Skip to main content
SpringerLink
Log in

Drug Design with Artificial Neural Networks

  • Reference work entry
Encyclopedia of Complexity and Systems Science

Definition of the Subject

The fundamental hypothesis of the structure‐property models is that thestructural features of molecules determine the physical, chemical and biological properties of chemical compounds. The first studies that usestructure‐activity relationships to explain the biological properties of sets of compounds were published by Kopp [74], Crum-Brown and Frazer [18], Meyer [88], and Overton [97]. Modernstructure‐activity relationships (SAR) and quantitativestructure‐activity relationships (QSAR) models are based on theHansch model that predicts a biological property as a statistical correlation with steric, electronic, and hydrophobicindices [27,35,36,37]. The Hansch model shaped the general scene ofstructure‐activity correlations, and almost all subsequent SAR and QSAR models are variations that extend the Hansch model with novel classes ofdescriptors or with more powerful statistical models, such as partial least squares (PLS), artificial neural networks (ANN),...

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 3,499.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 549.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Abbreviations

Artificial neuron:

An artificial neuron is a mathematical function that simulates in a simplified form the functions of biological neurons. Usually, an artificial neuron has four computational functions, namely receives signals through input connections from other neurons or from the environment, sums the input signals, applies a nonlinear functions (transfer function or activation function) to the sum, and sends the result to other neurons or as output from the neural network.

Counterpropagation neural network:

The counterpropagation neural network is a hybrid network that consists of a self‐organizing map as the hidden layer and an output layer that has as output a computed value for the modeled property. The network implements a supervised learning algorithm that converges to a unique solution.

Multilayer feedforward artificial neural network:

A multilayer feedforward (MLF) artificial neural network consists of artificial neurons organized in layers. The MLF network has an input layer that receives the structural descriptors for each molecule, an output layer that provides one or more computed properties, and one or more hidden layers situated between the input and the output layers. Each neuron in a hidden layer receives signals from neurons in the preceding layer and sends signals to the neurons in the next layer.

Perceptron:

A perceptron is a linear classifier that consists of a layer of input neurons and an output neuron. Each connection between an input neuron and the output neuron has a weight. Depending on the sum of the signals received by the output neuron, its output is +1 or −1.

Quantitative structure‐activity relationships:

Quantitative structure‐activity relationships (QSAR) represent regression models that define quantitative correlations between the chemical structure of molecules and their physical properties (boiling point, melting point, aqueous solubility), chemical properties and reactivities (chromatographic retention, reaction rate), or biological activities (cell growth inhibition, enzyme inhibition, lethal dose). The fundamental hypotheses of QSAR are that similar chemicals have similar properties, and that small structural changes result in small changes in property values. The general form of a QSAR equation is \( { P(i)=f(\mathbf{SD}_{i}) } \), where P(i) is a physical, chemical, or biological property of compound \( { i, \mathbf{SD}_{i} } \) is a vector of structural descriptors of i, and f is a mathematical function such as linear regression, partial least squares, artificial neural networks, or support vector machines. A QSAR model for a property P is based on a dataset of chemical compounds with known values for the property P, and a matrix of structural descriptors computed for all chemicals. The learning (training) of the QSAR model is the process of determining the optimum parameters of the regression function f. After the training phase, a QSAR model may be used to predict the property P for novel compounds that are not present in the learning set of molecules.

Radial basis function network:

The radial basis function (RBF) neural network has three layers, namely an input layer, a hidden layer with a nonlinear RBF activation function and a linear output layer.

Self‐organizing map:

A self‐organizing map (SOM) is an artificial neural network that uses an unsupervised learning algorithm to project a high dimensional input space into a two dimensional space called a map. The topology of the input space is preserved in SOM, and points that are close to each other in the SOM grid correspond to input vectors that are close to each other in the input space. A SOM consists of neurons arranged usually in a rectangular or hexagonal grid. Each neuron has a position on the map and a weight vector of the same dimension as the input vectors.

Structural descriptor:

A structural descriptor (SD) is a numerical value computed from the chemical structure of a molecule, which is invariant to the numbering of the atoms in the molecule. Structural descriptors may be classified as constitutional (counts of molecular fragments, such as rings, functional groups, or atom pairs), topological indices (computed from the molecular graph), geometrical (volume, surface, charged‐surface), quantum (atomic charges, energies of molecular orbitals), and molecular field (such as those used in CoMFA, CoMSIA, or CoRSA).

Structure–activity relationships:

Structure–activity relationships (SAR) represent classification models that can discriminate between sets of chemicals that belong to different classes of biological activities, usually active/inactive towards a certain biological receptor. The general form of a SAR equation is \( { C(i) = f(\mathbf{SD}_{i}) } \), where C(i) is the activity class of compound i (active/inactive, inhibitor/non‐inhibitor, ligand/non‐ligand), \( { \mathbf{SD}_{i} } \) is a vector of structural descriptors of i, and f is a classification function such as k‑nearest neighbors, linear discriminant analysis, random trees, random forests, Bayesian networks, artificial neural networks, or support vector machines.

