in the present study, and one may have a new application in therapyof psychiatric disorders other than being an antineoplastic agent. Obviously, themodel in this paper possesses abilities for high-throughput new drug and targetdiscovery in a timely manner.
3. A new calculation method is proposed by integrating gene chip data andsub-network under the drug effect, as well as pathway information available, tobuild a machine learning model, for the prediction of drug combination. Firstlygene expression data of single drug is used to forecast gene expression variationratio of drug combinations. The weight of existing PPI network is definedaccording to gene expression ratios before and after the treatment, and theoptimal drug sub-network is identified by jActiveModules. Genes in the optimalsub-network is thought to be the response of cell system to drug interference. Thefrequencies of the genes in the optimal sub-network by drug combinations andsingle drug alone appearing in different pathways are adopted as the featurevectors to optimize the features and construct the model. Results of the crossvalidation indicate that mean area under the ROC curve reaches0.7941, whichindicates that this model can classify the positive and negative samples of drugcombination very well. A case study in cancer as an instance finds that, amongthe first10forecasted drug combinations, three already exist in the database andtwo others are supported in literature review, further indicating the effectivenessof the model.
引文
1. van der Horst, E., et al., A novel chemogenomics analysis of G protein-coupledreceptors (GPCRs) and their ligands: a potential strategy for receptorde-orphanization. BMC Bioinformatics,2010.11: p.316.
2. Keiser, M.J., et al., Relating protein pharmacology by ligand chemistry. NatBiotechnol,2007.25(2): p.197-206.
3. Keiser, M.J., et al., Predicting new molecular targets for known drugs. Nature,2009.462(7270): p.175-81.
4. DeGraw, A.J., et al., Prediction and evaluation of protein farnesyltransferaseinhibition by commercial drugs. J Med Chem,2010.53(6): p.2464-71.
5. Paolini, G.V., et al., Global mapping of pharmacological space. NatBiotechnol,2006.24(7): p.805-15.
6. GANELLIN, C., P. LINDBERG, and L. MITSCHER, GLOSSARY OF TERMSUSED IN MEDICINAL CHEMISTRY.
7. Sprague, P., Automated chemical hypothesis generation and databasesearching with Catalyst. Perspectives in Drug Discovery and Design,1995.3(1): p.1-20.
8. Barnum, D., et al., Identification of common functional configurations amongmolecules. J Chem Inf Comput Sci,1996.36(3): p.563-71.
9. Sprague, P.W. and R. Hoffmann, CATALYST Pharmacophore Models andTheir Utility As Queries for Searching3D Databases, in Computer-AssistedLead Finding and Optimization.2007, Verlag Helvetica Chimica Acta. p.223-240.
10. Langer, T. and R.D. Hoffmann, Pharmacophores and pharmacophoresearches.2006, Weinheim: Wiley-VCH;[Chichester: John Wiley,distributor].
11. Nicklaus, M.C., et al., HIV-1integrase pharmacophore: discovery ofinhibitors through three-dimensional database searching. J Med Chem,1997.40(6): p.920-9.
12. Koide, Y., et al., Development of novel EDG3antagonists using a3D databasesearch and their structure-activity relationships. J Med Chem,2002.45(21): p.4629-38.
13. Debnath, A.K., Generation of predictive pharmacophore models for CCR5antagonists: study with piperidine-and piperazine-based compounds as a newclass of HIV-1entry inhibitors. J Med Chem,2003.46(21): p.4501-15.
14. Kurogi, Y., et al., Discovery of novel mesangial cell proliferation inhibitorsusing a three-dimensional database searching method. J Med Chem,2001.44(14): p.2304-7.
15. Wolber, G. and T. Langer, LigandScout:3-D pharmacophores derived fromprotein-bound ligands and their use as virtual screening filters. J Chem InfModel,2005.45(1): p.160-9.
16. Rollinger, J.M., Accessing target information by virtual parallel screening-Theimpact on natural product research. Phytochemistry Letters,2009.2(2): p.53-58.
17. Rollinger, J.M., et al., In silico target fishing for rationalized ligand discoveryexemplified on constituents of Ruta graveolens. Planta Med,2009.75(3): p.195-204.
18. Sharples, D., Factors affecting the binding of tricyclic tranquillizers andantidepressants to human serum albumin. J Pharm Pharmacol,1976.28(2): p.100-5.
19. Verma, R.P. and C. Hansch, An approach toward the problem of outliers inQSAR. Bioorg Med Chem,2005.13(15): p.4597-621.
20. Polanski, J., et al., Modeling robust QSAR. J Chem Inf Model,2006.46(6): p.2310-8.
21. Kurup, A., C-QSAR: a database of18,000QSARs and associated biologicaland physical data. J Comput Aided Mol Des,2003.17(2-4): p.187-96.
22. Hansch, C., et al., Chem-bioinformatics: comparative QSAR at the interfacebetween chemistry and biology. Chemical Reviews-Columbus,2002.102(3): p.783-812.
23. Shoichet, B.K., Virtual screening of chemical libraries. Nature,2004.432(7019): p.862-5.
24. Klebe, G., Virtual ligand screening: strategies, perspectives and limitations.Drug Discov Today,2006.11(13-14): p.580-94.
25. Kitchen, D.B., et al., Docking and scoring in virtual screening for drugdiscovery: methods and applications. Nat Rev Drug Discov,2004.3(11): p.935-49.
26. Ghoshal, N., P. Manoharan, and R.S.K. Vijayan, Rationalizing fragment baseddrug discovery for BACE1: insights from FB-QSAR, FB-QSSR, multi objective(MO-QSPR) and MIF studies. Journal of Computer-Aided Molecular Design,2010.24(10): p.843-864.
27. Leach, A.R., B.K. Shoichet, and C.E. Peishoff, Prediction of protein-ligandinteractions. Docking and scoring: successes and gaps. J Med Chem,2006.49(20): p.5851-5.
28. Cheng, A.C., et al., Structure-based maximal affinity model predictssmall-molecule druggability. Nat Biotechnol,2007.25(1): p.71-5.
29. Evers, A., H. Gohlke, and G. Klebe, Ligand-supported homology modelling ofprotein binding-sites using knowledge-based potentials. J Mol Biol,2003.334(2): p.327-45.
30. Chen, Y.Z. and D.G. Zhi, Ligand-protein inverse docking and its potential usein the computer search of protein targets of a small molecule. Proteins,2001.43(2): p.217-26.
31. Vigers, G.P. and J.P. Rizzi, Multiple active site corrections for docking andvirtual screening. J Med Chem,2004.47(1): p.80-9.
32. Gao, Z., et al., PDTD: a web-accessible protein database for drug targetidentification. BMC Bioinformatics,2008.9: p.104.
33. Fradera, X. and J. Mestres, Guided docking approaches to structure-baseddesign and screening. Curr Top Med Chem,2004.4(7): p.687-700.