Bibliography

  1. Adams CP, Brantner VV (2006) Estimating the cost of new drug development: is itreally 802 million dollars? Health Aff 25:420–428

    Google Scholar 

  2. Agrafiotis DK, Cedeño W (2002) Feature selection for structure‐activitycorrelation using binary particle swarms. J Med Chem 45:1098–1107

    Google Scholar 

  3. Anzali S, Gasteiger J, Holzgrabe U, Polanski J, Sadowski J, Teckentrup A,Wagener M (1998) The use of self‐organizing neural networks in drug design. Perspect Drug Discov Design9–11:273–299

    Google Scholar 

  4. Balaban AT, Ivanciuc O (1999) Historical development of topological indices. In:Devillers J, Balaban AT (eds) Topological Indices and Related Descriptors in QSAR and QSPR. Gordon and Breach Science Publishers, Amsterdam,pp 21–57

    Google Scholar 

  5. Baldi P, Pollastri G (2004) The principled design of large-scale recursiveneural network architectures‐DAG-RNNs and the protein structure prediction problem. J Mach Learn Res 4:575–602

    MATH  Google Scholar 

  6. Basak SC, Grunwald GD, Host GE, Niemi GJ, Bradbury SP (1998) A comparativestudy of molecular similarity, statistical, and neural methods for predicting toxic modes of action. Environ Toxicol Chem17:1056–1064

    Google Scholar 

  7. Baskin II, Palyulin VA, Zefirov NS (1997) A neural device for searchingdirect correlations between structures and properties of chemical compounds. J Chem Inf Comput Sci 37:715–721

    Google Scholar 

  8. Bernazzani L, Duce C, Micheli A, Mollica V, Sperduti A, Starita A, Tiné MR(2006) Predicting physical‐chemical properties of compounds from molecular structures by recursive neural networks. J Chem Inf Model46:2030–2042

    Google Scholar 

  9. Berndt ER, Gottschalk AHB, Strobeck MW (2005) Opportunities for improving thedrug development process: Results from a survey of industry and the FDA. National Bureau of Economic Research Workshop on Innovation Policy and theEconomy, NBER Working Paper No 11425, Washington, DC

    Google Scholar 

  10. Bishop CM (1996) Neural Networks for Pattern Recognition. Oxford UniversityPress, Oxford, 504 pp

    MATH  Google Scholar 

  11. Boiani M, Cerecetto H, M González, Gasteiger J (2008) Modelinganti‐Trypanosoma cruzi activity of N‑oxide containing heterocycles, J Chem Inf Model48:213–219

    Google Scholar 

  12. Bonchev D (1983) Information Theoretic Indices for Characterization ofChemical Structure. Research Studies Press, Chichester

    Google Scholar 

  13. Bonchev D, Rouvray DH (eds) (1991) Chemical Graph Theory. Introduction andFundamentals. Abacus Press/Gordon & Breach Science Publishers, New York

    MATH  Google Scholar 

  14. Bruneau P, McElroy NR (2006) logD \( { _{7.4} } \)Modeling using Bayesian regularized neural networks. Assessment and correction of the errors of prediction. J Chem Inf Model46:1379–1387

    Google Scholar 

  15. Bulsari AB (1995) Neural Networks for Chemical Engineers. Elsevier, Amsterdam,609 pp

    Google Scholar 

  16. Caballero J, Tundidor‐Camba A, Fernández M (2007) Modeling of theinhibition constant (K i ) of some cruzain ketone‐basedinhibitors using 2D spatial autocorrelation vectors and data‐diverse ensembles of Bayesian‐regularized genetic neural networks. QSAR Comb Sci26:27–40

    Google Scholar 

  17. Choi S (2003) Nefazodone (Serzone) withdrawn because of hepatotoxicity. CanMed Assoc J 169:1187–1187

    Google Scholar 

  18. Crum-Brown A, Frazer T (1868–1869) On the connection between chemicalconstitution and physiological action. Part 1. On the physiological action of the ammonium bases, derived from Strychia, Brucia, Thebaia, Codeia, Morphiaand Nicotia. Trans Royal Soc Edinburgh 25:257–274

    Google Scholar 

  19. Cruz JA, Wishart DS (2006) Applications of machine learning in cancerprediction and prognosis. Cancer Inform 2:59–78

    Google Scholar 

  20. DiMasi JA (2002) The value of improving the productivity of the drugdevelopment process: faster times and better decisions. Pharmacoeconomics 20(S3):1–10