34. Clemente, J.C., et al., Structure of the aspartic protease plasmepsin4from themalarial parasite Plasmodium malariae bound to anallophenylnorstatine-based inhibitor. Acta Crystallogr D Biol Crystallogr,2006.62(Pt3): p.246-52.
35. Grzybowski, B.A., et al., Combinatorial computational method gives newpicomolar ligands for a known enzyme. Proc Natl Acad Sci U S A,2002.99(3):p.1270-3.
36. Bissantz, C., Conformational changes of G protein-coupled receptors duringtheir activation by agonist binding. J Recept Signal Transduct Res,2003.23(2-3): p.123-53.
37. Chen, Y.Z. and C.Y. Ung, Prediction of potential toxicity and side effectprotein targets of a small molecule by a ligand-protein inverse dockingapproach. J Mol Graph Model,2001.20(3): p.199-218.
38. Zahler, S., et al., Inverse in silico screening for identification of kinaseinhibitor targets. Chem Biol,2007.14(11): p.1207-14.
39. MacDonald, M.L., et al., Identifying off-target effects and hidden phenotypesof drugs in human cells. Nat Chem Biol,2006.2(6): p.329-37.
40. Mitchell, T.M., Machine Learning. McGraw-Hill series in computer science.1997, New York: McGraw-Hill. xvii,414p.
41. Jensen, L.J. and A. Bateman, The rise and fall of supervised machine learningtechniques. Bioinformatics,2011.27(24): p.3331-2.
42. Strombergsson, H. and G.J. Kleywegt, A chemogenomics view onprotein-ligand spaces. BMC Bioinformatics,2009.10Suppl6: p. S13.
43. Browne, R.P., P.D. McNicholas, and M.D. Sparling, Model-based learningusing a mixture of mixtures of Gaussian and uniform distributions. IEEE TransPattern Anal Mach Intell,2012.34(4): p.814-7.
44. Nidhi, et al., Prediction of biological targets for compounds usingmultiple-category Bayesian models trained on chemogenomics databases. JChem Inf Model,2006.46(3): p.1124-33.
45. Nigsch, F., et al., Computational toxicology: an overview of the sources ofdata and of modelling methods. Expert Opinion on Drug Metabolism&Toxicology,2009.5(1): p.1-14.
46. van Laarhoven, T., S.B. Nabuurs, and E. Marchiori, Gaussian interactionprofile kernels for predicting drug-target interaction. Bioinformatics,2011.27(21): p.3036-43.
47. Li, Q. and L. Lai, Prediction of potential drug targets based on simplesequence properties. BMC Bioinformatics,2007.8: p.353.
48. Yamanishi, Y., et al., Prediction of drug-target interaction networks from theintegration of chemical and genomic spaces. Bioinformatics,2008.24(13): p.i232-40.
49. Bleakley, K. and Y. Yamanishi, Supervised prediction of drug-targetinteractions using bipartite local models. Bioinformatics,2009.25(18): p.2397-403.
50. Yu, W., et al., Predicting drug-target interactions based on an improvedsemi-supervised learning approach. Drug Development Research,2011.72(2):p.219-224.
51. Zhao, S. and S. Li, Network-based relating pharmacological and genomicspaces for drug target identification. PLoS One,2010.5(7): p. e11764.
52. Wale, N. and G. Karypis, Target fishing for chemical compounds usingtarget-ligand activity data and ranking based methods. J Chem Inf Model,2009.49(10): p.2190-201.
53. Ehrman, T.M., D.J. Barlow, and P.J. Hylands, Virtual screening of Chineseherbs with random forest. Journal of Chemical Information and Modeling,2007.47(2): p.264-278.
54. Paoletta, S., et al., Screening of herbal constituents for aromatase inhibitoryactivity. Bioorganic&Medicinal Chemistry,2008.16(18): p.8466-8470.
55. Zhao, J., P. Jiang, and W.D. Zhang, Molecular networks for the study of TCMPharmacology. Briefings in Bioinformatics,2010.11(4): p.417-430.
56. Wodak, S.J., et al., Challenges and Rewards of Interaction Proteomics.Molecular&Cellular Proteomics,2009.8(1): p.3-18.
57. Hase, T., et al., Structure of protein interaction networks and their implicationson drug design. PLoS Comput Biol,2009.5(10): p. e1000550.
58. Zhu, M., et al., The analysis of the drug-targets based on the topologicalproperties in the human protein-protein interaction network. J Drug Target,2009.17(7): p.524-32.
59. Yildirim, M.A., et al., Drug-target network. Nat Biotechnol,2007.25(10): p.1119-26.
60. Mestres, J., et al., The topology of drug-target interaction networks: implicitdependence on drug properties and target families. Mol Biosyst,2009.5(9): p.1051-7.
61. Samaga, R., et al., The logic of EGFR/ErbB signaling: theoretical propertiesand analysis of high-throughput data. PLoS Comput Biol,2009.5(8): p.e1000438.
62. Lee, E., et al., The roles of APC and Axin derived from experimental andtheoretical analysis of the Wnt pathway. PLoS Biol,2003.1(1): p. E10.
63. Swameye, I., et al., Identification of nucleocytoplasmic cycling as a remotesensor in cellular signaling by databased modeling. Proc Natl Acad Sci U S A,2003.100(3): p.1028-33.
64. Zi, Z. and E. Klipp, Constraint-based modeling and kinetic analysis of theSmad dependent TGF-beta signaling pathway. PLoS One,2007.2(9): p. e936.
65. Schmierer, B., et al., Mathematical modeling identifies Smadnucleocytoplasmic shuttling as a dynamic signal-interpreting system. ProcNatl Acad Sci U S A,2008.105(18): p.6608-13.
66. Radulescu, O., et al., Robust simplifications of multiscale biochemicalnetworks. BMC Syst Biol,2008.2: p.86.
67. Chen, W.W., et al., Input-output behavior of ErbB signaling pathways asrevealed by a mass action model trained against dynamic data. Mol Syst Biol,2009.5: p.239.
68. Bluthgen, N., et al., A systems biological approach suggests thattranscriptional feedback regulation by dual-specificity phosphatase6shapesextracellular signal-related kinase activity in RAS-transformed fibroblasts.Febs J,2009.276(4): p.1024-35.
69. Borisov, N., et al., Systems-level interactions between insulin-EGF networksamplify mitogenic signaling. Mol Syst Biol,2009.5: p.256.
70. Schoeberl, B., et al., Therapeutically targeting ErbB3: a key node inligand-induced activation of the ErbB receptor-PI3K axis. Sci Signal,2009.2(77): p. ra31.
71. Sahin, O., et al., Modeling ERBB receptor-regulated G1/S transition to findnovel targets for de novo trastuzumab resistance. BMC Syst Biol,2009.3: p.1.
72. Raman, K. and N. Chandra, Flux balance analysis of biological systems:applications and challenges. Brief Bioinform,2009.10(4): p.435-49.