    Google Scholar 

  21. DiMasi JA, Hansen RW, Grabowski HG (2003) The price of innovation: newestimates of drug development costs. J Health Econ 22:151–185

    Google Scholar 

  22. Dieppe PA, Ebrahim S, Martin RM, Jüni P (2004) Lessons from the withdrawal ofrofecoxib. Br Med J 329:867–868

    Google Scholar 

  23. Duce C, Micheli A, Solaro R, Starita A, Tiné MR (2006) Prediction ofchemical‐physical properties by neural networks for structures. Macromol Symp 234:13–19

    Google Scholar 

  24. Duce C, Micheli A, Starita A, Tiné MR, Solaro R (2006) Prediction of polymerproperties from their structure by recursive neural networks. Macromol Rapid Commun 27:711–715

    Google Scholar 

  25. Faich GA, Moseley RH (2001) Troglitazone (Rezulin) and hepaticinjury. Pharmacoepidemiol Drug Saf 10:537–547

    Google Scholar 

  26. Filter M, Eichler‐Mertens M, Bredenbeck A, Losch FO, Sharav T, GivehchiA, Walden P, Wrede P (2006) A strategy for the identification of canonical and non‐canonical MHC I‑binding epitopes using an ANN-basedepitope prediction algorithm. QSAR Comb Sci 25:350–358

    Google Scholar 

  27. Fujita T, Iwasa J, Hansch C (1964) A new substituent constant, π,derived from partition coefficients. J Am Chem Soc 86:5175–5180

    Google Scholar 

  28. Furberg CD, Pitt B (2001) Withdrawal of cerivastatin from the worldmarket. Curr Control Trials Cardivasc Med 2:205–207

    Google Scholar 

  29. Ghafourian T, Cronin MTD (2006) The effect of variable selection on thenon‐linear modelling of oestrogen receptor binding. QSAR Comb Sci 25:824–835

    Google Scholar 

  30. Gini G, Craciun MV, König C, Benfenati E (2004) Combining unsupervised andsupervised artificial neural networks to predict aquatic toxicity. J Chem Inf Comput Sci 44:1897–1902

    Google Scholar 

  31. Gleeson MP, Waters NJ, Paine SW, Davis AM (2006) In silico human and ratV ss quantitative structure‐activity relationshipmodels. J Med Chem 49:1953–1963

    Google Scholar 

  32. Goulon‐Sigwalt‐Abram A, Duprat A, Dreyfus G (2005) From Hopfieldnets to recursive networks to graph machines: Numerical machine learning for structured data. Theor Comput Sci344:298–334

    Google Scholar 

  33. Hall LH, Story CT (1996) Boiling point and critical temperature ofa heterogeneous data set: QSAR with atom type electrotopological state indices using artificial neural networks. J Chem InfComput Sci 36:1004–1014

    Google Scholar 

  34. Hall LH, Story CT (1997) Boiling point of a set of alkanes, alcohols andchloroalkanes: QSAR with atom type electrotopological state indices using artificial neural networks. SAR QSAR Environ Res6:139–161

    Google Scholar 

  35. Hansch C (1969) A quantitative approach to biochemicalstructure‐activity relationships. Acc Chem Res 2:232–239

    Google Scholar 

  36. Hansch C, Fujita T (1964) \( { \rho -\sigma -\pi } \) analysis. A method for the correlation of biological activityand chemical structure. J Am Chem Soc 86:1616–1626

    Google Scholar 

  37. Hansch C, Maloney PP, Fujita T, Muir RM (1962) Correlation of biologicalactivity of phenoxyacetic acids with Hammett substituent constants and partition coefficients. Nature 194:178–180

    ADS  Google Scholar 

  38. He L, Jurs PC, Kreatsoulas C, Custer LL, Durham SK, Pearl GM (2005)Probabilistic neural network multiple classifier system for predicting the genotoxicity of quinolone and quinoline derivatives. Chem Res Toxicol18:428–440

    Google Scholar 

  39. Hecht‐Nielsen R (1987) Counterpropagation networks. Appl Optics26:4979–4984

    Google Scholar 

  40. Hecht‐Nielsen R (1988) Applications of counterpropagationnetworks. Neural Netw 1:131–139

    Google Scholar 

  41. Hecht‐Nielsen R (1990) Neurocomputing, Addison‐Wesley,Reading

    Google Scholar 

  42. Hogan V (2000) Pemoline (Cylert): market withdrawal. Can Med Assoc J162:106–106

    Google Scholar 

  43. Hopfield JJ (1982) Neural networks and physical systems with emergentcollective computational abilities. Proc Natl Acad Sci USA 79:2554–2558