73. Goltsov, A., et al., Kinetic modelling of NSAID action on COX-1: focus on invitro/in vivo aspects and drug combinations. Eur J Pharm Sci,2009.36(1): p.122-36.
74. Autiero, I., S. Costantini, and G. Colonna, Modeling of the bacterialmechanism of methicillin-resistance by a systems biology approach. PLoS One,2009.4(7): p. e6226.
75. Leung, E.L., et al., Network-based drug discovery by integrating systemsbiology and computational technologies. Brief Bioinform,2012.
76. Borisy, A.A., et al., Systematic discovery of multicomponent therapeutics. ProcNatl Acad Sci U S A,2003.100(13): p.7977-82.
77. Wong, P.K., et al., Closed-loop control of cellular functions using combinatorydrugs guided by a stochastic search algorithm. Proc Natl Acad Sci U S A,2008.105(13): p.5105-10.
78. Yoon, B.J., Enhanced stochastic optimization algorithm for finding effectivemulti-target therapeutics. BMC Bioinformatics,2011.12Suppl1: p. S18.
79. Zinner, R.G., et al., Algorithmic guided screening of drug combinations ofarbitrary size for activity against cancer cells. Mol Cancer Ther,2009.8(3): p.521-32.
80. Wang, Y., et al., A novel methodology for multicomponent drug design and itsapplication in optimizing the combination of active components from Chinesemedicinal formula Shenmai. Chem Biol Drug Des,2010.75(3): p.318-24.
81. Wang, Y., X. Wang, and Y. Cheng, A computational approach to botanicaldrug design by modeling quantitative composition-activity relationship. ChemBiol Drug Des,2006.68(3): p.166-72.
82. Huang, S.S. and E. Fraenkel, Integrating proteomic, transcriptional, andinteractome data reveals hidden components of signaling and regulatorynetworks. Sci Signal,2009.2(81): p. ra40.
83. Lan, A., et al., ResponseNet: revealing signaling and regulatory networkslinking genetic and transcriptomic screening data. Nucleic Acids Res,2011.39(Web Server issue): p. W424-9.
84. Wang, L., et al., Dissection of mechanisms of Chinese medicinal formulaRealgar-Indigo naturalis as an effective treatment for promyelocytic leukemia.Proc Natl Acad Sci U S A,2008.105(12): p.4826-31.
85. Zhang, Q.Y., et al., A systems biology understanding of the synergistic effectsof arsenic sulfide and Imatinib in BCR/ABL-associated leukemia. Proc NatlAcad Sci U S A,2009.106(9): p.3378-83.
86. Li, S., B. Zhang, and N. Zhang, Network target for screening synergistic drugcombinations with application to traditional Chinese medicine. BMC SystBiol,2011.5Suppl1: p. S10.
87. Li, Q., et al., A network-based multi-target computational estimation schemefor anticoagulant activities of compounds. PLoS One,2011.6(3): p. e14774.
88. Li, S., et al., Herb network construction and co-module analysis foruncovering the combination rule of traditional Chinese herbal formulae. BMCBioinformatics,2010.11Suppl11: p. S6.
89. Sun, Y., et al., Towards a bioinformatics analysis of anti-Alzheimer's herbalmedicines from a target network perspective. Brief Bioinform,2012.
90. Wu, Z., X.M. Zhao, and L. Chen, A systems biology approach to identifyeffective cocktail drugs. BMC Syst Biol,2010.4Suppl2: p. S7.
91. Zhao, X.M., et al., Prediction of drug combinations by integrating molecularand pharmacological data. PLoS Comput Biol,2011.7(12): p. e1002323.
92. Zou, J., et al., Neighbor communities in drug combination networkscharacterize synergistic effect. Mol Biosyst,2012.8(12): p.3185-96.
93. Harel, D. and Y.A. Feldman, Algorithmics: the spirit of computing.3rd edn..3rd ed. ed.2004, Harlow: Addison-Wesley.
94. Fitzgerald, J.B., et al., Systems biology and combination therapy in the questfor clinical efficacy. Nat Chem Biol,2006.2(9): p.458-66.
95. Goldoni, M. and C. Johansson, A mathematical approach to study combinedeffects of toxicants in vitro: evaluation of the Bliss independence criterion andthe Loewe additivity model. Toxicol In Vitro,2007.21(5): p.759-69.
96. Chou, T.-C., Drug Combination Studies and Their Synergy QuantificationUsing the Chou-Talalay Method. Cancer Research,2010.70(2): p.440-446.
97. Chou, T.C., et al., Computerized quantitation of synergism and antagonism oftaxol, topotecan, and cisplatin against human teratocarcinoma cell growth: arational approach to clinical protocol design. J Natl Cancer Inst,1994.86(20):p.1517-24.
98. Chou, T.C. and P. Talalay, Quantitative analysis of dose-effect relationships:the combined effects of multiple drugs or enzyme inhibitors. Adv EnzymeRegul,1984.22: p.27-55.
99. Yan, H., et al., A formal model for analyzing drug combination effects and itsapplication in TNF-alpha-induced NFkappaB pathway. BMC Syst Biol,2010.4: p.50.
100. van Driel, M.A., et al., A text-mining analysis of the human phenome. Eur JHum Genet,2006.14(5): p.535-42.
101. Kuhn, M., et al., STITCH: interaction networks of chemicals and proteins.Nucleic Acids Res,2008.36(Database issue): p. D684-8.
102. Elsevier MDL:2440Camino Ramon, Suite300, San Ramon, CA94583;http://www.mdl.com.
103. Chen, I.J. and R.E. Hubbard, Lessons for fragment library design: analysis ofoutput from multiple screening campaigns. J Comput Aided Mol Des,2009.23(8): p.603-20.
104.(MOE), M.O.E., Chemical Computing Group Inc.1010Sherbooke St. West,Suite#910, Montreal, QC, Canada, H3A2R7.,2008.
105. Papadatos, G., How similar is similar? A study of the similarity principle usingmolecular fingerprints in the context of lead optimisation. UK QSAR&Chemoinformatics Spring Meeting.,2009.
106. Ebert, B., S. Andersen, and P. Krogsgaard-Larsen, Ketobemidone, methadoneand pethidine are non-competitive N-methyl-D-aspartate (NMDA) antagonistsin the rat cortex and spinal cord. Neurosci Lett,1995.187(3): p.165-8.
107. Rodriguez, A.M., et al., Physiological and molecular characterization ofgenetic competence in Streptococcus sanguinis. Mol Oral Microbiol,2011.26(2): p.99-116.
108. Linden, A., Measuring diagnostic and predictive accuracy in diseasemanagement: an introduction to receiver operating characteristic (ROC)analysis. J Eval Clin Pract,2006.12(2): p.132-9.
109. Chen, C.Y., TCM Database@Taiwan: the world's largest traditional Chinesemedicine database for drug screening in silico. PLoS One,2011.6(1): p.e15939.