    MathSciNet  ADS  Google Scholar 

  44. Hristozov D, Da Costa FB, Gasteiger J (2007) Sesquiterpenelactones‐based classification of the family Asteraceae using neural networks and k‑nearestneighbors. J Chem Inf Model 47:9–19

    Google Scholar 

  45. Huuskonen J (2003) QSAR modeling with the electrotopological state indices:Predicting the toxicity of organic chemicals. Chemosphere 50:949–953

    Google Scholar 

  46. Huuskonen J, Rantanen J, Livingstone D (2000) Prediction of aqueous solubilityfor a diverse set of organic compounds based on atom-type electrotopological state indices. Eur J Med Chem35:1081–1088

    Google Scholar 

  47. Ivanciuc O (1998) Artificial neural networks applications, Part 9. MolNetprediction of alkane boiling points. Rev Roum Chim 43:885–894

    Google Scholar 

  48. Ivanciuc O (1999) Artificial neural networks applications. Part 11. MolNetprediction of alkane densities. Rev Roum Chim 44:619–631

    Google Scholar 

  49. Ivanciuc O (1999) Molecular graph descriptors used in neural networkmodels. In: Devillers J, Balaban AT (eds) Topological Indices and Related Descriptors in QSAR and QSPR. Gordon and Breach Science Publishers, Amsterdam,pp 697–777

    Google Scholar 

  50. Ivanciuc O (1999) The neural network MolNet prediction of alkane enthalpies.Anal Chim Acta 384:271–284

    Google Scholar 

  51. Ivanciuc O (2000) Artificial neural networks applications. Part 12. Theprediction of alkane heat capacities with the MolNet neural network. Rev Roum Chim 45:391–403

    Google Scholar 

  52. Ivanciuc O (2001) New neural networks for structure‐property models. In:Diudea MV (ed) QSPR/QSAR Studies by Molecular Descriptors. Nova Science Publishers, Huntington, pp 213–231

    Google Scholar 

  53. Ivanciuc O (2003) Aquatic toxicity prediction for polar and nonpolar narcoticpollutants with support vector machines. Internet Electron J Mol Des 2:195–208

    Google Scholar 

  54. Ivanciuc O (2003) Graph theory in chemistry. In: Gasteiger J (ed) Handbook ofChemoinformatics, vol 1. Wiley-VCH, Weinheim, pp 103–138

    Google Scholar 

  55. Ivanciuc O (2003) Topological indices. In: Gasteiger J (ed) Handbook ofChemoinformatics, vol 3. Wiley-VCH, Weinheim, pp 981–1003

    Google Scholar 

  56. Ivanciuc O, Rabine J-P, Cabrol DB, Panaye A, Doucet JP (1996)13C NMR chemical shift prediction of sp2 carbon atoms in acyclic alkenes using neural networks. J Chem Inf Comput Sci 36:644–653

    Google Scholar 

  57. Ivanciuc O, Rabine J-P, Cabrol DB, Panaye A, Doucet JP (1997)13C NMR chemical shift prediction of the sp3 carbon atoms in the α position relative tothe double bond in acyclic alkenes. J Chem Inf Comput Sci 37:587–598

    Google Scholar 

  58. Izrailev S, Agrafiotis DK (2002) Variable selection for QSAR by artificial antcolony systems. SAR QSAR Environ Res 13:417–423

    Google Scholar 

  59. Jezierska A, Vračko M, Basak SC (2004) Counter‐propagationartificial neural networks as a tool for the independent variable selection: Structure‐mutagenicity study on aromatic amines. Mol Divers8:371–377

    Google Scholar 

  60. Jurs P (2003) Quantitative structure‐property relationships. In:Gasteiger J (ed) Handbook of Chemoinformatics, vol 3. Wiley-VCH, Weinheim, pp 1314–1335

    Google Scholar 

  61. Kaiser KLE (2003) The use of neural networks in QSARs for acute aquatictoxicological endpoints. J Mol Struct (Theochem) 622:85–95

    ADS  Google Scholar 

  62. Katritzky AR, Pacureanu LM, Dobchev DA, Fara DC, Duchowicz PR, Karelson M(2006) QSAR modeling of the inhibition of glycogen synthase kinase-3. Bioorg Med Chem 14:4987–5002

    Google Scholar 

  63. Keyhani S, Diener‐West M, Powe N (2006) Are development times forpharmaceuticals increasing or decreasing? Health Aff 25:461–468

    Google Scholar 

  64. Khan J, Wei JS, Ringnér M, Saal LH, Ladanyi M, Westermann F, Berthold F,Schwab M, Antonescu CR, Peterson C, Meltzer PS (2001) Classification and diagnostic prediction of cancers using gene expression profiling and artificialneural networks. Nature Med 7:673–679

    Google Scholar 

  65. Kier LB, Hall LH (1976) Molecular Connectivity in Chemistry and DrugResearch. Academic Press, New York

    Google Scholar 

  66. Kier LB, Hall LH (1986) Molecular Connectivity in Structure‐ActivityAnalysis. Research Studies Press, Letchworth

    Google Scholar 

  67. Kier LB, Hall LH (1999) Molecular Structure Description. TheElectrotopological State. Academic Press, San Diego

    Google Scholar 

  68. Kim H-J, Choo H, Cho YS, Koh HY, No KT, Pae AN (2006) Classification ofdopamine, serotonin, and dual antagonists by decision trees. Bioorg Med Chem 14:2763–2770

    Google Scholar 

  69. Kireev DB (1995) ChemNet: A novel neural network based method forgraph/property mapping. J Chem Inf Comput Sci 35:175–180

    Google Scholar 

  70. Ko D, Xu W, Windle B (2005) Gene function classification using NCI-60 cellline gene expression profiles. Comput Biol Chem 29:412–419

    MATH  Google Scholar 

  71. Kohonen T (1989) Self‐Organization and Associative Memory, 3edn. Springer, Berlin

    Google Scholar 

  72. Kohonen T (1995) Self‐Organizing Maps. Springer,Berlin

    Google Scholar 

  73. Kola I, Landis J (2004) Can the pharmaceutical industry reduce attritionrates? Nat. Rev. Drug Discov 3:711–715

    Google Scholar 

  74. Kopp H (1844) Ueber den Zusammenhang zwischen der chemischen Constitution undeinigen physikalischen Eigen‐schaften bei flüssigen Verbindungen. Ann Chem Pharm 50:71–144

    Google Scholar 

  75. Kozioł J (2002) Neural network modeling of melting temperatures forsulfur‐containing organic compounds. Internet Electron J Mol Des 1:80–93

    Google Scholar 

  76. Lasser KE, Allen PD, Woolhandler SJ, Himmelstein DU, Wolfe SN, Bor DH (2002)Timing of new black box warnings and withdrawals for prescription medications. J Am Med Assoc 287:2215–2220

    Google Scholar 

  77. Li H, Ung CY, Yap CW, Xue Y, Li ZR, Cao ZW, Chen YZ (2005) Prediction ofgenotoxicity of chemical compounds by statistical learning methods. Chem Res Toxicol 18:1071–1080

    Google Scholar 

  78. Li H, Ung CY, Yap CW, Xue Y, Li ZR, Chen YZ (2006) Prediction of estrogenreceptor agonists and characterization of associated molecular descriptors by statistical learning methods. J Mol Graph Modell25:313–323

    Google Scholar 

  79. Li H, Yap CW, Ung CY, Xue Y, Cao ZW, Chen YZ (2005) Effect of selection ofmolecular descriptors on the prediction of blood-brain barrier penetrating and nonpenetrating agents by statistical learning methods. J Chem Inf Model45:1376–1384

    Google Scholar 

  80. Lin HH, Han LY, Yap CW, Xue Y, Liu XH, Zhu F, Chen YZ (2007) Prediction offactor Xa inhibitors by machine learning methods. J Mol Graph Modell 26:505–518

    Google Scholar 

  81. Lohninger H (1993) Evaluation of neural networks based on radial basisfunctions and their application to the prediction of boiling points from structural parameters. J Chem Inf Comput Sci33:736–744

    Google Scholar 

  82. Lü WJ, Chen YL, Ma WP, Zhang XY, Luan F, Liu MC, Chen XG, Hu ZD (2008) QSARstudy of neuraminidase inhibitors based on heuristic method and radial basis function network. Eur J Med Chem43:569–576

    Google Scholar 

  83. Mazurek S, Ward TR, Novič M (2007) Counter propagation artificial neuralnetworks modeling of an enantioselectivity of artificial metalloenzymes. Mol Divers 11:141–152

    Google Scholar 

  84. McCulloch WS, Pitts WH (1943) A logical calculus of the ideas immanent innervous activity. Bull Math Biophys 7:115–133

    MathSciNet  Google Scholar 

  85. Meissner M, Schmuker M, Schneider G (2006) Optimized Particle SwarmOptimization (OPSO) and its application to artificial neural network training. BMC Bioinformatics 7:125

    Google Scholar 

  86. Melagraki G, Afantitis A, Makridima K, Sarimveis H, Igglessi‐MarkopoulouO (2006) Prediction of toxicity using a novel RBF neural network training methodology. J Mol Model 12:297–305

    Google Scholar 

  87. Melagraki G, Afantitis A, Sarimveis H, Igglessi‐Markopoulou O,Alexandridis A (2006) A novel RBF neural network training methodology to predict toxicity to Vibrio fischeri. Mol Divers10:213–221