110. Hubbard, T., et al., The Ensembl genome database project. Nucleic Acids Res,2002.30(1): p.38-41.
111. Karlin, S. and S.F. Altschul, Methods for assessing the statistical significanceof molecular sequence features by using general scoring schemes. Proc NatlAcad Sci U S A,1990.87(6): p.2264-8.
112. Chang, C.-C. and C.-J. Lin, LIBSVM: A library for support vector machines.ACM Trans. Intell. Syst. Technol.,2011.2(3): p.1-27.
113. Peng, H., F. Long, and C. Ding, Feature selection based on mutualinformation: criteria of max-dependency, max-relevance, and min-redundancy.IEEE Trans Pattern Anal Mach Intell,2005.27(8): p.1226-38.
114. Ding, C. and H. Peng, Minimum redundancy feature selection from microarraygene expression data. J Bioinform Comput Biol,2005.3(2): p.185-205.
115. Durant, J.L., et al., Reoptimization of MDL Keys for Use in Drug Discovery.Journal of Chemical Information and Computer Sciences,2002.42(6): p.1273-1280.
116. Brown, R.D. and Y.C. Martin, The Information Content of2D and3DStructural Descriptors Relevant to Ligand-Receptor Binding. Journal ofChemical Information and Computer Sciences,1997.37(1): p.1-9.
117. Bruning, J.B., et al., Coupling of receptor conformation and ligand orientationdetermine graded activity. Nat Chem Biol,2010.6(11): p.837-43.
118. Bertrand, T., et al., Structural basis for human monoglyceride lipase inhibition.J Mol Biol,2010.396(3): p.663-73.
119. Williams, M., Commentary: genome-based CNS drug discovery: D-aminoacid oxidase (DAAO) as a novel target for antipsychotic medications: progressand challenges. Biochem Pharmacol,2009.78(11): p.1360-5.
120. Lai, C.H., H.Y. Lane, and G.E. Tsai, Clinical and cerebral volumetric effects ofsodium benzoate, a D-amino acid oxidase inhibitor, in a drug-naive patientwith major depression. Biol Psychiatry,2011.71(4): p. e9-e10.
121. Shenoy, S.R. and B. Jayaram, Proteins: sequence to structure andfunction--current status. Curr Protein Pept Sci,2010.11(7): p.498-514.
122. Laskowski, R.A. and M.B. Swindells, LigPlot+: multiple ligand-proteininteraction diagrams for drug discovery. J Chem Inf Model,2011.51(10): p.2778-86.
123. Liu, Y., et al., DCDB: drug combination database. Bioinformatics,2010.26(4):p.587-8.
124. Wishart, D.S., et al., DrugBank: a knowledgebase for drugs, drug actions anddrug targets. Nucleic Acids Res,2008.36(Database issue): p. D901-6.
125. Mootha, V.K., et al., PGC-1alpha-responsive genes involved in oxidativephosphorylation are coordinately downregulated in human diabetes. NatGenet,2003.34(3): p.267-73.
126. Subramanian, A., et al., Gene set enrichment analysis: a knowledge-basedapproach for interpreting genome-wide expression profiles. Proc Natl AcadSci U S A,2005.102(43): p.15545-50.
127. Ideker, T., et al., Discovering regulatory and signalling circuits in molecularinteraction networks. Bioinformatics,2002.18Suppl1: p. S233-40.
128. Ideker, T., et al., Testing for differentially-expressed genes bymaximum-likelihood analysis of microarray data. J Comput Biol,2000.7(6): p.805-17.
129. Kendall, S.M., Stuart, A. and Ord, J.K., Kendall's Advanced Theory ofStatistics,5th edition. Oxford University Press, NY, pp.446,1987.
130. Kirkpatrick, S., C.D. Gelatt, Jr., and M.P. Vecchi, Optimization by simulatedannealing. Science,1983.220(4598): p.671-80.
131. Cline, M.S., et al., Integration of biological networks and gene expressiondata using Cytoscape. Nat Protoc,2007.2(10): p.2366-82.
132. Zhao, J., et al., In vitro combination characterization of the new anticancerplant drug beta-elemene with taxanes against human lung carcinoma. Int JOncol,2007.31(2): p.241-52.
133. Matsunaga, T., et al., Combination therapy of an anticancer drug with theFNIII14peptide of fibronectin effectively overcomes cell adhesion-mediateddrug resistance of acute myelogenous leukemia. Leukemia,2008.22(2): p.353-60.
134. Wedel, S., et al., Molecular targeting of prostate cancer cells by a triple drugcombination down-regulates integrin driven adhesion processes, delays cellcycle progression and interferes with the cdk-cyclin axis. BMC Cancer,2011.11: p.375.
135. Simpson, G.R., et al., Combination of a fusogenic glycoprotein, pro-drugactivation and oncolytic HSV as an intravesical therapy for superficialbladder cancer. Br J Cancer,2012.106(3): p.496-507.
136. Kotelnikova, E., et al., Computational approaches for drug repositioning andcombination therapy design. J Bioinform Comput Biol,2010.8(3): p.593-606.
137. Gopalan, A., et al., Eliminating drug resistant breast cancer stem-like cellswith combination of simvastatin and gamma-tocotrienol. Cancer Lett,2013.328(2): p.285-96.
138. Gioeli, D., et al., Compensatory pathways induced by MEK inhibition areeffective drug targets for combination therapy against castration-resistantprostate cancer. Mol Cancer Ther,2011.10(9): p.1581-90.
139. Bozec, A., et al., The mTOR-targeting drug temsirolimus enhances thegrowth-inhibiting effects of the cetuximab-bevacizumab-irradiationcombination on head and neck cancer xenografts. Oral Oncol,2011.47(5): p.340-4.
140. Naito, T., et al., Effects of calcineurin inhibitors on pharmacokinetics ofmycophenolic acid and its glucuronide metabolite during the maintenanceperiod following renal transplantation. Biol Pharm Bull,2006.29(2): p.275-80.
141. Fryknas, M., et al., Phenotype-based screening of mechanistically annotatedcompounds in combination with gene expression and pathway analysisidentifies candidate drug targets in a human squamous carcinoma cell model.J Biomol Screen,2006.11(5): p.457-68.
142. Siddiqui-Jain, A., et al., CK2inhibitor CX-4945suppresses DNA repairresponse triggered by DNA-targeted anticancer drugs and augments efficacy:mechanistic rationale for drug combination therapy. Mol Cancer Ther,2012.11(4): p.994-1005.
143. Cheok, C.F., A. Dey, and D.P. Lane, Cyclin-dependent kinase inhibitorssensitize tumor cells to nutlin-induced apoptosis: a potent drug combination.Mol Cancer Res,2007.5(11): p.1133-45.