    Google Scholar 

  88. MeyerH (1899) Zur Theorie der Alkoholnarkose, welche Eigenschaft der Anästhetica bedingt ihre narkotische Wirkung. Arch Exp Pathol Pharmakol42:109–118

    Google Scholar 

  89. Micheli A, Portera F, Sperduti A (2005) A preliminary empiricalcomparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains. Neurocomputing64:73–92

    Google Scholar 

  90. Micheli A, Sperduti A, Starita A (2007) An introduction to recursive neuralnetworks and kernel methods for cheminformatics. Curr Pharm Design 13:1469–1495

    Google Scholar 

  91. Micheli A, Sperduti A, Starita A, Bianucci AM (2001) Analysis of the internalrepresentations developed by neural networks for structures applied to quantitative structure‐activity relationship studies of benzodiazepines. J Chem Inf Comput Sci 41:202–218

    Google Scholar 

  92. Minsky ML, Papert SA (1969) Perceptrons. MIT Press,Cambridge

    MATH  Google Scholar 

  93. Moody J, Darken CJ (1989) Fast learning in networks of locally‐tunedprocessing units. Neural Comput 1:281–294

    Google Scholar 

  94. Muresan S, Sadowski J (2005) “In-house likeness”: Comparison oflarge compound collections using artificial neural networks. J Chem Inf Model 45:888–893

    Google Scholar 

  95. Niwa T (2003) Using general regression and probabilistic neural networks topredict human intestinal absorption with topological descriptors derived from two‐dimensional chemical structures. J Chem Inf Comput Sci43:113–119

    Google Scholar 

  96. Niwa T (2004) Prediction of biological targets using probabilistic neuralnetworks and atom-type descriptors. J Med Chem 47:2645–2650

    Google Scholar 

  97. Overton CE (1901) Studien über die Narkose. Zugleich ein Beitrag zurAllgemeinen Pharmakologie. Gustav Fisher Verlag, Jena

    Google Scholar 

  98. Papa E, Villa F, Gramatica P (2005) Statistically validated QSARs, based ontheoretical descriptors, for modeling aquatic toxicity of organic chemicals in Pimephales promelas (fathead minnow). J Chem Inf Model45:1256–1266

    Google Scholar 

  99. Patankar SJ, Jurs PC (2002) Prediction of glycine/NMDA receptor antagonistinhibition from molecular structure. J Chem Inf Comput Sci 42:1053–1068

    Google Scholar 

  100. Patankar SJ, Jurs PC (2003) Classification of inhibitors of protein tyrosinephosphatase 1B using molecular structure based descriptors. J Chem Inf Comput Sci 43:885–899

    Google Scholar 

  101. Pitts WH, McCulloch WS (1947) How we know universals: The perception ofauditory and visual forms. Bull Math Biophys 9:127–147

    Google Scholar 

  102. Plewczynski D, Spieser SAH, Koch U (2006) Assessing different classificationmethods for virtual screening. J Chem Inf Model 46:1098–1106

    Google Scholar 

  103. Rabow AA, Shoemaker RH, Sausville EA, Covell DG (2002) Mining the NationalCancer Institute's tumor‐screening database: Identification of compounds with similar cellular activities. J Med Chem45:818–840

    Google Scholar 

  104. Ripley BD (2008) Pattern Recognition and Neural Networks. CambridgeUniversity Press, Cambridge, 416 pp

    MATH  Google Scholar 

  105. Roche O, Trube G, Zuegge J, Pflimlin P, Alanine A, Schneider G (2002)A virtual screening method for prediction of the hERG potassium channel liability of compound libraries. Chem Bio Chem3:455–459

    Google Scholar 

  106. Rosenblatt F (1962) Principles of Neurodynamics: Perceptrons and the Theoryof Brain Mechanisms. Spartan Books, Washington

    MATH  Google Scholar 

  107. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations byback‐propagating errors. Nature 323:533–536

    ADS  Google Scholar 

  108. Rumelhart DE, McClelland JL (eds) (1986) Parallel DistributedProcessing. MIT Press, Cambridge, 344 pp

    Google Scholar 

  109. Saxena AK, Schaper K-J (2006) QSAR analysis of the time- anddose‐dependent anti‐inflammatory in vivo activity of substituted imidazo[1:2-a]pyridines using artificialneural networks. QSAR Comb Sci 25:590–597

    Google Scholar 

  110. Seierstad M, Agrafiotis DK (2006) A QSAR model of hERG binding usinga large, diverse, and internally consistent training set. Chem Biol Drug Des 67:284–296

    Google Scholar 

  111. Selaru FM, Xu Y, Yin J, Zou T, Liu TC, Mori Y, Abraham JM, Sato F, Wang S,Twigg C, Olaru A, Shustova V, Leytin A, Hytiroglou P, Shibata D, Harpaz N, Meltzer SJ (2002) Artificial neural networks distinguish among subtypes ofneoplastic colorectal lesions. Gastroenterology 122:606–613