144. Siefker-Radtke, A.O., et al., Phase II clinical trial of neoadjuvant alternatingdoublet chemotherapy with ifosfamide/doxorubicin and etoposide/cisplatin insmall-cell urothelial cancer. J Clin Oncol,2009.27(16): p.2592-7.
145. Hanna, R.K., et al., Metformin potentiates the effects of paclitaxel inendometrial cancer cells through inhibition of cell proliferation andmodulation of the mTOR pathway. Gynecol Oncol.125(2): p.458-69.
146. Tseng, S.C., et al., Metformin-mediated downregulation of p38
mitogen-activated protein kinase-dependent excision repair
cross-complementing1decreases DNA repair capacity and sensitizes human
lung cancer cells to paclitaxel. Biochem Pharmacol,2013.85(4): p.583-94.
2. Keiser, M.J., et al., Relating protein pharmacology by ligand chemistry. NatBiotechnol,2007.25(2): p.197-206.
3. Keiser, M.J., et al., Predicting new molecular targets for known drugs. Nature,2009.462(7270): p.175-81.
4. DeGraw, A.J., et al., Prediction and evaluation of protein farnesyltransferaseinhibition by commercial drugs. J Med Chem,2010.53(6): p.2464-71.
5. Paolini, G.V., et al., Global mapping of pharmacological space. NatBiotechnol,2006.24(7): p.805-15.
6. GANELLIN, C., P. LINDBERG, and L. MITSCHER, GLOSSARY OF TERMSUSED IN MEDICINAL CHEMISTRY.
7. Sprague, P., Automated chemical hypothesis generation and databasesearching with Catalyst. Perspectives in Drug Discovery and Design,1995.3(1): p.1-20.
8. Barnum, D., et al., Identification of common functional configurations amongmolecules. J Chem Inf Comput Sci,1996.36(3): p.563-71.
9. Sprague, P.W. and R. Hoffmann, CATALYST Pharmacophore Models andTheir Utility As Queries for Searching3D Databases, in Computer-AssistedLead Finding and Optimization.2007, Verlag Helvetica Chimica Acta. p.223-240.
10. Langer, T. and R.D. Hoffmann, Pharmacophores and pharmacophoresearches.2006, Weinheim: Wiley-VCH;[Chichester: John Wiley,distributor].
11. Nicklaus, M.C., et al., HIV-1integrase pharmacophore: discovery ofinhibitors through three-dimensional database searching. J Med Chem,1997.40(6): p.920-9.
12. Koide, Y., et al., Development of novel EDG3antagonists using a3D databasesearch and their structure-activity relationships. J Med Chem,2002.45(21): p.4629-38.
13. Debnath, A.K., Generation of predictive pharmacophore models for CCR5antagonists: study with piperidine-and piperazine-based compounds as a newclass of HIV-1entry inhibitors. J Med Chem,2003.46(21): p.4501-15.
14. Kurogi, Y., et al., Discovery of novel mesangial cell proliferation inhibitorsusing a three-dimensional database searching method. J Med Chem,2001.44(14): p.2304-7.
15. Wolber, G. and T. Langer, LigandScout:3-D pharmacophores derived fromprotein-bound ligands and their use as virtual screening filters. J Chem InfModel,2005.45(1): p.160-9.
16. Rollinger, J.M., Accessing target information by virtual parallel screening-Theimpact on natural product research. Phytochemistry Letters,2009.2(2): p.53-58.
17. Rollinger, J.M., et al., In silico target fishing for rationalized ligand discoveryexemplified on constituents of Ruta graveolens. Planta Med,2009.75(3): p.195-204.
18. Sharples, D., Factors affecting the binding of tricyclic tranquillizers andantidepressants to human serum albumin. J Pharm Pharmacol,1976.28(2): p.100-5.
19. Verma, R.P. and C. Hansch, An approach toward the problem of outliers inQSAR. Bioorg Med Chem,2005.13(15): p.4597-621.
20. Polanski, J., et al., Modeling robust QSAR. J Chem Inf Model,2006.46(6): p.2310-8.
21. Kurup, A., C-QSAR: a database of18,000QSARs and associated biologicaland physical data. J Comput Aided Mol Des,2003.17(2-4): p.187-96.
22. Hansch, C., et al., Chem-bioinformatics: comparative QSAR at the interfacebetween chemistry and biology. Chemical Reviews-Columbus,2002.102(3): p.783-812.
23. Shoichet, B.K., Virtual screening of chemical libraries. Nature,2004.432(7019): p.862-5.
24. Klebe, G., Virtual ligand screening: strategies, perspectives and limitations.Drug Discov Today,2006.11(13-14): p.580-94.
25. Kitchen, D.B., et al., Docking and scoring in virtual screening for drugdiscovery: methods and applications. Nat Rev Drug Discov,2004.3(11): p.935-49.
26. Ghoshal, N., P. Manoharan, and R.S.K. Vijayan, Rationalizing fragment baseddrug discovery for BACE1: insights from FB-QSAR, FB-QSSR, multi objective(MO-QSPR) and MIF studies. Journal of Computer-Aided Molecular Design,2010.24(10): p.843-864.
27. Leach, A.R., B.K. Shoichet, and C.E. Peishoff, Prediction of protein-ligandinteractions. Docking and scoring: successes and gaps. J Med Chem,2006.49(20): p.5851-5.
28. Cheng, A.C., et al., Structure-based maximal affinity model predictssmall-molecule druggability. Nat Biotechnol,2007.25(1): p.71-5.
29. Evers, A., H. Gohlke, and G. Klebe, Ligand-supported homology modelling ofprotein binding-sites using knowledge-based potentials. J Mol Biol,2003.334(2): p.327-45.
30. Chen, Y.Z. and D.G. Zhi, Ligand-protein inverse docking and its potential usein the computer search of protein targets of a small molecule. Proteins,2001.43(2): p.217-26.
31. Vigers, G.P. and J.P. Rizzi, Multiple active site corrections for docking andvirtual screening. J Med Chem,2004.47(1): p.80-9.
32. Gao, Z., et al., PDTD: a web-accessible protein database for drug targetidentification. BMC Bioinformatics,2008.9: p.104.
33. Fradera, X. and J. Mestres, Guided docking approaches to structure-baseddesign and screening. Curr Top Med Chem,2004.4(7): p.687-700.
34. Clemente, J.C., et al., Structure of the aspartic protease plasmepsin4from themalarial parasite Plasmodium malariae bound to anallophenylnorstatine-based inhibitor. Acta Crystallogr D Biol Crystallogr,2006.62(Pt3): p.246-52.
35. Grzybowski, B.A., et al., Combinatorial computational method gives newpicomolar ligands for a known enzyme. Proc Natl Acad Sci U S A,2002.99(3):p.1270-3.
36. Bissantz, C., Conformational changes of G protein-coupled receptors duringtheir activation by agonist binding. J Recept Signal Transduct Res,2003.23(2-3): p.123-53.
37. Chen, Y.Z. and C.Y. Ung, Prediction of potential toxicity and side effectprotein targets of a small molecule by a ligand-protein inverse dockingapproach. J Mol Graph Model,2001.20(3): p.199-218.
38. Zahler, S., et al., Inverse in silico screening for identification of kinaseinhibitor targets. Chem Biol,2007.14(11): p.1207-14.
39. MacDonald, M.L., et al., Identifying off-target effects and hidden phenotypesof drugs in human cells. Nat Chem Biol,2006.2(6): p.329-37.
40. Mitchell, T.M., Machine Learning. McGraw-Hill series in computer science.1997, New York: McGraw-Hill. xvii,414p.
41. Jensen, L.J. and A. Bateman, The rise and fall of supervised machine learningtechniques. Bioinformatics,2011.27(24): p.3331-2.
42. Strombergsson, H. and G.J. Kleywegt, A chemogenomics view onprotein-ligand spaces. BMC Bioinformatics,2009.10Suppl6: p. S13.
43. Browne, R.P., P.D. McNicholas, and M.D. Sparling, Model-based learningusing a mixture of mixtures of Gaussian and uniform distributions. IEEE TransPattern Anal Mach Intell,2012.34(4): p.814-7.
44. Nidhi, et al., Prediction of biological targets for compounds usingmultiple-category Bayesian models trained on chemogenomics databases. JChem Inf Model,2006.46(3): p.1124-33.
45. Nigsch, F., et al., Computational toxicology: an overview of the sources ofdata and of modelling methods. Expert Opinion on Drug Metabolism&Toxicology,2009.5(1): p.1-14.
46. van Laarhoven, T., S.B. Nabuurs, and E. Marchiori, Gaussian interactionprofile kernels for predicting drug-target interaction. Bioinformatics,2011.27(21): p.3036-43.
47. Li, Q. and L. Lai, Prediction of potential drug targets based on simplesequence properties. BMC Bioinformatics,2007.8: p.353.
48. Yamanishi, Y., et al., Prediction of drug-target interaction networks from theintegration of chemical and genomic spaces. Bioinformatics,2008.24(13): p.i232-40.
49. Bleakley, K. and Y. Yamanishi, Supervised prediction of drug-targetinteractions using bipartite local models. Bioinformatics,2009.25(18): p.2397-403.
50. Yu, W., et al., Predicting drug-target interactions based on an improvedsemi-supervised learning approach. Drug Development Research,2011.72(2):p.219-224.
51. Zhao, S. and S. Li, Network-based relating pharmacological and genomicspaces for drug target identification. PLoS One,2010.5(7): p. e11764.
52. Wale, N. and G. Karypis, Target fishing for chemical compounds usingtarget-ligand activity data and ranking based methods. J Chem Inf Model,2009.49(10): p.2190-201.
53. Ehrman, T.M., D.J. Barlow, and P.J. Hylands, Virtual screening of Chineseherbs with random forest. Journal of Chemical Information and Modeling,2007.47(2): p.264-278.
54. Paoletta, S., et al., Screening of herbal constituents for aromatase inhibitoryactivity. Bioorganic&Medicinal Chemistry,2008.16(18): p.8466-8470.
55. Zhao, J., P. Jiang, and W.D. Zhang, Molecular networks for the study of TCMPharmacology. Briefings in Bioinformatics,2010.11(4): p.417-430.
56. Wodak, S.J., et al., Challenges and Rewards of Interaction Proteomics.Molecular&Cellular Proteomics,2009.8(1): p.3-18.
57. Hase, T., et al., Structure of protein interaction networks and their implicationson drug design. PLoS Comput Biol,2009.5(10): p. e1000550.
58. Zhu, M., et al., The analysis of the drug-targets based on the topologicalproperties in the human protein-protein interaction network. J Drug Target,2009.17(7): p.524-32.
59. Yildirim, M.A., et al., Drug-target network. Nat Biotechnol,2007.25(10): p.1119-26.
60. Mestres, J., et al., The topology of drug-target interaction networks: implicitdependence on drug properties and target families. Mol Biosyst,2009.5(9): p.1051-7.
61. Samaga, R., et al., The logic of EGFR/ErbB signaling: theoretical propertiesand analysis of high-throughput data. PLoS Comput Biol,2009.5(8): p.e1000438.
62. Lee, E., et al., The roles of APC and Axin derived from experimental andtheoretical analysis of the Wnt pathway. PLoS Biol,2003.1(1): p. E10.
63. Swameye, I., et al., Identification of nucleocytoplasmic cycling as a remotesensor in cellular signaling by databased modeling. Proc Natl Acad Sci U S A,2003.100(3): p.1028-33.
64. Zi, Z. and E. Klipp, Constraint-based modeling and kinetic analysis of theSmad dependent TGF-beta signaling pathway. PLoS One,2007.2(9): p. e936.
65. Schmierer, B., et al., Mathematical modeling identifies Smadnucleocytoplasmic shuttling as a dynamic signal-interpreting system. ProcNatl Acad Sci U S A,2008.105(18): p.6608-13.
66. Radulescu, O., et al., Robust simplifications of multiscale biochemicalnetworks. BMC Syst Biol,2008.2: p.86.
67. Chen, W.W., et al., Input-output behavior of ErbB signaling pathways asrevealed by a mass action model trained against dynamic data. Mol Syst Biol,2009.5: p.239.
68. Bluthgen, N., et al., A systems biological approach suggests thattranscriptional feedback regulation by dual-specificity phosphatase6shapesextracellular signal-related kinase activity in RAS-transformed fibroblasts.Febs J,2009.276(4): p.1024-35.
69. Borisov, N., et al., Systems-level interactions between insulin-EGF networksamplify mitogenic signaling. Mol Syst Biol,2009.5: p.256.
70. Schoeberl, B., et al., Therapeutically targeting ErbB3: a key node inligand-induced activation of the ErbB receptor-PI3K axis. Sci Signal,2009.2(77): p. ra31.
71. Sahin, O., et al., Modeling ERBB receptor-regulated G1/S transition to findnovel targets for de novo trastuzumab resistance. BMC Syst Biol,2009.3: p.1.
72. Raman, K. and N. Chandra, Flux balance analysis of biological systems:applications and challenges. Brief Bioinform,2009.10(4): p.435-49.
73. Goltsov, A., et al., Kinetic modelling of NSAID action on COX-1: focus on invitro/in vivo aspects and drug combinations. Eur J Pharm Sci,2009.36(1): p.122-36.
74. Autiero, I., S. Costantini, and G. Colonna, Modeling of the bacterialmechanism of methicillin-resistance by a systems biology approach. PLoS One,2009.4(7): p. e6226.
75. Leung, E.L., et al., Network-based drug discovery by integrating systemsbiology and computational technologies. Brief Bioinform,2012.
76. Borisy, A.A., et al., Systematic discovery of multicomponent therapeutics. ProcNatl Acad Sci U S A,2003.100(13): p.7977-82.