    Google Scholar 

  112. Shen Q, Jiang J-H, Jiao C-X, Lin W-Q, Shen G-L, Yu R-Q (2004) Hybridizedparticle swarm algorithm for adaptive structure training of multilayer feed‐forward neural network: QSAR studies of bioactivity of organiccompounds. J Comput Chem 25:1726–1735

    Google Scholar 

  113. Shen Q, Shi W-M, Yang X-P, Ye B-X (2006) Particle swarm algorithm trainedneural network for QSAR studies of inhibitors of platelet‐derived growth factor receptor phosphorylation. Eur J Pharm Sci28:369–376

    ADS  Google Scholar 

  114. Siu F-M, Che C-M (2006) Quantitative structure‐activity (affinity)relationship (QSAR) study on protonation and cationization of α‑amino acids. J Phys Chem A 110:12348–12354

    Google Scholar 

  115. So S-S, Karplus M (1996) Evolutionary optimization in quantitativestructure‐activity relationship: An application of genetic neural networks. J Med Chem 39:1521–1530

    Google Scholar 

  116. So S-S, Karplus M (1996) Genetic neural networks for quantitativestructure‐activity relationships: Improvements and application of benzodiazepine affinity for benzodiazepine/GABA A receptors. J Med Chem 39:5246–5256

    Google Scholar 

  117. Spycher S, Nendza M, Gasteiger J (2004) Comparison of differentclassification methods applied to a mode of toxic action data set. QSAR Comb Sci 23:779–791

    Google Scholar 

  118. Spycher S, Pellegrini E, Gasteiger J (2005) Use of structure descriptors todiscriminate between modes of toxic action of phenols. J Chem Inf Model 45:200–208

    Google Scholar 

  119. Statnikov A, Aliferis CF, Tsamardinos I, Hardin D, Levy S (2005)A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. Bioinformatics21:631–643

    Google Scholar 

  120. Sutherland JJ, O'Brien LA, Weaver DF (2004) A comparison of methods formodeling quantitative structure‐activity relationships. J Med Chem 47:5541–5554

    Google Scholar 

  121. Taskinen J, Yliruusi J (2003) Prediction of physicochemical properties basedon neural network modelling. Adv Drug Deliv Rev 55:1163–1183

    Google Scholar 

  122. Terfloth L, Gasteiger J (2001) Neural networks and genetic algorithms indrug design. Drug Discov Today 6:S102–S108

    Google Scholar 

  123. Tetko IV, Tanchuk VY, Villa AEP (2001) Prediction of n‑octanol/water partition coefficients from PHYSPROP database using artificial neural networks and E-state indices. J ChemInf Comput Sci 41:1407–1421

    Google Scholar 

  124. Todeschini R, Consonni V (2003) Descriptors from molecular geometry. In:Gasteiger J (ed) Handbook of Chemoinformatics, vol 3. Wiley-VCH, Weinheim, pp 1004–1033

    Google Scholar 

  125. Trinajstić N (1992) Chemical Graph Theory. CRC Press, BocaRaton

    Google Scholar 

  126. Varnek A, Kireeva N, Tetko IV, Baskin II, Solov'ev VP (2007) Exhaustive QSPRstudies of a large diverse set of ionic liquids: How accurately can we predict melting points? J Chem Inf Model47:1111–1122

    Google Scholar 

  127. Votano JR, Parham M, Hall LH, Kier LB, Oloff S, Tropsha A, Xie Q, Tong W(2004) Three new consensus QSAR models for the prediction of Ames genotoxicity. Mutagenesis 19:365–377

    Google Scholar 

  128. Votano JR, Parham M, Hall LM, Hall LH, Kier LB, Oloff S, Tropsha A (2006)QSAR modeling of human serum protein binding with several modeling techniques utilizing structure‐information representation. J Med Chem49:7169–7181

    Google Scholar 

  129. Vracko M (2005) Kohonen artificial neural network and counter propagationneural network in molecular structure‐toxicity studies. Curr Comput‐Aided Drug Des 1:73–78

    Google Scholar 

  130. Wagner S, Hofmann A, Siedle B, Terfloth L, Merfort I, Gasteiger J (2006)Development of a structural model for NF-\( { \ifx\letex\relax\Kappa\else K\fi } \)B inhibition of sesquiterpene lactones using self‐organizing neural networks. J Med Chem49:2241–2252

    Google Scholar 

  131. Wan C, Harrington PB (1999) Self‐configuring radial basis functionneural networks for chemical pattern recognition. J Chem Inf Comput Sci 39:1049–1056