77. Wong, P.K., et al., Closed-loop control of cellular functions using combinatorydrugs guided by a stochastic search algorithm. Proc Natl Acad Sci U S A,2008.105(13): p.5105-10.
78. Yoon, B.J., Enhanced stochastic optimization algorithm for finding effectivemulti-target therapeutics. BMC Bioinformatics,2011.12Suppl1: p. S18.
79. Zinner, R.G., et al., Algorithmic guided screening of drug combinations ofarbitrary size for activity against cancer cells. Mol Cancer Ther,2009.8(3): p.521-32.
80. Wang, Y., et al., A novel methodology for multicomponent drug design and itsapplication in optimizing the combination of active components from Chinesemedicinal formula Shenmai. Chem Biol Drug Des,2010.75(3): p.318-24.
81. Wang, Y., X. Wang, and Y. Cheng, A computational approach to botanicaldrug design by modeling quantitative composition-activity relationship. ChemBiol Drug Des,2006.68(3): p.166-72.
82. Huang, S.S. and E. Fraenkel, Integrating proteomic, transcriptional, andinteractome data reveals hidden components of signaling and regulatorynetworks. Sci Signal,2009.2(81): p. ra40.
83. Lan, A., et al., ResponseNet: revealing signaling and regulatory networkslinking genetic and transcriptomic screening data. Nucleic Acids Res,2011.39(Web Server issue): p. W424-9.
84. Wang, L., et al., Dissection of mechanisms of Chinese medicinal formulaRealgar-Indigo naturalis as an effective treatment for promyelocytic leukemia.Proc Natl Acad Sci U S A,2008.105(12): p.4826-31.
85. Zhang, Q.Y., et al., A systems biology understanding of the synergistic effectsof arsenic sulfide and Imatinib in BCR/ABL-associated leukemia. Proc NatlAcad Sci U S A,2009.106(9): p.3378-83.
86. Li, S., B. Zhang, and N. Zhang, Network target for screening synergistic drugcombinations with application to traditional Chinese medicine. BMC SystBiol,2011.5Suppl1: p. S10.
87. Li, Q., et al., A network-based multi-target computational estimation schemefor anticoagulant activities of compounds. PLoS One,2011.6(3): p. e14774.
88. Li, S., et al., Herb network construction and co-module analysis foruncovering the combination rule of traditional Chinese herbal formulae. BMCBioinformatics,2010.11Suppl11: p. S6.
89. Sun, Y., et al., Towards a bioinformatics analysis of anti-Alzheimer's herbalmedicines from a target network perspective. Brief Bioinform,2012.
90. Wu, Z., X.M. Zhao, and L. Chen, A systems biology approach to identifyeffective cocktail drugs. BMC Syst Biol,2010.4Suppl2: p. S7.
91. Zhao, X.M., et al., Prediction of drug combinations by integrating molecularand pharmacological data. PLoS Comput Biol,2011.7(12): p. e1002323.
92. Zou, J., et al., Neighbor communities in drug combination networkscharacterize synergistic effect. Mol Biosyst,2012.8(12): p.3185-96.
93. Harel, D. and Y.A. Feldman, Algorithmics: the spirit of computing.3rd edn..3rd ed. ed.2004, Harlow: Addison-Wesley.
94. Fitzgerald, J.B., et al., Systems biology and combination therapy in the questfor clinical efficacy. Nat Chem Biol,2006.2(9): p.458-66.
95. Goldoni, M. and C. Johansson, A mathematical approach to study combinedeffects of toxicants in vitro: evaluation of the Bliss independence criterion andthe Loewe additivity model. Toxicol In Vitro,2007.21(5): p.759-69.
96. Chou, T.-C., Drug Combination Studies and Their Synergy QuantificationUsing the Chou-Talalay Method. Cancer Research,2010.70(2): p.440-446.
97. Chou, T.C., et al., Computerized quantitation of synergism and antagonism oftaxol, topotecan, and cisplatin against human teratocarcinoma cell growth: arational approach to clinical protocol design. J Natl Cancer Inst,1994.86(20):p.1517-24.
98. Chou, T.C. and P. Talalay, Quantitative analysis of dose-effect relationships:the combined effects of multiple drugs or enzyme inhibitors. Adv EnzymeRegul,1984.22: p.27-55.
99. Yan, H., et al., A formal model for analyzing drug combination effects and itsapplication in TNF-alpha-induced NFkappaB pathway. BMC Syst Biol,2010.4: p.50.
100. van Driel, M.A., et al., A text-mining analysis of the human phenome. Eur JHum Genet,2006.14(5): p.535-42.
101. Kuhn, M., et al., STITCH: interaction networks of chemicals and proteins.Nucleic Acids Res,2008.36(Database issue): p. D684-8.
102. Elsevier MDL:2440Camino Ramon, Suite300, San Ramon, CA94583;http://www.mdl.com.
103. Chen, I.J. and R.E. Hubbard, Lessons for fragment library design: analysis ofoutput from multiple screening campaigns. J Comput Aided Mol Des,2009.23(8): p.603-20.
104.(MOE), M.O.E., Chemical Computing Group Inc.1010Sherbooke St. West,Suite#910, Montreal, QC, Canada, H3A2R7.,2008.
105. Papadatos, G., How similar is similar? A study of the similarity principle usingmolecular fingerprints in the context of lead optimisation. UK QSAR&Chemoinformatics Spring Meeting.,2009.
106. Ebert, B., S. Andersen, and P. Krogsgaard-Larsen, Ketobemidone, methadoneand pethidine are non-competitive N-methyl-D-aspartate (NMDA) antagonistsin the rat cortex and spinal cord. Neurosci Lett,1995.187(3): p.165-8.
107. Rodriguez, A.M., et al., Physiological and molecular characterization ofgenetic competence in Streptococcus sanguinis. Mol Oral Microbiol,2011.26(2): p.99-116.
108. Linden, A., Measuring diagnostic and predictive accuracy in diseasemanagement: an introduction to receiver operating characteristic (ROC)analysis. J Eval Clin Pract,2006.12(2): p.132-9.
109. Chen, C.Y., TCM Database@Taiwan: the world's largest traditional Chinesemedicine database for drug screening in silico. PLoS One,2011.6(1): p.e15939.
110. Hubbard, T., et al., The Ensembl genome database project. Nucleic Acids Res,2002.30(1): p.38-41.
111. Karlin, S. and S.F. Altschul, Methods for assessing the statistical significanceof molecular sequence features by using general scoring schemes. Proc NatlAcad Sci U S A,1990.87(6): p.2264-8.
112. Chang, C.-C. and C.-J. Lin, LIBSVM: A library for support vector machines.ACM Trans. Intell. Syst. Technol.,2011.2(3): p.1-27.
113. Peng, H., F. Long, and C. Ding, Feature selection based on mutualinformation: criteria of max-dependency, max-relevance, and min-redundancy.IEEE Trans Pattern Anal Mach Intell,2005.27(8): p.1226-38.
114. Ding, C. and H. Peng, Minimum redundancy feature selection from microarraygene expression data. J Bioinform Comput Biol,2005.3(2): p.185-205.
115. Durant, J.L., et al., Reoptimization of MDL Keys for Use in Drug Discovery.Journal of Chemical Information and Computer Sciences,2002.42(6): p.1273-1280.
116. Brown, R.D. and Y.C. Martin, The Information Content of2D and3DStructural Descriptors Relevant to Ligand-Receptor Binding. Journal ofChemical Information and Computer Sciences,1997.37(1): p.1-9.
117. Bruning, J.B., et al., Coupling of receptor conformation and ligand orientationdetermine graded activity. Nat Chem Biol,2010.6(11): p.837-43.
118. Bertrand, T., et al., Structural basis for human monoglyceride lipase inhibition.J Mol Biol,2010.396(3): p.663-73.
119. Williams, M., Commentary: genome-based CNS drug discovery: D-aminoacid oxidase (DAAO) as a novel target for antipsychotic medications: progressand challenges. Biochem Pharmacol,2009.78(11): p.1360-5.
120. Lai, C.H., H.Y. Lane, and G.E. Tsai, Clinical and cerebral volumetric effects ofsodium benzoate, a D-amino acid oxidase inhibitor, in a drug-naive patientwith major depression. Biol Psychiatry,2011.71(4): p. e9-e10.
121. Shenoy, S.R. and B. Jayaram, Proteins: sequence to structure andfunction--current status. Curr Protein Pept Sci,2010.11(7): p.498-514.
122. Laskowski, R.A. and M.B. Swindells, LigPlot+: multiple ligand-proteininteraction diagrams for drug discovery. J Chem Inf Model,2011.51(10): p.2778-86.
123. Liu, Y., et al., DCDB: drug combination database. Bioinformatics,2010.26(4):p.587-8.
124. Wishart, D.S., et al., DrugBank: a knowledgebase for drugs, drug actions anddrug targets. Nucleic Acids Res,2008.36(Database issue): p. D901-6.
125. Mootha, V.K., et al., PGC-1alpha-responsive genes involved in oxidativephosphorylation are coordinately downregulated in human diabetes. NatGenet,2003.34(3): p.267-73.
126. Subramanian, A., et al., Gene set enrichment analysis: a knowledge-basedapproach for interpreting genome-wide expression profiles. Proc Natl AcadSci U S A,2005.102(43): p.15545-50.
127. Ideker, T., et al., Discovering regulatory and signalling circuits in molecularinteraction networks. Bioinformatics,2002.18Suppl1: p. S233-40.
128. Ideker, T., et al., Testing for differentially-expressed genes bymaximum-likelihood analysis of microarray data. J Comput Biol,2000.7(6): p.805-17.
129. Kendall, S.M., Stuart, A. and Ord, J.K., Kendall's Advanced Theory ofStatistics,5th edition. Oxford University Press, NY, pp.446,1987.
130. Kirkpatrick, S., C.D. Gelatt, Jr., and M.P. Vecchi, Optimization by simulatedannealing. Science,1983.220(4598): p.671-80.
131. Cline, M.S., et al., Integration of biological networks and gene expressiondata using Cytoscape. Nat Protoc,2007.2(10): p.2366-82.
132. Zhao, J., et al., In vitro combination characterization of the new anticancerplant drug beta-elemene with taxanes against human lung carcinoma. Int JOncol,2007.31(2): p.241-52.
133. Matsunaga, T., et al., Combination therapy of an anticancer drug with theFNIII14peptide of fibronectin effectively overcomes cell adhesion-mediateddrug resistance of acute myelogenous leukemia. Leukemia,2008.22(2): p.353-60.
134. Wedel, S., et al., Molecular targeting of prostate cancer cells by a triple drugcombination down-regulates integrin driven adhesion processes, delays cellcycle progression and interferes with the cdk-cyclin axis. BMC Cancer,2011.11: p.375.
135. Simpson, G.R., et al., Combination of a fusogenic glycoprotein, pro-drugactivation and oncolytic HSV as an intravesical therapy for superficialbladder cancer. Br J Cancer,2012.106(3): p.496-507.
136. Kotelnikova, E., et al., Computational approaches for drug repositioning andcombination therapy design. J Bioinform Comput Biol,2010.8(3): p.593-606.
137. Gopalan, A., et al., Eliminating drug resistant breast cancer stem-like cellswith combination of simvastatin and gamma-tocotrienol. Cancer Lett,2013.328(2): p.285-96.
138. Gioeli, D., et al., Compensatory pathways induced by MEK inhibition areeffective drug targets for combination therapy against castration-resistantprostate cancer. Mol Cancer Ther,2011.10(9): p.1581-90.
139. Bozec, A., et al., The mTOR-targeting drug temsirolimus enhances thegrowth-inhibiting effects of the cetuximab-bevacizumab-irradiationcombination on head and neck cancer xenografts. Oral Oncol,2011.47(5): p.340-4.
140. Naito, T., et al., Effects of calcineurin inhibitors on pharmacokinetics ofmycophenolic acid and its glucuronide metabolite during the maintenanceperiod following renal transplantation. Biol Pharm Bull,2006.29(2): p.275-80.
141. Fryknas, M., et al., Phenotype-based screening of mechanistically annotatedcompounds in combination with gene expression and pathway analysisidentifies candidate drug targets in a human squamous carcinoma cell model.J Biomol Screen,2006.11(5): p.457-68.
142. Siddiqui-Jain, A., et al., CK2inhibitor CX-4945suppresses DNA repairresponse triggered by DNA-targeted anticancer drugs and augments efficacy:mechanistic rationale for drug combination therapy. Mol Cancer Ther,2012.11(4): p.994-1005.
143. Cheok, C.F., A. Dey, and D.P. Lane, Cyclin-dependent kinase inhibitorssensitize tumor cells to nutlin-induced apoptosis: a potent drug combination.Mol Cancer Res,2007.5(11): p.1133-45.
144. Siefker-Radtke, A.O., et al., Phase II clinical trial of neoadjuvant alternatingdoublet chemotherapy with ifosfamide/doxorubicin and etoposide/cisplatin insmall-cell urothelial cancer. J Clin Oncol,2009.27(16): p.2592-7.
145. Hanna, R.K., et al., Metformin potentiates the effects of paclitaxel inendometrial cancer cells through inhibition of cell proliferation andmodulation of the mTOR pathway. Gynecol Oncol.125(2): p.458-69.
146. Tseng, S.C., et al., Metformin-mediated downregulation of p38
mitogen-activated protein kinase-dependent excision repair
cross-complementing1decreases DNA repair capacity and sensitizes human
lung cancer cells to paclitaxel. Biochem Pharmacol,2013.85(4): p.583-94.