    Google Scholar 

  132. WangJ, Johannsen TH, Myklebost O, Hovig E (2003) Tumor classificationand marker gene prediction by feature selection and fuzzy c-means clustering using microarray data. BMC Bioinformatics 4:60

    Google Scholar 

  133. Wang Y-H, Li Y, Li Y-H, Yang S-L, Yang L (2005) Modeling K m values using electrotopological state: Substrates for cytochromeP450 3A4‐mediated metabolism. Bioorg Med Chem Lett 15:4076–4084

    Google Scholar 

  134. Wasserman PD (1989) Neural Computing. Van Nostrand Reinhold, New York, 230pp

    Google Scholar 

  135. Weinstein JN, Kohn KW, Grever MR, Viswanadhan VN, Rubinstein LV, Monks AP,Scudiero DA, Welch L, Koutsoukos AD, Chiausa AJ, Paull KD (1992) Neural computing in cancer drug development: Predicting mechanism of action. Science258:447–451

    ADS  Google Scholar 

  136. Wessel MD, Jurs PC, Tolan JW, Muskal SM (1998) Prediction of humanintestinal absorption of drug compounds from molecular structure. J Chem Inf Comput Sci 38:726–735

    Google Scholar 

  137. Xiao Y-D, Clauset A, Harris R, Bayram E, Santago P, Schmitt JD (2005)Supervised self‐organizing maps in drug discovery, 1. Robust behavior with overdetermined data sets. J Chem Inf Model45:1749–1758

    Google Scholar 

  138. Xu Y, Selaru FM, Yin J, Zou TT, Shustova V, Mori Y, Sato F, Liu TC, Olaru A,Wang S, Kimos MC, Perry K, Desai K, Greenwald BD, Krasna MJ, Shibata D, Abraham JM, Meltzer SJ (2002) Artificial neural networks and gene filteringdistinguish between global gene expression profiles of Barrett's esophagus and esophageal cancer. Cancer Res62:3493–3497

    Google Scholar 

  139. Xue Y, Li H, Ung CY, Yap CW, Chen YZ (2006) Classification of a diverseset of Tetrahymena pyriformis toxicity chemical compounds from molecular descriptors by statistical learning methods. Chem Res Toxicol19:1030–1039

    Google Scholar 

  140. Xue Y, Yap CW, Sun LZ, Cao ZW, Wang JF, Chen YZ (2004) Prediction ofP‑glycoprotein substrates by a support vector machine approach. J Chem Inf Comput Sci 44:1497–1505

    Google Scholar 

  141. Yap CW, Li ZR, Chen YZ (2006) Quantitative structure‐pharmacokineticrelationships for drug clearance by using statistical learning methods. J Mol Graph Modell 24:383–395

    Google Scholar 

  142. Zheng G, Xiao M, Lu XH (2005) QSAR study on the Ah receptor‐bindingaffinities of polyhalogenated dibenzo-p‑dioxins using net atomic‐charge descriptors and a radial basisneural network. Anal Bioanal Chem 383:810–816

    Google Scholar 

  143. Zhou Y-P, Jiang J-H, Lin W-Q, Zou H-Y, Wu H-L, Shen G-L, Yu R-Q (2006)Adaptive configuring of radial basis function network by hybrid particle swarm algorithm for QSAR studies of organic compounds. J Chem Inf Model46:2494–2501

    Google Scholar 

  144. Zupan J (2003) Neural networks. In: Gasteiger J (ed) Handbook ofChemoinformatics, vol 3. Wiley-VCH, Weinheim, pp 1167–1215

    Google Scholar 

  145. Zupan J, Gasteiger J (1999) Neural Networks in Chemistry and DrugDesign. Wiley-VCH, Weinheim

    Google Scholar 

  146. Zupan J, Novič M, Gasteiger J (1995) Neural networks withcounter‐propagation learning‐strategy used for modeling. Chemometrics Intell Lab Syst 27:175–187

    Google Scholar 

  147. von Korff M, Hilpert K (2006) Assessing the predictive power of unsupervisedvisualization techniques to improve the identification of GPCR‐focused compound libraries. J Chem Inf Model46:1580–1587

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biochemistry and Molecular Biology, University of Texas Medical Branch, Galveston, USA

    Ovidiu Ivanciuc

Authors
  1. Ovidiu Ivanciuc
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. RAMTECH LIMITED, 122 Escalle Lane, Larkspur, CA, 94939, USA

    Robert A. Meyers Ph. D. (Editor-in-Chief) (Editor-in-Chief)

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag

About this entry

Cite this entry

Ivanciuc, O. (2009). Drug Design with Artificial Neural Networks. In: Meyers, R. (eds) Encyclopedia of Complexity and Systems Science. Springer, New York, NY. https://doi.org/10.1007/978-0-387-30440-3_134

Download citation

Publish with us

Policies and ethics

Search

Navigation